Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers

Mark Hopkins, Cristian Petrescu-Prahova, Roie Levin, Ronan Le Bras, Alvaro Herrasti, Vidur Joshi


Abstract
We present an approach for answering questions that span multiple sentences and exhibit sophisticated cross-sentence anaphoric phenomena, evaluating on a rich source of such questions – the math portion of the Scholastic Aptitude Test (SAT). By using a tree transducer cascade as its basic architecture, our system propagates uncertainty from multiple sources (e.g. coreference resolution or verb interpretation) until it can be confidently resolved. Experiments show the first-ever results 43% recall and 91% precision) on SAT algebra word problems. We also apply our system to the public Dolphin algebra question set, and improve the state-of-the-art F1-score from 73.9% to 77.0%.
Anthology ID:
D17-1083
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
795–804
Language:
URL:
https://aclanthology.org/D17-1083
DOI:
10.18653/v1/D17-1083
Bibkey:
Cite (ACL):
Mark Hopkins, Cristian Petrescu-Prahova, Roie Levin, Ronan Le Bras, Alvaro Herrasti, and Vidur Joshi. 2017. Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 795–804, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers (Hopkins et al., EMNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/D17-1083.pdf
Data
ALG514