Robust Word Vectors: Context-Informed Embeddings for Noisy Texts

Valentin Malykh, Varvara Logacheva, Taras Khakhulin


Abstract
We suggest a new language-independent architecture of robust word vectors (RoVe). It is designed to alleviate the issue of typos, which are common in almost any user-generated content, and hinder automatic text processing. Our model is morphologically motivated, which allows it to deal with unseen word forms in morphologically rich languages. We present the results on a number of Natural Language Processing (NLP) tasks and languages for the variety of related architectures and show that proposed architecture is typo-proof.
Anthology ID:
W18-6108
Volume:
Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text
Month:
November
Year:
2018
Address:
Brussels, Belgium
Editors:
Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
54–63
Language:
URL:
https://aclanthology.org/W18-6108
DOI:
10.18653/v1/W18-6108
Bibkey:
Cite (ACL):
Valentin Malykh, Varvara Logacheva, and Taras Khakhulin. 2018. Robust Word Vectors: Context-Informed Embeddings for Noisy Texts. In Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text, pages 54–63, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Robust Word Vectors: Context-Informed Embeddings for Noisy Texts (Malykh et al., WNUT 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6108.pdf