9th Workshop on Building and Using Comparable Corpora



Workshop Program

Monday, May 23, 2016, room Adria

09.15–9.25Opening Remarks
 Session 1: Invited Presentation
09.25–10.30The Name of the Game is Comparable Corpora
Ruslan Mitkov
10.30–11.00Coffee Break
 Session 2: Building Comparable Corpora
11:00–11:30Clustering Comparable Corpora of Russian and Ukrainian Academic Texts: Word Embeddings and Semantic Fingerprints
Andrey Kutuzov, Mikhail Kopotev, Tatyana Sviridenko and Lyubov Ivanova
11:30–12:00A 2D CRF Model for Sentence Alignment
Yong Xu and François Yvon
12:00–12:30Parallel Document Identification using Zipf’s Law
Mehdi Mohammadi
12.30–14.00Lunch Break
 Session 3: Invited Presentation
14.00–15.00Exploring the Richness and Limitations of Web Sources for Comparable Corpus Research
Gregory Grefenstette
 Session 4: Applications of Comparable Corpora
15.00–15.30A Mutual Iterative Enhancement Model for Simultaneous Comparable Corpora and Bilingual Lexicons Construction
Zede Zhu, Xinhua Zeng, Shouguo Zheng, Xiongwei Sun, Shaoqi Wang and Shizhuang Weng
10:00–10:30Hard Synonymy and Applications in Automatic Detection of Synonyms and Machine Translation
Ana Sabina Uban
16.00–16.30Coffee Break
 Session 5: Discussion
16:30–17:30Towards Preparation of the Second BUCC Shared Task: Detecting Parallel Sentences in Comparable Corpora
Pierre Zweigenbaum, Serge Sharoff and Reinhard Rapp