Learning Compositional Semantics for Open Domain Semantic Parsing

Phong Le, Willem Zuidema

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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 languageEnglish
Title of host publicationProceedings of COLING 2012: Technical Papers
Place of PublicationMumbai, India
PublisherAssociation for Computational Linguistics
Number of pages18
Publication statusPublished - Dec 2012
Event24th International Conference on Computational Linguistics - IIT Bombay, Mumbai, India
Duration: 8 Dec 201215 Dec 2012


Conference24th International Conference on Computational Linguistics
Abbreviated titleCOLING 2012
Internet address

Fingerprint Dive into the research topics of 'Learning Compositional Semantics for Open Domain Semantic Parsing'. Together they form a unique fingerprint.

Cite this