Break
AI2 Israel, Question Understanding • 2020
Break is a human annotated dataset of natural language questions and their Question Decomposition Meaning Representations (QDMRs). Break consists of 83,978 examples sampled from 10 question answering datasets over text, images and databases.
Leaderboard
Top Public Submissions
Details | Created | GED |
|---|---|---|
1 QDMR-BART + special tokens Chris Coleman and Alex Reneau, Northwestern University | 9/20/2020 | 24% |
2 QDMR-BARTv1 Chris Coleman and Alex Reneau, Northwestern University | 7/18/2020 | 23% |
3 Curriculum-trained CopyNet Chris Coleman and Alex Reneau, Northwestern University | 6/30/2020 | 27% |
4 CopyNet QDMR Parser Tomer Wolfson, Mor Geva, Ankit Gupta, Matt Gardner, Yoav Goldberg, Daniel Deutch and Jonathan Berant from Tel Aviv University and Allen Institute for AI | 4/2/2020 | 29% |
5 COPYNET QDMR-Parser Enhanced with RTT Augmentation Dana Arad from Tel-Aviv University and Yael Sapir from Tel-Aviv University | 5/27/2020 | 48% |
Authors
Tomer Wolfson, Mor Geva, Ankit Gupta, Matt Gardner, Yoav Goldberg, Daniel Deutch, Jonathan Berant