Joint Inference on Bilingual Parse Trees for PP-attachment Disambiguation

Geetanjali Rakshit


Abstract
Prepositional Phrase (PP) attachment is a classical problem in NLP for languages like English, which suffer from structural ambiguity. In this work, we solve this problem with the help of another language free from such ambiguities, using the parse tree of the parallel sentence in the other language, and word alignments. We formulate an optimization framework that encourages agreement between the parse trees for two languages, and solve it using a novel Dual Decomposition (DD) based algorithm. Experiments on the English-Hindi language pair show promising improvements over the baseline.
Anthology ID:
W19-3615
Volume:
Proceedings of the 2019 Workshop on Widening NLP
Month:
August
Year:
2019
Address:
Florence, Italy
Venue:
WiNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
43–45
Language:
URL:
https://aclanthology.org/W19-3615
DOI:
Bibkey:
Cite (ACL):
Geetanjali Rakshit. 2019. Joint Inference on Bilingual Parse Trees for PP-attachment Disambiguation. In Proceedings of the 2019 Workshop on Widening NLP, pages 43–45, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Joint Inference on Bilingual Parse Trees for PP-attachment Disambiguation (Rakshit, WiNLP 2019)
Copy Citation: