Archive

Tag Archives: linked data

Trip Report: ESWC 2019

June 28, 2019
academia, trip report
Leave a comment

From June 2 – 6, I had the pleasure of attending the Extended Semantic Web Conference 2019 held in Portorož, Solvenia. After ESWC, I had another semantic web visit with Axel Polleres, Sabrina Kirrane and team in Vienna. We had a great time avoiding the heat and talking about data search and other fun projects. I then paid the requisite price for all this travel and am just now getting down to emptying my notebook. Note to future self, do your trip reports at the end of the conference.

It’s been awhile since I’ve been at ESWC so it was nice to be back. The conference I think was down a bit in terms the number of attendees but the same community spirit and interesting content (check out the award winners) was there.  Shout out to Miriam Fernandez and the team for making it an invigorating event:

So what was I doing there. I was presenting work at the Deep Learning for Knowledge Graph workshop on trying to see if we could answer structured (e.g. SPARQL) queries over text (paper):

The workshop itself was packed. I think there were about 30-40 people in the room.  In addition to the presenting the workshop paper, I was also one of the mentors for the doctoral consortium. It was really nice to see the next up and coming students who put a lot of work into the session: a paper, a revised paper, a presentation and a poster. Victor and Maria-Esther did a fantastic job organizing this.

So what were my take-aways from the conference. I had many of the same thoughts coming out of this conference that I had when I was at the recent AKBC 2019 especially around the ideas of polyglot representation and scientific literature understanding as an important domain driver (e.g. a Predicting Entity Mentions in Scientific Literature and Mining Scholarly Data for Fine-Grained Knowledge Graph Construction. ) but there were some additional things as well.

Target Schemas

The first was a notion that I’ll term “target schemas”. Diana Maynard in her keynote talked about this. These are little conceptually focused ontologies designed specifically for the application domain. She talked about how working with domain experts to put together these little ontologies that could be the target for NLP tools was really a key part of building these domain specific analytical applications.   I think this notion of simple schemas is also readily apparent in many commercial knowledge graphs.

The notion of target schemas popped up again in an excellent talk by Katherine Thornton on the use of ShEx. In particular, I would call out the introduction of an EntitySchema part of Wikidata. (e.g. Schema for Human Gene or Software Title). These provide these little target schemas that say something to the effect of “Hey if you match this kind of schema, I can use them in my application”. I think this is a really powerful development.

The third keynote by Daniel Quercia was impressive. The Good City Life project about applying data to understand cities just makes you think. You really must check it out. More to this point of target schemas, however, was the use of these little conceptual descriptions in the various maps and analytics he did. By, for example, thinking about how to define urban sounds or feelings on a walking route, his team was able to develop these fantastic and useful views of the city.

I think the next step will be to automatically generate these target schemas. There was already some work headed into that direction. One was Generating Semantic Aspects for Queries , which was about how to use document mining to select which attributes for entities one should show for an entity. Think of it as selecting what should show up in a knowledge graph entity panel. Likewise, in the talk on Latent Relational Model for Relation Extraction, Gaetano Rossiello talked about how to think about using analogies between example entities to help extract these kind of schemas for small domains:

m97pj-zb.jpeg

I think this notion is worth exploring more.

Feral Spreadsheets

What more can I say:

We need more here. Things like MantisTable. Data wrangling is the problem. Talking to Daniel about the data behind his maps just confirmed this problem as well.

Knowledge Graph Engineering

This was a theme that was also at AKBC – the challenge of engineering knowledge graphs. As an example, the Knowledge Graph Building workshop was packed. I really enjoyed the discussion around how to evaluate the effectiveness of data mapping languages led by Ben de Meester especially with emphasis around developer usability. The experiences shared by the team from the industrial automation from Festo were really insightful. It’s amazing to see how knowledge graphs have been used to accelerate their product development process but also the engineering effort and challenges to get there.

GBVSKwXC

Likewise, Peter Haase in his audacious keynote (no slides – only a demo) showed how far we’ve come in the underlying platforms and technology to be able to create commercially useful knowledge graphs. This is really thanks to him and the other people who straddle the commercial/research line. It was neat to see the Open PHACTS style biomedical knowledge graph being built using SPARQL and api service wrappers:

V9RbjOo_.jpeg

However, still these kinds of wrappers need to be built, the links need to be created and more importantly the data needs to be made available. A summary of challenges:

Overall, I really enjoyed the conference. I got a chance to spend sometime with a bunch of members of the community and it’s exciting to see the continued excitement and the number of new research questions.

Random Notes

 

Trip Report: Language, Data and Knowledge 2017

June 28, 2017
academia, linked data, trip report
Leave a comment

Last week, I was the first Language, Data and Knowledge Conference (LDK 2017) hosted in Galway, Ireland. If you show up at a natural language processing conference (especially someplace like LREC) you’ll find a group of people who think about and use linked/structured data. Likewise, if you show up at a linked data/semantic web conference, you’ll find folks who think about and use NLP. I would characterize LDK2017 as place where that intersection of people can hang out for a couple of days.

The conference had ~80 attendees from my count. I enjoyed the setup of a single track, plenty of time to talk, and also really trying to build the community by doing things together. I also enjoyed the fact that there were 4 keynotes for just two days. It really helped give spark to the conference.

Here are some my take-aways from the conference:

Social science as a new challenge domain

Antal van den Bosch gave an excellent keynote emphasizing the need for what he termed holistic approach to language especially for questions in the humanities and social science (tutorial here). This holistic approach takes into account the rich context that word occur in. In particular, he called out the notions of ideolect and socialect that are ways word are understood/used individually and in a particular social group. He are argued the understanding of these computational is a key notion in driving tasks like recommendation.

I personally was interested in Antal’s joint work with Folgert Karsdorp (checkout his github repos!) on Story Networks – constructing networks of how stories are told and retold. For example, how the story of Red Riding Hood has morphed and changed overtime and what are the key sources for its work. This reminded me of the work on information diffusion in social networks. This has direct bearing on how we can detect and track how ideas and technologies propagate in science communication.

