Learning and Evaluating Sparse Interpretable Sentence Embeddings

Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko, Thomas Hofmann


Abstract
Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have the benefit of increased interpretability properties: to some degree, each dimension can be understood by a human and associated with a recognizable feature in the data. In this paper, we transfer this idea to sentence embeddings and explore several approaches to obtain a sparse representation. We further introduce a novel, quantitative and automated evaluation metric for sentence embedding interpretability, based on topic coherence methods. We observe an increase in interpretability compared to dense models, on a dataset of movie dialogs and on the scene descriptions from the MS COCO dataset.
Anthology ID:
W18-5422
Volume:
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2018
Address:
Brussels, Belgium
Venues:
EMNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
200–210
Language:
URL:
https://aclanthology.org/W18-5422
DOI:
10.18653/v1/W18-5422
Bibkey:
Cite (ACL):
Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko, and Thomas Hofmann. 2018. Learning and Evaluating Sparse Interpretable Sentence Embeddings. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 200–210, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Learning and Evaluating Sparse Interpretable Sentence Embeddings (Trifonov et al., 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-5422.pdf
Data
COCOSentEval