Enriching ASR Lattices with POS Tags for Dependency Parsing

Moritz Stiefel, Ngoc Thang Vu


Abstract
Parsing speech requires a richer representation than 1-best or n-best hypotheses, e.g. lattices. Moreover, previous work shows that part-of-speech (POS) tags are a valuable resource for parsing. In this paper, we therefore explore a joint modeling approach of automatic speech recognition (ASR) and POS tagging to enrich ASR word lattices. To that end, we manipulate the ASR process from the pronouncing dictionary onward to use word-POS pairs instead of words. We evaluate ASR, POS tagging and dependency parsing (DP) performance demonstrating a successful lattice-based integration of ASR and POS tagging.
Anthology ID:
W17-4605
Volume:
Proceedings of the Workshop on Speech-Centric Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
37–47
Language:
URL:
https://aclanthology.org/W17-4605
DOI:
10.18653/v1/W17-4605
Bibkey:
Cite (ACL):
Moritz Stiefel and Ngoc Thang Vu. 2017. Enriching ASR Lattices with POS Tags for Dependency Parsing. In Proceedings of the Workshop on Speech-Centric Natural Language Processing, pages 37–47, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Enriching ASR Lattices with POS Tags for Dependency Parsing (Stiefel & Vu, 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-4605.pdf