Combining Sentiment Lexica with a Multi-View Variational Autoencoder
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- OA-Combining Sentiment Lexica
Final published version, 268 KB, PDF document
When assigning quantitative labels to a dataset, different methodologies may rely on different scales. In particular, when assigning polarities to words in a sentiment lexicon, annotators may use binary, categorical, or continuous labels. Naturally, it is of interest to unify these labels from disparate scales to both achieve maximal coverage over words and to create a single, more robust sentiment lexicon while retaining scale coherence. We introduce a generative model of sentiment lexica to combine disparate scales into a common latent representation. We realize this model with a novel multi-view variational autoencoder (VAE), called SentiVAE. We evaluate our approach via a downstream text classification task involving nine English-Language sentiment analysis datasets; our representation outperforms six individual sentiment lexica, as well as a straightforward combination thereof.
Original language | English |
---|---|
Title of host publication | 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) |
Publisher | Association for Computational Linguistics |
Publication date | 2019 |
Pages | 635-640 |
DOIs | |
Publication status | Published - 2019 |
Event | 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019 - Minneapolis, United States Duration: 3 Jun 2019 → 7 Jun 2019 |
Conference
Conference | 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019 |
---|---|
Land | United States |
By | Minneapolis |
Periode | 03/06/2019 → 07/06/2019 |
Number of downloads are based on statistics from Google Scholar and www.ku.dk
No data available
ID: 240629209