Alert button
Picture for Yoshifumi Kawasaki

Yoshifumi Kawasaki

Alert button

Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment

Add code
Bookmark button
Alert button
May 19, 2023
Ryo Nagata, Hiroya Takamura, Naoki Otani, Yoshifumi Kawasaki

Figure 1 for Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment
Figure 2 for Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment
Figure 3 for Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment
Figure 4 for Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment

In this paper, we propose methods for discovering semantic differences in words appearing in two corpora based on the norms of contextualized word vectors. The key idea is that the coverage of meanings is reflected in the norm of its mean word vector. The proposed methods do not require the assumptions concerning words and corpora for comparison that the previous methods do. All they require are to compute the mean vector of contextualized word vectors and its norm for each word type. Nevertheless, they are (i) robust for the skew in corpus size; (ii) capable of detecting semantic differences in infrequent words; and (iii) effective in pinpointing word instances that have a meaning missing in one of the two corpora for comparison. We show these advantages for native and non-native English corpora and also for historical corpora.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon