13th Workshop on Building and Using Comparable Corpora

Details for attendance

The workshop takes place as an online event on May 11 from 9:15 to 16:35 UTC+2 (Central European Summer Time).

Link to attend: https://bbb.limsi.fr/b/pie-636-a4v

This uses BigBlueButton (BBB), a free software (http://docs.bigbluebutton.org/) which works through WebRTC, meaning that you just need to use your Web browser, no need to install specific software. This works with Chrome, Firefox, Safari, and also with the most recent version of Edge (Jan. 2020). On your smartphone or tablet use your Web browser too: Chrome, Firefox, Safari. There is no way to connect using a simple phone on this installation of BBB.

Attendance is free but please send e-mail to reinhardrapp (at) gmx (dot) de to obtain further information.

All attendees

For planning purposes, we encourage (but do not require) attendees to announce their intention to participate to pz (at) limsi (dot) fr.

Just connect to the above-specified BBB link, enter your given name and family name, and join the meeting.

When connecting, please choose the “Listen Only” option: this will lower the bandwidth and server load. This will keep your microphone inactive during the meeting. Unmute it only to ask a question at question time (in Listen Only mode, click on the headphones button, bottom center of the screen, to leave the audio, then click it again to join audio and choose the Microphone option). More conveniently, you can ask questions in the Public Chat pane of the BBB window. The session chair will collect the questions and ask them to the presenter at question time.
Please do not share your webcam except when presenting.
There is a Public Chat pane on the left of the BBB screen: you can display it or not.
You can switch the presentation or video to full screen mode for more comfortable viewing (click on the arrows button at the bottom right of the presentation).
Please see http://docs.bigbluebutton.org/ for more information.

Authors

You can either

Upload a PDF presentation to BBB and page through it while presenting live. See below for details on how to present on BBB.
Record a video presentation, upload it to a video sharing platform, and share the link to its address. YouTube, Vimeo, Instructure Media, Twitch and Daily Motion URLs are supported by BBB. See below for details on how to present on BBB.

Please test your connection and presentation before the workshop. For this purpose, the presentation room is already opened for authors ahead of time. Just connect to the above-specified BBB link, enter your name and join or start the meeting, click on the "+" button at the bottom left of the window, click on "become a presenter" if needed.

PDF: once you have Presenter status, the same "+" button will give you access to an "Upload a presentation" entry. Drag your PDF presentation to the designated location, then click the Confirm button. Use the arrows at the bottom of the screen to move forward and backward.
Recorded video: once you have Presenter status, the same "+" button will give you access to a "Share an external video" entry. Paste the URL of your video, then click the Share a new video button. Click the start button to play it.

Programme

9:15-9:30	Opening
9:30-10:20	Session 1: Invited Presentation Holger Schwenk, Facebook AI Research
	Session 2: Shared task: Bilingual Lexicon Induction from Comparable Corpora
10:20-10:40	Overview of the Fourth BUCC Shared Task: Bilingual Dictionary Induction from Comparable Corpora Reinhard Rapp, Pierre Zweigenbaum and Serge Sharoff
10:40-11:00	TALN/LS2N Participation at the BUCC Shared Task: Bilingual Dictionary Induction from Comparable Corpora Martin Laville, Amir Hazem and Emmanuel Morin
11:00-11:20	Coffee break
11:20-11:40	LMU Bilingual Dictionary Induction System with Word Surface Similarity Scores for BUCC 2020 Silvia Severini, Viktor Hangya, Alexander Fraser and Hinrich Schütze
11:40-12:00	BUCC2020: Bilingual Dictionary Induction using Cross-lingual Embedding Sanjanasri JP, Vijay Krishna Menon and Soman KP
12:00-13:00	Lunch break
13:00-13:50	Session 3: Invited Presentation Jörg Tiedemann, University of Helsinki
	Session 4: Corpus Construction
13:50-14:10	Constructing a Bilingual Corpus of Parallel Tweets Hamdy Mubarak, Sabit Hassan and Ahmed Abdelali
14:10-14:30	cEnTam: Creation and Validation of a New English-Tamil Bilingual Corpus Sanjanasri JP, Premjith B, Vijay Krishna Menon and Soman KP
14:30-14:50	Coffee break
	Session 5: Semantics
14:50-15:10	Automatic Creation of Correspondence Table of Meaning Tags from Two Dictionaries in One Language Using Bilingual Word Embedding Teruo Hirabayashi, Kanako Komiya, Masayuki Asahara and Hiroyuki Shinnou
15:10-15:30	Mining Semantic Relations from Comparable Corpora through Intersections of Word Embeddings Špela Vintar, Larisa Grčić Simeunović, Matej Martinc, Senja Pollak and Uroš Stepišnik
	Session 6: Machine Translation
15:30-15:50	Benchmarking Multidomain English-Indonesian Machine Translation Tri Wahyu Guntara, Alham Fikri Aji and Radityo Eko Prasojo
15:50-16:10	Reducing the Search Space for Parallel Sentences in Comparable Corpora Rémi Cardon and Natalia Grabar
16:10-16:30	Line-a-line: A Tool for Annotating Word-Alignments Maria Skeppstedt, Magnus Ahltorp, Gunnar Eriksson and Rickard Domeij
16:30-16:35	Closing