Combining Sentiment Lexica with a Multi-View Variational Autoencoder
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- OA-Combining Sentiment Lexica
Forlagets udgivne version, 268 KB, PDF-dokument
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.
Originalsprog | Engelsk |
---|---|
Titel | 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) |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2019 |
Sider | 635-640 |
DOI | |
Status | Udgivet - 2019 |
Begivenhed | 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019 - Minneapolis, USA Varighed: 3 jun. 2019 → 7 jun. 2019 |
Konference
Konference | 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019 |
---|---|
Land | USA |
By | Minneapolis |
Periode | 03/06/2019 → 07/06/2019 |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 240629209