I had a great discussion with SocialAI team (Erica Briscoe & Scott Appling) from Georgia Tech about their work on computational social science. In particular, two pointers: the new DARPA next generation social science program to scale-up social science research and their work on characterizing technology capabilities from data for innovation assessment.

Turning toward the long tail of entities

There were a number of talks that focused on how to deal with entities that aren’t necessarily popular. Bichen Shi presented work done at Nokia Bell Labs on entity mention disambiguation. They used Apache Spark to train 700,000 classifiers – one per every entity mention in wikipedia. This allowed them to obtain much more accurate per-mention entity links. Note they used Gerbil for their evaluation. Likewise, Hendrik ter Horst focused on entity linking specifically targeting technical domains (i.e. MeSH & chemicals). During Q/A it was clear that straight-up gazeetering provides an extremely strong baseline in this task. Marieke van Erp presented work on fine-grained entity typing in Spanish and Dutch using word embeddings to go classify hundreds up types.

Natural language generation from KBs is worth a deeper look

Natural language generation from knowledge bases continues a pace. Kathleen McKeown‘s keynote touched on this, in particular, her recent work on mining paraphrasal templates that combines both knowledge bases and free text.  I was impressed with the work of Nina Dethlefs on using deep learning for generating textual description from  a knowledge base. The key insight was how to quickly generate systems to do NLG where the data was sparse using hierarchical composition. In googling around when writing this trip report I stumbled upon Ehud Reiter’s blog which is a good read.

A couple of nice overview slides

While not a theme, there we’re some really nice slides describingfundamentals.

From C. Maria Keet:

2017-06-20 10.09.40

From Christian Chiarcos/Bettina Klimek:

2017-06-20-11-09-34.jpg

From Sangha Nam

2017-06-19 11.07.02

Overall, it was a good kick-off to a conference. Very well organized and some nice research.

Random Thoughts

Trip Report: Challenges in Extracting and Managing References

April 5, 2017
academia, linked data, trip report
Leave a comment

At the end of last week, I was at a small workshop held by the EXCITE project around the state of the art in extracting references from academic papers (in particular PDFs). This was an excellent workshop that brought together people who are deep into the weeds of this subject including, for example, the developers of ParsCit and CERMINE. While reference string extraction sounds fairly obscure the task itself touches on a lot of the challenges one needs in general for making sense of the scholarly literature.

Begin aside: Yes, I did run a conference called Beyond the PDF 2 and  have been known to tweet things like:

But, there’s a lot of great information in papers so we need to get our machines to read. end aside.

You can roughly catergorize the steps of reference extraction as follows:

  1. Extract the structure of the article.  (e.g. find the reference section)
  2. Extract the reference string itself
  3. Parsing the reference string into its parts (e.g. authors, journal, issue number, title, …)

Check out these slides from Dominika Tkaczyk that give a nice visual overview of this process. In general, performance on this task is pretty good (~.9 F1) for the reference parsing step but gets harder when including all steps.

There were three themes that popped out for me:

  1. The reading experience
  2. Resources
  3. Reading from the image

The Reading Experience

Min-Yen Kan gave an excellent talk about how text mining of the academic literature could improve the ability for researchers to come to grips with the state of science. He positioned the field as one where we have the ground work  and are working on building enabling tools (e.g. search, management, policies) but there’s still a long way to go in really building systems that give insights to researchers. As custodian of the ACL Anthology about trying to put these innovations into practice. Prof. Kan is based in Singapore but gave probably one of the best skype talks I have ever been part of it. Slides are below but you should check it out on youtube.

Another example of improving the reading experience was David Thorne‘s presentation around some of the newer things being added to Utopia docs – a souped-up PDF reader. In particular, the work on the Lazarus project which by extracting assertions from the full text of the article allows one to traverse an “idea” graph along side the “citation” graph. On a small note, I really like how the articles that are found can be traversed in the reader without having to download them separately. You can just follow the links. As usual, the Utopia team wins the “we hacked something really cool just now” award by integrating directly with the Excite projects citation lookup API.

Finally, on the reading experience front. Andreas Hotho presented BibSonomy the social reference manager his research group has been operating over the past ten years. It’s a pretty amazing success resulting in 23 papers, 160 papers use the dataset, 96 million google hits, ~1000 weekly active users active. Obviously, it’s a challenge running this user facing software from an academic group but clearly it has paid dividends. The main take away I had in terms of reader experience is that it’s important to identify what types of users you have and how the resulting information they produce can help or hinder in its application for other users (see this paper).

Resources

The interesting thing about this area is the number of resources available (both software and data) and how resources are also the outcome of the work (e.g. citation databases).  Here’s a listing of the open resources that I heard called out:

This is not to mention the more general sources of information like, CiteSeer, ArXiv or PubMed, etc. What also was nice to see is how many systems built on-top of other software. I was also happy to see the following:

An interesting issue was the transparency of algorithms and quality of the resulting citation databases.  Nees Jan van Eck from CWTS and developer of VOSViewer gave a nice overview of trying to determine the quality of reference matching in the Web of Science. Likewise, Lee Giles gave a review of his work looking at author disambiguation for CiteSeerX and using an external source to compare that process. A pointer that I hadn’t come across was the work by Jurafsky on author disambiguation:

Michael Levin, Stefan Krawczyk, Steven Bethard, and Dan Jurafsky. 2012. Citation-based bootstrapping for large-scale author disambiguation. Journal of the American Society for Information Science and Technology 63:5, 1030-1047.

Reading from the image

In the second day of the workshop, we broke out into discussion groups. In my group, we focused on understanding the role of deep learning in the entire extraction process. Almost all the groups are pursing this.

I was thankful to both Akansha Bhardwaj and Roman Kern for walking us through their pipelines. In particular, Akansha is using scanned images of reference sections as her source and starting to apply CNN’s for doing semantic segmentation where they were having pretty good success.

We discussed the potential for doing the task completely from the ground up using a deep neural network. This was an interesting discussion as current state of the art techniques already use quite a lot of positional information for training This can be gotten out of the pdf and some of the systems already use the images directly. However, there’s a lot of fiddling that needs to go on to deal with the pdf contents so maybe the image actual provides a cleaner place to start. However, then we get back to the issue of resources and how to appropriately generate the training data necessary.

Random Notes

  • The organizers set-up a slack backchannel which was useful.
  • I’m not a big fan of skype talks, but they were able to get two important speakers that way and they organized it well. When it’s the difference between having field leaders and not, it makes a big difference.
  • EU projects can have a legacy – Roman Kern is still using code from http://code-research.eu where Mendeley was a consortium member.
  • Kölsch is dangerous but tasty
  • More workshops should try the noon to noon format.

 

 

Trip Report: ISWC 2015

October 20, 2015
academia, trip report
4 Comments

Last week, I hung out in Bethlehem, Pennsylvania for the the 14th International Semantic Web Conference. Bethlehem is famous for the Lehigh University Benchmark  (LUBM) and Bethlehem Steel. This is the major conference focused on the intersection of semantics and web technologies. In addition to being technically super cool, it was a great chance for me to meet many friends and make some new ones.

Let’s begin with some stats:

  • ~450 attendees
  • The conference continues to be selective:
    • Research track: 22% acceptance rate
    • Empirical studies track: 29% acceptance rate
    • In-use track: 40% acceptance rate
    • Datasets and Ontologies: 22% acceptance rate
  • There were 265 submissions across all tracks which is surprisingly the same number as last year.
  • More stats and info in Stefan’s slides (e.g. move to Portugal if you want to get your papers in the conference.)
  • Fancy visualizations courtesy of the STKO group

Before getting into what I thought were the major themes of the conference, a brief note. Reviewing is at the heart of any academic conference. While we can always try and improve review quality, it’s worth calling out good reviewing. The best reviewers were Maribel Acosta (research) and Markus Krötzsch (applied). As data sets and ontologies track co-chair, I can attest to how important good reviewers are.  For this new track we relied heavily on reviewers being flexible and looking at these sorts of contributions differently. So thanks to them!

For me there were three themes of ISWC:

  1. The Spectrum of Entity Resolution
  2. The Spectrum of Linked Data Querying
  3. Buy more RAM

The Spectrum of Entity Resolution

Maybe its because I attended the NLP & DBpedia workshop or the conversation I had about string similarity with Michelle Cheatham, but one theme that I saw was the continued amalgamation of natural language processing (NLP) style entity resolution with database entity resolution (i.e. record linkage). This movement stems from the fact that an increasing amount of linked data is a combination of data extracted from semi-structured sources as well as from NLP. But in addition to that, NLP sources rely on some of these semi-structured datasources to do NLP.

Probably, the best example of that idea is the work that Andrew McCallum presented in his keynote on “epistemlogical knowledge bases”.

Briefly, the idea is to reason with all the information coming from both basic low level NLP (e.g. basic NER, or even surface forms) as well as the knowledge base jointly (plus, anything else) to generate a knowledge base.  One method to do this is universal schemas. For a good intro, check out Sebastien Riedel’s slides.

From McCallum, I like the following papers which gives a good justification and results of doing collective/joint inference.

(Self promotion aside: check out Sara Magliacane’s work on Probabilistic Soft Logics for another way of doing joint inference.)

Following on from this notion of reasoning jointly, Hulpus, Prangnawarat and Hayes showed how to use the graph-based structure of linked data to to perform joint entity and word sense disambiguation from text. Likewise, Prokofyev et al. use the properties of a knowledge graph to perform better co-reference resolution. Essentially, they use this background knowledge to split the clusters of co-referrent entities produced by Stanford CoreNLP. On the same idea, but for more structured data, the TableEL system uses a joint model with soft constraints to perform entity linking for web tables, improving performance by up-to 75% on web tables. (code & data)

One approach to entity linking that I liked was from the Raphael Troncy’s crew titled “Reveal Entities From Texts With a Hybrid Approach” (paper, slides). (Shouldn’t it be “Revealing..”?). They showed that by using essentially the provenance of the data sources they are able to build an adaptive entity linking pipeline. Thus, one doesn’t necessarily have to do as much domain tuning to use these pipelines.

While not specifically about entity resolution, a paper worth pointing out is Type-Constrained Representation Learning in Knowledge Graphs from Denis Krompaß, Stephan Baier and Volker Tresp. They show how background knowledge about entity types can help improve link prediction tasks for generating knowledge graphs. Again, use the kitchen sink and you’ll perform better.

There were a couple of good resources presented for entity resolution tasks.  Bryl, Bizer and Paulheim produced a dataset of surface forms for dbpedia entities. They were able to boost performance up to 20% for extracting accurate surface forms for entities through filtering. Another tool, LANCE looks great for systematically generating benchmark and test sets for instance matching (i.e. entity linking). Also, Michel Dumontier presented work that had a benchmark for entity linking from the life sciences domain.

Finally, as we get better at entity resolution, I think people will turn towards fusion (getting the best possible representation for a real world entity). Examples include:

The Spectrum of Linked Data Querying

So Linked Data Fragments from Ruben Verborgh was the huge breakout of the conference. Oscar Corcho’s excellent COLD keynote was a riff off thinking about the spectrum (from data dumps through to full sparql queries) that was introduced by Reuben. Another example was the work of Maribel Acosta and Maria-Esther Vidal on “Networks of Linked Data Eddies: An Adaptive Web Query Processing Engine for RDF Data”. They developed an adaptive client side spraql query engine for linked data fragments. This allows the server side to support a much simpler API by having a more intelligent client side. (An aside, kids this is how a technical talk should be done. Precise, clean, technical, understandable. Can’t wait to have the the video lecture for reference.)

Even the most centralized solution, the LODLaundromat which is a clean crawl of the entire web of data supports Linked Data Fragments. In some sense, by asking the server to do less you can handle more linked data, and thus do more powerful analysis. This is exemplified by the best paper LODLab byLaurens Rietveld, Wouter Beek, and Stefan Schlobach, which allowed for the reproduction of 3 existing analysis of the web of data at scale.

I think Olaf Hartig, in his paper on LDQL, framed the problem best as (N, Q) (slides). First define the “crawl” of the web you want to query (N)  and then define the query (Q). When we think about what and where are crawls are, we can think about what execution strategies and types of queries we can best support. Or put another way:

More Main Memory = better Triple Stores

Designing scalable graph / triple stores has always been a challenge. We’ve been trapped by the limits of RAM. But computer architecture is changing, and we now have systems that have a lot of main memory either in one machine or across multiple machines. This is a boon to triple stores and graph processing in general. See for example Leskovec team’s work from SIGMOD:

We saw that theme at ISWC as well:

Moral of the story: Buy RAM

Conclusion

This years conference explored the many spectra of the combination of the web and semantics. I liked the mix of methods used by papers and the range of practical (the industry session was packed) to theoretical results. I also think the community is no longer hemmed in by the standards but are using them as solid starting point. This was pointed out by Ian Horrocks in his keynote:
https://twitter.com/txkuhn/status/654654988623327232
Additionally, this flexibility was exemplified by the best applied paper, “Building and Using a Knowledge Graph to Combat Human Trafficking” by  Pedro Szekely et al.. They used the parts of the semantic web stack that helped (like ontologies and JSON-LD) but used elastic search for storage to create a vital and important solution to a real challenging problem.
Overall, this was an excellent conference.  Next year’s conference is in Kobe, I hope you submit some great papers and I’ll seen you there!

Random Thoughts

Preview: ISWC 2015 Data & Ontologies Track

October 6, 2015
academia, events, linked data
2 Comments

Next week is the 2015 International Semantic Web Conference. I had the opportunity with the Michel Dumontier to chair a new track on Datasets and Ontologies. A key part of of the Semantic Web has always been shared resources, whether it’s common standards through the W3C or open datasets like those found in the LOD cloud. Indeed, one of the major successes of our community is the availability of these resources.

ISWC over the years has experimented with different ways of highlighting these contributions and bringing them into the scientific literature. For the past couple of years, we have had an evaluation track specifically devoted to reproducibility and evaluation studies. Last year datasets were included to form a larger RDBS track. This year we again have a specific Empirical Studies and Evaluation track along side the Data & Ontologies track.

The reviewers had a tough job for this track. First, it was new so it’s hard to make a standard judgment. Secondly, we asked reviewers not only to review the paper but the resource itself along a number of dimensions. Overall, I think they did a good job. Below you’ll find the resources chosen for presentation at the conference and a brief headline of what to me is interesting about the paper. In the spirt of the track, I link to the resource as well as the paper.

Datasets

  •  Automatic Curation of Clinical Trials Data in LinkedCT by Oktie Hassanzadeh and Renée J Miller (paper) – clinicaltrials.gov published as linked data in an open and queryable. This resource has been around since 2008. I love the fact that they post downtime and other status info on twitter https://twitter.com/linkedct
  • LSQ: Linked SPARQL Queries Dataset by Muhammad Saleem, Muhammad Intizar Ali, Qaiser Mehmood, Aidan Hogan and Axel-Cyrille Ngonga Ngomo (paper). – Query logs are becoming an ever more important resource from everything from search engines to database query optimization. See for example USEWOD. This resource provides queryable versions in SPARQL of the query logs from several major datasets including dbpedia and linked geo data.
  • Provenance-Centered Dataset of Drug-Drug Interactions by Juan Banda, Tobias Kuhn, Nigam Shah and Michel Dumontier (paper) – this resources provides aggregated set of drug-drug interactions coming from 8 different sources. I like how they provided a doi for the bulk download of their datasource as well as spraql endpoint. It also uses nanopublications as the representation format.
  • Semantic Bridges for Biodiversity Science by Natalia Villanueva-Rosales, Nicholas Del Rio, Deana Pennington and Luis Garnica Chavira (paper) – this resource allows biodiversity scientist to work with species distribution models. The interesting thing about this resource is that it not only provides linked data, a spraql endpoint and ontologies but also semantic web services (i.e. SADI) for orchestrating these models.
  • DBpedia Commons: Structured Multimedia Metadata for Wikimedia Commons by Gaurav Vaidya, Dimitris Kontokostas, Magnus Knuth, Jens Lehmann and Sebastian Hellmann  (paper) – this is another chapter in exposing wikimedia content as structured data. This resource provides structured information for the media content in Wikimedia commons. Now you can spraql for all images with a CC-by-sa v2.0 license.

Ontologies

Overall, I think this is a good representation of the plethora of deep datasets and ontologies that the community is creating.  Take a minute and check out these new resources.

Trip Report: WWW 2015

May 27, 2015
events, trip report
3 Comments

Last week I was in Florence Italy for the 23rd International World Wide Web Conference (WWW 2015). This is the leading computer science conference focused on web technology writ large. It’s a big conference – 1400 attendees this year. WWW is excellent for getting a good bearing on the latest across multiple subfields in computer science. Another way to say it is that I run into friends from the semantic web community, NLP community, data mining community, web standards community, the scholarly communication community, etc.. I think on the Tuesday night I traversed four different venues hanging out with various groups.

This is the first time since 2010 that I attended WWW. It was good to be back. I was there the entire week so there was a ton but I’ll try to boil what I saw down into 3 takeaways. But first…

What was I doing there?

First, was that I co-authored a research track paper with Marcin Wylot and Philippe Cudré-Mauroux of the eXascale Infolab (cool name) on Executing Provenance Queries over Web Data (slides, paper). We showed that because of the highly selective nature of provenance on the web of data, we can actually improve query performance within a triple store. I was super happy to have this accepted given the ~14%! acceptance rate.

Second, I gave the opening talk of the Semantics, Analytics, Visualisation: Enhancing Scholarly Data (SAVE-SD) workshop. I discussed the current state of scholarly productivity and used the notion of the burden of knowledge as a motivation for knowledge graphs as a mechanism to help increase that productivity. I even went web for my slides.

Continuing on the theme of knowledge graphs, I participated on a panel in the industry track around knowledge graphs. More thoughts on this coming up.

