Leveraging Newswire Treebanks for Parsing Conversational Data with Argument Scrambling

Riyaz A. Bhat, Irshad Bhat, Dipti Sharma


Abstract
We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new dataset containing 506 dependency trees for sentences from Bollywood (Hindi) movie scripts and Twitter posts of Hindi monolingual speakers. We show that a dependency parser trained on a newswire treebank is strongly biased towards the canonical structures and degrades when applied to conversational data. Inspired by Transformational Generative Grammar (Chomsky, 1965), we mitigate the sampling bias by generating all theoretically possible alternative word orders of a clause from the existing (kernel) structures in the treebank. Training our parser on canonical and transformed structures improves performance on conversational data by around 9% LAS over the baseline newswire parser.
Anthology ID:
W17-6309
Volume:
Proceedings of the 15th International Conference on Parsing Technologies
Month:
September
Year:
2017
Address:
Pisa, Italy
Venues:
IWPT | WS
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
61–66
Language:
URL:
https://www.aclweb.org/anthology/W17-6309
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-6309.pdf