Continue reading “原国家网信办移动网络管理局局长方楠应邀来校开展讲座”
While deep learning methods have led to many breakthroughs in practical natural language applications, most notably in Machine Translation, Machine Reading/Question Answering, etc., there is still a sense among many NLP researchers that we have a long way to go before we can develop systems that can actually “understand” human language. “Understanding” natural language entails many different human-like capabilities, and they include but are not limited to the ability to track entities in a text, understand the relations between these entities, track events and their participants described in a text, understand how events unfold over time, and distinguish events that have actually happened from events that are planned or intended, are uncertain, or did not happen at all. We believe a critical step in achieving natural language understanding is to design meaning representations for text that have the necessary meaning “ingredients” that help us achieve these capabilities. Such meaning representations also need to be easy to produce in order to generate sufficient amounts of data to allow the training of accurate meaning representation parsers.
Continue reading “Call for Papers: the First International Workshop on Designing Meaning Representations (DMR 2019)”
CALL FOR PAPERS
3rd Workshop on Structured Prediction for NLP
Continuous representations, task-level supervision and latent linguistic structure
June 2–7, 2019; Minneapolis, USA
(co-located with NAACL)
*Submission Deadline: Wednedsay, March 6, 2019, 11:59pm GMT-12*
Continue reading “SPNLP19: Call for papers”
ACL 2019 FOURTH CONFERENCE ON MACHINE TRANSLATION (WMT19)
Shared Tasks on translation, MT evaluation, and automated post-editing.
August 1-2, 2019, in conjunction with ACL 2019 in Florence, Italy
As part of WMT, as in previous years, we will be organising a collection of shared tasks related to machine translation. We hope that both beginners and established research groups will participate. This year we have so far confirmed the following tasks
– Translation tasks
– Closely related languages
– Evaluation tasks
– Quality estimation
– Other tasks
– Automatic post-editing
Continue reading “First Call for Participation: WMT19 Machine Translation related Shared Tasks”
First International Workshop on e-Commerce and NLP (ECNLP’2019)
Co-located with WWW 2019 in San Francisco, California, USA, May 13-14, 2019
NLP and IR have been powering e-Commerce applications since the early days of the fields. Today, NLP and IR already play a significant role in e-commerce tasks, including product search, recommender systems, product question answering, machine translation (MT), sentiment analysis, product description and review summarization, and customer review processing, amongst many other tasks. With the exploding popularity of chatbots and shopping assistants – both text- and voice-based – NLP, IR, question answering, and dialogue systems research is poised to transform e-commerce once again, but requires a forum where new and unfinished ideas could be discussed. The ECNLP workshop aims to provide a venue for the dissemination of late-breaking research results and ideas related to e-commerce and online shopping, bringing together researchers from both academia and industry.
Continue reading “First International Workshop on e-Commerce and NLP (ECNLP’2019)”
Second Call for Participation
SemEval 2019 Task 6 – OffensEval: Identifying and Categorizing Offensive Language in Social Media
Shared Task Website: https://competitions.codalab.org/competitions/20011
Offensive language is pervasive in social media. Online communities, social media platforms, and technology companies have been investing heavily in ways to cope with offensive language to prevent abusive behavior in social media. One of the most effective strategies to tackle this problem is to use computational methods to identify offense, aggression, and hate speech in user-generated content (e.g. posts, comments, microblogs, etc.).
Continue reading “Second Call for Participation: SemEval 2019 Task 6 – OffensEval: Identifying and Categorizing Offensive Language in Social Media”
CALL FOR PAPER OFFERINGS for LREC Shared Task on Reproducibility
Did you author a recent paper in the area of Natural Language
Processing and Computational Linguistics, and are you interested in
further visibility of your paper, and wondering how well other
researchers are able to reproduce your results?
Please consider offering your paper for the upcoming
Shared Task on Reproducibility!
Scientific knowledge is grounded on falsifiable predictions and thus
its credibility and raison d’être relies on the possibility of
repeating experiments and getting similar results as originally
obtained and reported. In many young scientific areas, including
ours, acknowledgment and promotion of reproduction of
results need very much to be increased.
Continue reading “CALL FOR PAPER OFFERINGS for LREC Shared Task on Reproducibility”
We are looking for a post-doc in neural machine translation as part of the Horizon2020 ICT RIA project “Bergamot: Browser-based Multilingual Translation“. If you have recently defended a PhD thesis (or are close to defending) and have experience with deep learning methods in machine translation and other sequence-to-sequence NLP, then this is your chance to work in close collaboration with several internationally renowned research groups and grow as an independent researcher.
The aim of the Bergamot project is to allow NMT engines to run offline in a web browser, while dynamically adapting to the user’s requirements, content and the surrounding context, as well as yielding controllable output quality. As part of the position you will work on faster and lighter multi-domain and multilingual NMT approaches that can adapt to various kinds of context info.
Continue reading “Fwd: H2020-funded Post-doc in Neural Machine Translation, Tartu, Estonia”
The third version of the ParaCrawl corpus has been released! Parallel corpus is now available in all 24 of the official EU languages. 6 new languages are added to the v3 release namely Bulgarian, Danish, Greek, Slovak, Slovenian and Swedish. For the previously released languages, more data is added to the corpus.
For each language, two different versions of the corpus are released based on two cleaning tools, i.e. BiCleaner and Zipporah. ParaCrawl corpus is crawled from a large number of websites. The selection of websites is based on CommonCrawl, but ParaCrawl is extracted from a brand new crawl which has much higher coverage of these selected websites than CommonCrawl.
Continue reading “ParaCrawl corpus release v3.0”
Continue reading “实验室史晓东教授和两名博士生赴安阳参加第一届甲骨文信息处理国际学术研讨会”