Implicit Subjective and Sentimental Usages in Multi-sense Word Embeddings

Yuqi Sun, Haoyue Shi, Junfeng Hu


Abstract
In multi-sense word embeddings, contextual variations in corpus may cause a univocal word to be embedded into different sense vectors. Shi et al. (2016) show that this kind of pseudo multi-senses can be eliminated by linear transformations. In this paper, we show that pseudo multi-senses may come from a uniform and meaningful phenomenon such as subjective and sentimental usage, though they are seemingly redundant. In this paper, we present an unsupervised algorithm to find a linear transformation which can minimize the transformed distance of a group of sense pairs. The major shrinking direction of this transformation is found to be related with subjective shift. Therefore, we can not only eliminate pseudo multi-senses in multisense embeddings, but also identify these subjective senses and tag the subjective and sentimental usage of words in the corpus automatically.
Anthology ID:
W18-6203
Volume:
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
October
Year:
2018
Address:
Brussels, Belgium
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8–13
Language:
URL:
https://aclanthology.org/W18-6203
DOI:
10.18653/v1/W18-6203
Bibkey:
Cite (ACL):
Yuqi Sun, Haoyue Shi, and Junfeng Hu. 2018. Implicit Subjective and Sentimental Usages in Multi-sense Word Embeddings. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 8–13, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Implicit Subjective and Sentimental Usages in Multi-sense Word Embeddings (Sun et al., WASSA 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/W18-6203.pdf
Data
MPQA Opinion Corpus