SEQˆ3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression

Christos Baziotis, Ion Androutsopoulos, Ioannis Konstas, Alexandros Potamianos


Abstract
Neural sequence-to-sequence models are currently the dominant approach in several natural language processing tasks, but require large parallel corpora. We present a sequence-to-sequence-to-sequence autoencoder (SEQˆ3), consisting of two chained encoder-decoder pairs, with words used as a sequence of discrete latent variables. We apply the proposed model to unsupervised abstractive sentence compression, where the first and last sequences are the input and reconstructed sentences, respectively, while the middle sequence is the compressed sentence. Constraining the length of the latent word sequences forces the model to distill important information from the input. A pretrained language model, acting as a prior over the latent sequences, encourages the compressed sentences to be human-readable. Continuous relaxations enable us to sample from categorical distributions, allowing gradient-based optimization, unlike alternatives that rely on reinforcement learning. The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets.
Anthology ID:
N19-1071
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
673–681
Language:
URL:
https://aclanthology.org/N19-1071
DOI:
10.18653/v1/N19-1071
Bibkey:
Cite (ACL):
Christos Baziotis, Ion Androutsopoulos, Ioannis Konstas, and Alexandros Potamianos. 2019. SEQˆ3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 673–681, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
SEQˆ3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression (Baziotis et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/N19-1071.pdf
Presentation:
 N19-1071.Presentation.pdf
Video:
 https://vimeo.com/353462534