Using BERT Embeddings to Model Word Importance in Conversational Transcripts for Deaf and Hard of Hearing Users

Akhter Al Amin, Saad Hassan, Cecilia Alm, Matt Huenerfauth


Abstract
Deaf and hard of hearing individuals regularly rely on captioning while watching live TV. Live TV captioning is evaluated by regulatory agencies using various caption evaluation metrics. However, caption evaluation metrics are often not informed by preferences of DHH users or how meaningful the captions are. There is a need to construct caption evaluation metrics that take the relative importance of words in transcript into account. We conducted correlation analysis between two types of word embeddings and human-annotated labelled word-importance scores in existing corpus. We found that normalized contextualized word embeddings generated using BERT correlated better with manually annotated importance scores than word2vec-based word embeddings. We make available a pairing of word embeddings and their human-annotated importance scores. We also provide proof-of-concept utility by training word importance models, achieving an F1-score of 0.57 in the 6-class word importance classification task.
Anthology ID:
2022.ltedi-1.5
Volume:
Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venues:
ACL | LTEDI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
35–40
Language:
URL:
https://aclanthology.org/2022.ltedi-1.5
DOI:
10.18653/v1/2022.ltedi-1.5
Bibkey:
Cite (ACL):
Akhter Al Amin, Saad Hassan, Cecilia Alm, and Matt Huenerfauth. 2022. Using BERT Embeddings to Model Word Importance in Conversational Transcripts for Deaf and Hard of Hearing Users. In Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion, pages 35–40, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Using BERT Embeddings to Model Word Importance in Conversational Transcripts for Deaf and Hard of Hearing Users (Amin et al., LTEDI 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.ltedi-1.5.pdf