Knowledge graph panel www

The Takeaways

From my perspective there were three core takeaways:

  1. Knowledge Graphs/Bases everywhere
  2. Assume the Web
  3. Scholarly applications are interesting applications

1. Knowledge Graphs/Bases everywhere

I could call this Entities everywhere. Perhaps, it was the sessions I chose to attend but it felt like when I was at the conference in 2010 where every other paper was about online advertising. There were a ton of papers on entity linking, entity disambiguation, entity (etc.) many others had knowledge base construction as a motivation.

2015-05-21 14.49.54

There were two tutorials on knowledge graphs both of them were full and the one from Google/Facebook involved moving to a completely new room. Both were excellent. The one from the Yago team has really good material.  As a side note, it was interesting to sit-in on tutorials where I already have a decent handle on the material. It let me compare my own intellectual framework for the material and others out there. For example, I liked the Yago tutorial’s distinction between source-centric and yield-centric information extraction and how we pursue the yield approach when doing automated knowledge base construction. A recommended exercise for the reader.

Beyond just being a plethora of stuff, I think our panel discussion highlighted themes that appeared across several papers.

Dealing with long tail entities
In general, approaches to knowledge base construction have relied on well known entities (e.g. wikipedia) and frequency (you’re mentioned a lot, you’re an entity). For many domain specific entities, for example in science, and also emergent entities this is a challenge. A number of authors tried to tackle this by:

  • looking at web page titles as a potential data source for entities (Song et al.)
  • use particular types of web tables to help assign entities to classes (Wang et al.)
  • use social context help entity extraction (Jie Tang et al. )
  • discover new meta relations between entities (Meng et al.)

Quality
All the organizations on the industry panel spend significant resources on quality maintenance of their knowledge graphs. The question here is how to best decrease the amount of human input and increase automation.

An interesting example that was talked about quite frequently is the move of Freebase to Wikidata. Wikidata runs under the same guidelines as Wikipedia so all facts need to have claims grounded in sources from the Web. Well it turns out this is difficult because many facts are sourced from Wikipedia itself. This kind of dare I say it provenance is really important. Most current large scale knowledge graphs support provenance but as we automate more it would be nice to be able to automatically judge these sources using that provenance.

One paper that I saw that addressed quality issues this was GERBIL – General Entity Annotator Benchmarking Framework. This 25 author paper! devised a common framework for testing entity linking tools. It’s great to see the community looking at these sorts of common QA frameworks.

Multimedia
This seemed to be bubbling up. On the panel, the company Tagasauris was looking at constructing a mediaGraph by analyzing video content. During the Yago tutorial, the presenters mentioned potential future work on extracting common sense knowledge by looking at videos. In general, both extraction of facts from multimedia but also using knowledge graphs to understand multimedia seems like a challenging but fruitful area. One particular example was the paper “Tagging Personal Photos with Transfer Deep Learning”. What was cool was the injection of a personal photo ontology into the training of the network as priors. This led to both better results but probably more impotently decreased the training time. Another example is the work from Gerhard Weikum’s group on extracting knowledge from movie scripts. 

Finally, as I commented at the Linked Data on the Web Workshop, the growth of knowledge graphs is a triumph of the semantic web and linked data. Making knowledge bases open and available on the Web using reusable schemes has really been a boon to the area.

2. Assume the Web

It’s obvious but is worth repeating: the web is really big!

These stats were from Andrei Broder’s excellent keynote. The size of the web motivates the need for better web technology (e.g. search) and as that improves so do our expectations. Broder called out three axes of progress

  1. scaling up with quality
  2. faster response
  3. higher functionality levels

We progress on all these dimensions. But the scale of the web doesn’t just change the technology we need to develop but it changes our methods.

For example, a paper I liked a lot was “Leveraging Pattern Semantics for Extracting Entities in Enterprises”. This bares resembles towards problems we face extracting entities that are not found on the web because there only mentioned within a private environment (e.g. internal product names). But even in this environment they rely on the Web. They rank semantic patterns they extract by using relations extracted from the web.

For me, it means that even if the application isn’t necessarily for “the web”, I should think about the web as a potential part of the solution.

3 Scholarly applications are interesting applications

I’m biased, but I think scholarly applications are particularly interesting and you saw that at WWW. I attended two workshops dealing with technology and scholarship. SAVE-SD and Big Scholar. I was particularly impressed with the scholarly knowledge graph that’s being built on-top of the Bing Satori Knowledge Graph, which covers venues, authors, papers, and organizations from 100 million papers. (It seems there are probably 120 million total on the web.) At their demo they showed some awesome queries that you can do like:  “papers on multiple sclerosis citing artificial intelligence” Another example is venues appearing in the side of bing searches with related venues, due dates, etc:

See Kuansan Wang’s (@kuansanw) talk for more info (slides). As far as I understand, MSR will also be releasing the Microsoft Academic Graph for experimentation in a couple of weeks. Based on this graph MSR is co-organizing with Antonio Gulli from Elsevier the WSDM Cup in 2016

It was a pleasure to meet C. Lee Giles of CiteSeerX. It was good seeing an overview of that system and he had some good pointers (e.g. GROBID for metadata extraction and ParsCit for citation extraction).

From SAVE-SD there were two papers that caught my eye:

There were also a number of main track papers that applied methods to scholarly content.

Overall, WWW 2015 was a huge event so this trip report really is just what I could touch. I didn’t even get the chance to go to the W3C sessions and Web Science talks. You can check out all the proceedings here, definitely worth a look.

Random thoughts

  • The web isn’t scale free – it’s log-log. Gotta check out Clauset et al 2009, Power-law distributions in empirical data
  • If you’re a researcher remember that Broder’s “A taxonomy of web search” – was originally rejected from WWW 2002, it now has 1700+ citations.
  • Aidan Hogan + 1 for colorful slides and showing that we need to just deal with blank nodes and not get so hung up about it.  (paper, code)
  • If you do machine learning, do your parameter studies. Most papers had them.
  • PROV and information diffusion combined. So awesome.
  • Ah conference internet… It’s always hard.
  • People are hiring like crazy. Booths from Baidu, Facebook, Yahoo, LinkedIn. Oh, and never discount how frisbee’s can motivate highly educated geeks.
  • On the hiring note, I liked how the companies listed their attendees and their talks.
  • Tons and tons of talks with authors from companies. I should really do some stats. It was like every paper.
  • Italy, food, florentine steak – yummy!
  • Corollary, running is necessary but running in Florence is beautiful. Head by the Duomo across the river and up through the gardens.
  • What you can do with four square data:  2015-05-21 11.27.11
  • Larry and Sergei won the test of time award. 
  • Gotta ask the folks at Insight about their distributional semantics work.

My talking head at EDF 2014

April 6, 2014
interdisciplinary research, linked data, provenance, talks
Leave a comment

A couple of weeks ago, I was at the European Data Forum in Athens talking about the Open PHACTS project. You can find a video of my talk with slides here. Slides are embedded below.

Trip Report: ISWC 2013

November 5, 2013
academia, events, linked data
2 Comments

It’s been about a week since I got from Australia attending the International Semantic Web Conference  (ISWC 2013).  This is the premier forum for the latest in research on using semantics on the Web. Overall, it was a great conference – both well run and there was a good buzz. (Note, I’m probably a bit biased – I was  chair of this year’s In-Use track) .

ISWC is a fairly hard conference to get into and the quality is strong.

More importantly, almost all the talks I went to were worth thinking about. You can find the proceedings of the conference online either as a complete zip here or published by Springer. You can find more stats on the conference here.

As an aside, before digging into the meat of the conference – Sydney was great. Really a fantastic city – very cosmopolitan and with great coffee. I suggest Single Origin Roasters.  Also, Australia has wombats – wombats are like the chillest animal ever.

Wombat

From my perspective, there were three main themes to take away from the conference:

  1. Impressive applications of semantic web technologies
  2. Core ontologies as the framework for connecting complex integration and retrieval tasks
  3. Starting to come to grips with messiness

Applications

We are really seeing how semantic technologies can power great applications. All three keynotes highlighted the use of Semantic Tech. I think Ramanathan Guha’s keynote probably highlighted this the best in his discussion of the growth of schema.org.

Beyond the slide above, he brought up representatives from Yandex, Yahoo, and Microsoft on stage to join Google to tell how they are using schema.org. Drupal and WordPress will have schema.org in their cores in 2014. Schema.org is being used to drive everything from veteran friendly job search, to rich pins on Pinterest and enabling Open Table reservations to be easily put into your calendar. So schema.org is clearly a success.

Peter Mika presented a paper on how Yahoo is using ontologies to drive entity recommendations in searches. For example, you search for Brad Pitt and they show you related entities like Angelina Jolie or  Fight Club. The nice thing about the paper is that it showed how the deployment in production (in Yahoo! Web Search in the US) increases click through rates.

Roi Blanco, Berkant Barla Cambazoglu, Peter Mika, Nicolas Torzec: Entity Recommendations in Web Search. International Semantic Web Conference (2) 2013: 33-48

I think it was probably Yves Raimond’s conference – he showed some amazing things being done at the BBC using semantic web technology. He had an excellent keynote at the COLD workshop – also highlighting some challenges on where we need to improve to ease the use of these technologies in production. I recommend you check out the slides above. Of all the applications, their work on mining the world service archive  of the BBC to enrich content being created. This work won the Semantic Web Challenge.

In the biomedical domain, there were two  papers showing how semantics can be embedded in tools that regular users use.  One showed how the development of ICD-11 (ICD is the most widely used clinical classification developed by the WHO) is  supported using semtech. The other I liked was the use of excel templates (developed using RightField) that transparently captured data according to a domain model for Systems biology.

Also in the biomedical domain, IBM presented an approach for using semantic web technologies to help coordinate health and social care at the semantic web challenge.

Finally, there was a neat application presented by Jane Hunter applying these technologies to art preservation: The Twentieth Century in Paint.

I did a review of all the in-use papers leading up to the conference but it’s good enough to say that there were numerous impressive applications. Also, I think it says something about the health of the community when you see slides like this:

Core Ontologies + Other Methods

There were a number of interesting papers that were around the idea of using a combination of well-known ontologies and then either record linkage or other machine learning methods to populate knowledge bases.

A paper that I like a lot (and also won the best student paper) was titled Knowledge Graph Identification (by Jay Pujara, Hui Mia, Lise Getoor and William Cohen) sums it up nicely:

Our approach, knowledge graph identification (KGI) combines the tasks of entity resolution, collective classification and link prediction mediated by rules based on ontological information.

Interesting papers under this theme were:

From my perspective, it was also nice to see the use of the W3C Provenance Model (PROV) as one of these core ontologies in many different papers and two of the keynotes. People are using it as a substructure to do a number of different applications – I intend to write a whole post on this – but until then here’s proof by twitter:

Coming to grips with messiness

It’s pretty evident that when dealing with the web things are messy. There were a couple of papers that documented this empirically either in terms of the availability of endpoints or just looking at the heterogeneity of the markup available from web pages.

In some sense, the papers mentioned in the prior theme also try to deal with this messiness. Here are another couple of papers looking at essentially how do deal with or even use this messiness.

One thing that seemed a lot more present in this year’s conference than last year  was the term entity. This is obviously popular because of things like google knowledge graph – but in some sense maybe it gives a better description of what we are aiming to get out of the data we have – machine readable descriptions or real world concepts/things.

Misc.

There are some things that are of interest that don’t fit neatly into the themes above. So I’ll just try a bulleted list.

  • We won the Best Demo Paper Award for git2prov.org
  • Our paper on using NoSQL stores for RDF went over very well. Congrats to Marcin for giving a good presentation.
  • The format of mixing talks from different tracks by topic and having only 20 minutes per talk was great.
  • VUA had a great showing – 3 main track papers, a bunch of workshop papers, a couple of different posters, 4 workshop organizers giving talks at the workshop summary session, 2 organizing committee members, alumni all over the place, plus a bunch of stuff I probably forgot to mention.
  • The colocation with Web Directions South was great – it added a nice extra energy to the conference.
  • There were best reviewer awards won by Oscar Corcho, Tania Tudorache, and Aidan Hogan
  • Peter Fox seemed to give a keynote just for me – concept maps, PROV followed with abductive reasoning.
  • Did I mention that the coffee in Sydney (and Newcastle) is really good and lots of places serve proper breakfast!

Preview: ISWC Semantic Web In-Use track

July 13, 2013
academia, linked data
2 Comments

iswc2013

This past week we (Achille Fokoue & myself) sent the paper notifications for the 2013 International Semantic Web Conference’s In-Use Track. The track seeks to highlight innovative semantic technologies being applied and deployed in practice. With the selection made by the program committee (Thanks!), I think we have definitely achieved that goal.

So if you’re coming to Sydney (& you should definitely be coming to Sydney) here’s what’s in store. (Papers are listed below.) You’ll see  a number of papers where semantic technologies are being deployed in companies to help end users including:

  • how semantic technologies are helping the BBC expose its archive to its journalists [1];
  • how OWL and RDF and being combined to give energy saving tips to 300,000 customers at EDF [2];
  • and how the search result pages in Yahoo! Search are being improved through the use ofknowledge bases [3].

Streaming

Dealing with streaming data has been a growing research theme in recent years. In the in-use track, we are seeing some of the fruits of that research in particular with respect to monitoring city events.  Balduini et al. report on the use of Streaming Linked Data Framework for monitoring the London Olympic Games 2012 and Milano Design Week 2013. (Yes, the semantic web is fashionable) [4]. IBM will present its work on the real-time urban monitoring of Dublin – requiring both scale but also low-latency solutions [5].

Life sciences

Semantic technologies have a long history of being deployed in healthcare and life sciences. We’ll see that again at this year’s conference. We get a progress report on the usage of these technologies in the development of the 11th revision of the International Classification of Diseases (ICD-11) [6]. ICD-11 involves 270 domain experts using the iCAT tool. We see how the intermixing (plain-old) spreadsheets and semantic technologies is enabling systems biology to better share its data [7]. In the life sciences, and in particular in drug discovery, both public and private data are critical, we see how the Open PHACTS project is tackling the problem of intermixing such data [8].

Semantics for Science & Research

Continuing on the science theme, the track will have reports on improving the reliability of scientific workflows [9], how linked data is being leverage to understand the economic impact of R&D in Europe [10]; and how our community is “eating its own dogfood” to enable better scientometric analysis of journals [11].  Lastly, you’ll get a talk on  the use of semantic annotations to help crowd source 3D representations of Greek Pottery for cultural heritage (a paper that I just think is so cool – I hope for videos) [12].

Semantic Data Availability

Reasoning relies on the availability of data exposed with its associated semantics. We’ve seen how the Linking Open Data movement helped bootstrap the uptake of Semantic Web technologies. Likewise, the widespread deployment of RDFa and microformats have dramatically increased the amount of data availability. But what’s out there? Bizer et al. give us a report based on analyzing  3 billion web pages. (I expect some awesome charts in this presentation) [13].

Enriching data with semantics has benefits but also comes at a cost. Based on a case study of converting Norwegian Petroleum Directorate’s FactPages, we’ll get insight into those trade-offs [14].  Reducing the effort for such conversations and particularly interlinking is a key challenge. The Cross-language Service Retrieve system is tackling this for open government data across multiple languages [15].

Finally, in practice, a key way to “semantize” data is through the use of natural language processing tools. You’ll see how semantic tech is facilitating the reusability and interoperability of NLP tools using NIF 2.0 framework [16].

Conclusion

I hope you’ll agree that this really represents the best from the semantic web community. These 16 papers were selected from 79 submissions. The program committee (for the most part)  did a great job both with their reviewers and importantly the discussion. Any many cases it was a hard decision and the PCs ability to discuss and revise their views was crucial in making the final selection. Thanks to the PC, it is a lot of work to do and we definitely asked them to do it in a fairly compact way. Thank you!

A couple of other thoughts, I think decision to institute an abstract submission for the in-use track was a good one and that author rebuttals are more helpful than I thought they would be.

ISWC 2013 is going to be a fantastic conference. I’m looking forward to the location, the sessions and the community. I look forward to seeing you there. There are many ways to participate so check out http://iswc2013.semanticweb.org. 

Papers

  1. Yves Raimond, Michael Smethurst, Andrew McParland and Christopher Lowis. Using the past to explain the present: interlinking current affairs with archives via the Semantic Web
  2. Pierre Chaussecourte, Birte Glimm, Ian Horrocks, Boris Motik and Laurent Pierre. The Energy Management Adviser at EDF
  3. Roi Blanco, Berkant Barla Cambazoglu, Peter Mika and Nicolas Torzec. Entity recommendations in Web Search
  4. Marco Balduini, Emanuele Della Valle, Daniele Dell’Aglio, Themis Palpanas, Mikalai Tsytsarau and Cristian Confalonieri. Social listening of City Scale Events using the Streaming Linked Data Framework
  5. Simone Tallevi-Diotallevi, Spyros Kotoulas, Luca Foschini, Freddy Lecue and Antonio Corradi. Real-time Urban Monitoring in Dublin using Semantic and Stream Technologies
  6. Tania Tudorache, Csongor I Nyulas, Natasha F. Noy and Mark Musen. Using Semantic Web in ICD-11: Three Years Down the Road
  7. Katherine Wolstencroft, Stuart Owen, Olga Krebs, Quyen Ngyuen, Jacky. L. Snoep, Wolfgang Mueller and Carole Goble. Semantic Data and Models Sharing in systems Biology: The Just Enough Results Model and the SEEK Platform
  8. Carole Goble, Alasdair J. G. Gray, Lee Harland, Karen Karapetyan, Antonis Loizou, Ivan Mikhailov, Yrjana Rankka, Stefan Senger, Valery Tkachenko, Antony Williams and Egon Willighagen. Incorporating Private and Commercial Data into an Open Linked Data Platform for Drug Discovery
  9. José Manuel Gómez-Pérez, Esteban García-Cuesta, Aleix Garrido and José Enrique Ruiz. When History Matters – Assessing Reliability for the Reuse of Scientific Workflows
  10. Amrapali Zaveri, Joao Ricardo Nickenig Vissoci, Cinzia Daraio and Ricardo Pietrobon. Using Linked Data to evaluate the impact of Research and Development in Europe: a Structural Equation Model
  11. Yingjie Hu, Krzysztof Janowicz, Grant Mckenzie, Kunal Sengupta and Pascal Hitzler. A Linked Data-driven Semantically-enabled Journal Portal for Scientometrics
  12. Chih-Hao Yu, Tudor Groza and Jane Hunter. Reasoning on crowd-sourced semantic annotations to facilitate cataloguing of 3D artefacts in the cultural heritage domain
  13. Christian Bizer, Kai Eckert, Robert Meusel, Hannes Mühleisen, Michael Schuhmacher and Johanna Völker. Deployment of RDFa, Microdata, and Microformats on the Web – A Quantitative Analysis
  14. Martin G. Skjæveland, Espen H. Lian and Ian Horrocks. Publishing the Norwegian Petroleum Directorate’s FactPages as Semantic Web Data
  15. Fedelucio Narducci, Matteo Palmonari and Giovanni Semeraro. Cross-language Semantic Retrieval and Linking of E-gov Services
  16. Sebastian Hellmann, Jens Lehmann, Sören Auer and Martin Brümmer. Integrating NLP using Linked Data

Trip Report: ESWC 2013

June 3, 2013
events, linked data
3 Comments

I think since I’ve moved to Europe I’ve been attending ESWC (Extended/European Semantic Web Conference) and I always get something out of the event. There are plenty of familiar faces but also quite a few new people and it’s a great environment for having chats. In addition, the quality of the content is always quite good. This year the event was held in Montpellier and was for the most part well organized: the main conference wifi worked!

The stats:

  • 300 participants
  • 42 accepted papers from 162 submissions
  • 26% acceptance rate
  • 11 workshops + 7 tutorials

So what was I doing there:

The VU Semantic Web group also had a strong showing:

  • Albert Meroño-Peñuela won the best PhD symposium paper for his work on digital humanities and the semantic web.
  • The USEWOD workshop’s (led by Laura Hollink) datasets were used by a number of main track papers for evaluation.
  • Stefan Schlobach and Laura Hollink were on the organizing committee. And we organized a couple of workshops & tutorials.
  • Posters/Demos:
    • Albert Meroño-Peñuela, Rinke Hoekstra, Andrea Scharnhorst, Christophe Guéret and Ashkan Ashkpour. Longitudinal Queries over Linked Census Data.
    • Niels Ockeloen, Victor de Boer and Lora Aroyo. LDtogo: A Data Querying and Mapping Framework for Linked Data Applications.
  • Several workshop papers.

I’ll try to pull out what I thought were the highlights of the event.

What is a semantic web application?

Can you escape Frank?

Can you escape Frank?

The keynotes from Enrico Motta and David Karger focused on trying to define what a semantic web application was. This starts out in the form of does a Semantic Web application need to use the Semantic Web set of standards (e.g. RDF, OWL, etc). So from my perspective, the answer is no. These standards are great infrastructure for building these applications but are they necessary, no (see google knowledge graph).  Then what is a semantic web application?

From what I could gather, Motta would define it as an application that is scalable, uses the web and embraces Model Theoretic semantics. For me that’s rather limiting, there are many other semantics that may be appropriate… we can ground meaning in something else other than model theory. I think a good example of this is the work on Pragmatic Semantics that my colleague Stefan Schlobach presented at the Artificial Intelligence meets the Semantic Web workshop. Or we can reach back into AI and see discussion’s from Brooks’ classic paper Elephant’s Don’t Play Chess.  I felt that Karger’s definition (in what was a great keynote) was getting somewhere. He defined a semantic web application essentially as:

An application whose schema is expected to change.

This seems to me to capture the semantic portion of the definition, in a sense that the semantics need to be understood on the fly. However, I think we need to role the web back into this definition… Overall, I thought this discussion was worth having and helps the field define what it is that we are aiming at. To be continued…

Homebrew databases

2013-05-29 09.18.05

Homebrew databases

As I said, I thought Karger’s keynote was great. He gave a talk within a talk, on the subject of homebrew databases from this paper in CHI 2011:

Amy Voida, Ellie Harmon, and Ban Al-Ani. 2011. Homebrew databases: complexities of everyday information management in nonprofit organizations. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’11). ACM, New York, NY, USA, 915-924. DOI=10.1145/1978942.1979078 http://doi.acm.org/10.1145/1978942.1979078

They define a homebrew database as “an assemblage of information management resources that people have pieced together to satisfice their information management needs.” This is just what we see all the time, the combination of excel, word, email, databases and don’t forget normal paper brought together to try to attack information management problems. A number of our use cases from the pharma industry as well as science reflect essentially this practice. It’s great to see a good definition of this problem grounded in ethnographic studies.

The Concerns of Linking

There were a couple of good papers on generating linkage across datasets (the central point of linked data). In Open PHACTS, we’ve been dealing with the notion of essentially context dependent linkages. I think this notion is becoming more prevalent in the community. We had a lot of positive response on this in the poster session when presenting Open PHACTS. Probably, my favorite paper was on linking the Smithsonian American Art museum to the Linked Data cloud. They use PROV to drive their link generation. Essentially, proposing links to human’s who then verify the connections. See:

I also liked the following paper on which hardware environment you should use when doing link discovery. Result: use GPU’s there fast!

Additionally, I think the following paper is cool because they use network statistics not just to measure but to do something, namely create links:

APIs

APIs were a growing theme of the event with things like the Linked Data Platform working group and  the successful SALAD workshop. (Fantastic acronym). Although I was surprised people in the workshop hadn’t heard of the Linked Data API. We had a lot of good feedback on the Open PHACTS API. It’s just the case that there is more developer expertise for using web service apis rather than semweb tech. I’ve actually seen a lot of demand for Semweb skills and while we our doing our best to train people there is still this gap. It’s good then that we are thinking about how these two technologies play together nicely.

Random Notes

%d bloggers like this: