COGS: A Compositional Generalization Challenge Based on Semantic Interpretation
2020
Natural language is characterized by compositionality: the meaning of a complex expression is constructed from the meanings of its constituent parts. To facilitate the evaluation of the compositional abilities of language processing architectures, we introduce COGS, a semantic parsing dataset based on a fragment of English. The evaluation portion of COGS contains multiple systematic gaps that can only be addressed by compositional generalization; these include new combinations of familiar syntactic structures, or new combinations of familiar words and familiar structures. In experiments with Transformers and LSTMs, we found that in-distribution accuracy on the COGS test set was near-perfect (9699), but generalization accuracy was substantially lower (1635) and showed high sensitivity to random seed (+-68). These findings indicate that contemporary standard NLP models are limited in their compositional generalization capacity, and position COGS as a good way to measure progress.
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
0
Citations
NaN
KQI