InferLite: Simple Universal Sentence Representations from Natural Language Inference Data

Jamie Kiros, William Chan

[How to correct problems with metadata yourself]


Abstract
Natural language inference has been shown to be an effective supervised task for learning generic sentence embeddings. In order to better understand the components that lead to effective representations, we propose a lightweight version of InferSent, called InferLite, that does not use any recurrent layers and operates on a collection of pre-trained word embeddings. We show that a simple instance of our model that makes no use of context, word ordering or position can still obtain competitive performance on the majority of downstream prediction tasks, with most performance gaps being filled by adding local contextual information through temporal convolutions. Our models can be trained in under 1 hour on a single GPU and allows for fast inference of new representations. Finally we describe a semantic hashing layer that allows our model to learn generic binary codes for sentences.
Anthology ID:
D18-1524
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4868–4874
Language:
URL:
https://aclanthology.org/D18-1524
DOI:
10.18653/v1/D18-1524
Bibkey:
Cite (ACL):
Jamie Kiros and William Chan. 2018. InferLite: Simple Universal Sentence Representations from Natural Language Inference Data. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4868–4874, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
InferLite: Simple Universal Sentence Representations from Natural Language Inference Data (Kiros & Chan, EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/D18-1524.pdf
Attachment:
 D18-1524.Attachment.zip
Data
GLUEMultiNLISNLI