Cross-Lingual Emotion Lexicon Induction using Representation Alignment in Low-Resource Settings

Arun Ramachandran; Gerard de Melo

COLING 2020main8 citations

Cross-Lingual Emotion Lexicon Induction using Representation Alignment in Low-Resource Settings

Abstract

Emotion lexicons provide information about associations between words and emotions. They have proven useful in analyses of reviews, literary texts, and posts on social media, among other things. We evaluate the feasibility of deriving emotion lexicons cross-lingually, especially for low-resource languages, from existing emotion lexicons in resource-rich languages. For this, we start out from very small corpora to induce cross-lingually aligned vector spaces. Our study empirically analyses the effectiveness of the induced emotion lexicons by measuring translation precision and correlations with existing emotion lexicons, along with measurements on a downstream task of sentence emotion prediction.

BibTeX

@inproceedings{ramachandran-de-melo-2020-cross,
    title = "Cross-Lingual Emotion Lexicon Induction using Representation Alignment in Low-Resource Settings",
    author = "Ramachandran, Arun  and
      de Melo, Gerard",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2020.coling-main.517/",
    doi = "10.18653/v1/2020.coling-main.517",
    pages = "5879--5890"
}