Composition of Sentence Embeddings: Lessons from Statistical Relational Learning

Damien Sileo, Tim Van De Cruys, Camille Pradel, Philippe Muller


Abstract
Various NLP problems – such as the prediction of sentence similarity, entailment, and discourse relations – are all instances of the same general task: the modeling of semantic relations between a pair of textual elements. A popular model for such problems is to embed sentences into fixed size vectors, and use composition functions (e.g. concatenation or sum) of those vectors as features for the prediction. At the same time, composition of embeddings has been a main focus within the field of Statistical Relational Learning (SRL) whose goal is to predict relations between entities (typically from knowledge base triples). In this article, we show that previous work on relation prediction between texts implicitly uses compositions from baseline SRL models. We show that such compositions are not expressive enough for several tasks (e.g. natural language inference). We build on recent SRL models to address textual relational problems, showing that they are more expressive, and can alleviate issues from simpler compositions. The resulting models significantly improve the state of the art in both transferable sentence representation learning and relation prediction.
Anthology ID:
S19-1004
Volume:
Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Rada Mihalcea, Ekaterina Shutova, Lun-Wei Ku, Kilian Evang, Soujanya Poria
Venue:
*SEM
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
33–43
Language:
URL:
https://aclanthology.org/S19-1004
DOI:
10.18653/v1/S19-1004
Bibkey:
Cite (ACL):
Damien Sileo, Tim Van De Cruys, Camille Pradel, and Philippe Muller. 2019. Composition of Sentence Embeddings: Lessons from Statistical Relational Learning. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 33–43, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Composition of Sentence Embeddings: Lessons from Statistical Relational Learning (Sileo et al., *SEM 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/S19-1004.pdf
Data
SNLI