A Type-coherent, Expressive Representation as an Initial Step to Language Understanding
This work addresses the need for more effective semantic parsing in NLP, but it is incremental as it builds on existing logical frameworks.
The paper tackles the problem of semantic representation for language understanding by proposing underspecified logical forms (ULF) for Episodic Logic, which balances modeling semantics, enabling inferences, and recoverability, with preliminary results showing a three-person pairwise interannotator agreement of 0.88 on confident annotations.
A growing interest in tasks involving language understanding by the NLP community has led to the need for effective semantic parsing and inference. Modern NLP systems use semantic representations that do not quite fulfill the nuanced needs for language understanding: adequately modeling language semantics, enabling general inferences, and being accurately recoverable. This document describes underspecified logical forms (ULF) for Episodic Logic (EL), which is an initial form for a semantic representation that balances these needs. ULFs fully resolve the semantic type structure while leaving issues such as quantifier scope, word sense, and anaphora unresolved; they provide a starting point for further resolution into EL, and enable certain structural inferences without further resolution. This document also presents preliminary results of creating a hand-annotated corpus of ULFs for the purpose of training a precise ULF parser, showing a three-person pairwise interannotator agreement of 0.88 on confident annotations. We hypothesize that a divide-and-conquer approach to semantic parsing starting with derivation of ULFs will lead to semantic analyses that do justice to subtle aspects of linguistic meaning, and will enable construction of more accurate semantic parsers.