Abstract / Description of output
This paper introduces a new approach to learning compositional semantics for open domain semantic parsing. Our approach is called Dependency-based Semantic Composition using Graphs (DeSCoG) and deviates from existing approaches in several ways. First, we remove the need of the lambda calculus by using a graph-based variant of Discourse Representation Structures to represent semantic building blocks and defining new combinatory operations for our graph structures. Second, we propose a probability model to approximate probability distributions over possible semantic compositions. And third, we use a variant of alignment algorithms from machine translation to learn a lexicon. On the Groningen Meaning Bank (a recently released, large-scale, domain-general, semantically annotated corpus; Basile et al. (2012)), where we preprocess sentences with an existing dependency parser, we achieve results significantly better than the baseline. On Geoquery we obtain performance comparable to semantic parsers that were developed specifically for that domain.
Original language | English |
---|---|
Title of host publication | Proceedings of COLING 2012: Technical Papers |
Place of Publication | Mumbai, India |
Publisher | Association for Computational Linguistics |
Pages | 1535-1552 |
Number of pages | 18 |
Publication status | Published - Dec 2012 |
Event | 24th International Conference on Computational Linguistics - IIT Bombay, Mumbai, India Duration: 8 Dec 2012 → 15 Dec 2012 http://www.coling2012-iitb.org/ |
Conference
Conference | 24th International Conference on Computational Linguistics |
---|---|
Abbreviated title | COLING 2012 |
Country/Territory | India |
City | Mumbai |
Period | 8/12/12 → 15/12/12 |
Internet address |