Assessing Composition in Sentence Vector Representations

Allyson Ettinger, Ahmed Elgohary, Colin Phillips, Philip Resnik


Abstract
An important component of achieving language understanding is mastering the composition of sentence meaning, but an immediate challenge to solving this problem is the opacity of sentence vector representations produced by current neural sentence composition models. We present a method to address this challenge, developing tasks that directly target compositional meaning information in sentence vector representations with a high degree of precision and control. To enable the creation of these controlled tasks, we introduce a specialized sentence generation system that produces large, annotated sentence sets meeting specified syntactic, semantic and lexical constraints. We describe the details of the method and generation system, and then present results of experiments applying our method to probe for compositional information in embeddings from a number of existing sentence composition models. We find that the method is able to extract useful information about the differing capacities of these models, and we discuss the implications of our results with respect to these systems’ capturing of sentence information. We make available for public use the datasets used for these experiments, as well as the generation system.
Anthology ID:
C18-1152
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1790–1801
Language:
URL:
https://aclanthology.org/C18-1152
DOI:
Bibkey:
Cite (ACL):
Allyson Ettinger, Ahmed Elgohary, Colin Phillips, and Philip Resnik. 2018. Assessing Composition in Sentence Vector Representations. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1790–1801, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Assessing Composition in Sentence Vector Representations (Ettinger et al., COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/C18-1152.pdf
Code
 aetting/compeval-generation-system