Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning

Shuai Tang, Virginia R. de Sa


Abstract
Encoder-decoder models for unsupervised sentence representation learning using the distributional hypothesis effectively constrain the learnt representation of a sentence to only that needed to reproduce the next sentence. While the decoder is important to constrain the representation, these models tend to discard the decoder after training since only the encoder is needed to map the input sentence into a vector representation. However, parameters learnt in the decoder also contain useful information about the language. In order to utilise the decoder after learning, we present two types of decoding functions whose inverse can be easily derived without expensive inverse calculation. Therefore, the inverse of the decoding function serves as another encoder that produces sentence representations. We show that, with careful design of the decoding functions, the model learns good sentence representations, and the ensemble of the representations produced from the encoder and the inverse of the decoder demonstrate even better generalisation ability and solid transferability.
Anthology ID:
P19-1397
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4050–4060
Language:
URL:
https://aclanthology.org/P19-1397
DOI:
10.18653/v1/P19-1397
Bibkey:
Cite (ACL):
Shuai Tang and Virginia R. de Sa. 2019. Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4050–4060, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning (Tang & de Sa, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1397.pdf
Data
BookCorpusMPQA Opinion CorpusSICKSST