Looking back on LREC, I think I went with a real apprehension. My only previous conference experience was ACL 2013 in Sofia. I had a great time and so my feelings towards LREC were a mixture of excitement for it being similar, but also a worry that it might not be as good. I'm glad to report that it lived up to and even exceeded my expectations. The sessions were interesting; the posters engaging; the networking events were even fun; the attendees were approachable and people even engaged with my talk, asking questions and talking to me afterwards.
It was great to meet many of the people who I have previously referenced. Many of those who wrote the papers in the lexical simplification list were in attendance. I made it my business to approach them and introduce myself. It's a great experience to meet people who have written such great papers and have made a contribution to the field.
For those that might find it useful, I've collected two lists below. The first is a list of papers which had something to do with readability / simplification. The second is a list of papers which I found interesting for one reason or another. The simplification papers will be making their way to the lexical simplification list soon.
Improvements to Dependency Parsing Using Automatic Simplification of Data. T Jelínek PDF
Measuring Readability of Polish Texts: Baseline Experiments. B Broda, B Nitoń, W Gruszczyński and M Ogrodniczuk PDF
Can Numerical Expressions Be Simpler? Implementation and Demonstration of a Numerical Simplification System for Spanish. S Bautista and H Saggion PDF
Text Readability and Word Distribution in Japanese. Satoshi Sato PDF
And finally, my paper:
Out in the Open: Finding and Categorising Errors in the Lexical Simplification Pipeline. M Shardlow PDF
Some other papers that I found interesting were:
Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines. M Sabou, K Bontcheva, L Derczynski and A Scharl PDF
Identification of Multiword Expressions in the brWaC. P Anick M Verhagen and J Pustejovsky PDF
Creating a Massively Parallel Bible Corpus. T Mayer and M Cysouw PDF
Showing posts with label conference. Show all posts
Showing posts with label conference. Show all posts
Tuesday, June 03, 2014
Monday, July 29, 2013
ACL 2013 Pre-Blog.
In under a week I will be sitting on a plane headed to Bulgaria. This year I will be presenting at the Association for Computational Linguistics Conference in Sofia. I have been fortunate enough to have had two papers accepted for presentation.
The first paper is as a part of the Student Research Workshop. This is a part of the main conference, but they only accept papers from PhD students (making it slightly easier to get in to!). The paper I am presenting details some experiments in attempting to establish a baseline for complex word identification. I used the CW Corpus (see below) to test a few standard techniques in complex word identification. It turned out that they were all fairly similar, but that in itself was an unexpected and hence interesting finding! The mode of presentation will be via a poster, I think this will be quite difficult and require a lot of energy to stay engaged and motivated, but I'm up for the challenge.
I'm excited to attend the student research workshop. It will hopefully be an encouraging experience. Whilst I don't expect there to be many (if any!) people who are experts in text simplification there, I'm sure it will be very useful to meet other PhD students and see where their work is taking them.
The second paper is part of a co-located workshop called Predicting and Improving Text Readability for Target Reader Populations (PITR 2013). This is a much smaller workshop with a more specialised focus. It is very relevant to my field of research and so I'm interested to meet plenty of like minded people there. I have followed the work of some of the presenting authors, so it will be very exciting to meet them face to face.
This is more than just academic celebrity spotting of course. The paper I will be presenting is on the CW Corpus, a resource I developed for evaluating the identification of complex words. There are a lot of implementation details, which for the main part I will try not to bore people with. The main thing I want to do with this conference is to get people interested in the concept of complex word identification as it's own separate evaluable sub task. Hopefully people will respond well to this, seeing it as a valid area to be working in. I'm presenting a poster in this workshop and will also be giving a 15 minute talk on my research.
I'll write about the conference again soon, either whilst I'm out in Bulgaria, or when I get back.
The first paper is as a part of the Student Research Workshop. This is a part of the main conference, but they only accept papers from PhD students (making it slightly easier to get in to!). The paper I am presenting details some experiments in attempting to establish a baseline for complex word identification. I used the CW Corpus (see below) to test a few standard techniques in complex word identification. It turned out that they were all fairly similar, but that in itself was an unexpected and hence interesting finding! The mode of presentation will be via a poster, I think this will be quite difficult and require a lot of energy to stay engaged and motivated, but I'm up for the challenge.
I'm excited to attend the student research workshop. It will hopefully be an encouraging experience. Whilst I don't expect there to be many (if any!) people who are experts in text simplification there, I'm sure it will be very useful to meet other PhD students and see where their work is taking them.
The second paper is part of a co-located workshop called Predicting and Improving Text Readability for Target Reader Populations (PITR 2013). This is a much smaller workshop with a more specialised focus. It is very relevant to my field of research and so I'm interested to meet plenty of like minded people there. I have followed the work of some of the presenting authors, so it will be very exciting to meet them face to face.
This is more than just academic celebrity spotting of course. The paper I will be presenting is on the CW Corpus, a resource I developed for evaluating the identification of complex words. There are a lot of implementation details, which for the main part I will try not to bore people with. The main thing I want to do with this conference is to get people interested in the concept of complex word identification as it's own separate evaluable sub task. Hopefully people will respond well to this, seeing it as a valid area to be working in. I'm presenting a poster in this workshop and will also be giving a 15 minute talk on my research.
I'll write about the conference again soon, either whilst I'm out in Bulgaria, or when I get back.
Subscribe to:
Posts (Atom)