Evaluation of Semantic Dependency Labeling Across Domains

Abstract

One of the key concerns in computational semantics is to construct a domain independent semantic representation which captures the richness of natural language, yet can be quickly customized to a specific domain for practical applications. We propose to use generic semantic frames defined in FrameNet, a domain-independent semantic resource, as an intermediate semantic representation for language understanding in dialog systems. In this paper we: (a) outline a novel method for FrameNet-style semantic dependency labeling that builds on a syntactic dependency parse; and (b) compare the accuracy of domain-adapted and generic approaches to semantic parsing for dialog tasks, using a frame-annotated corpus of human-computer dialogs in an airline reservation domain.

Cite

Text

Stoyanchev et al. "Evaluation of Semantic Dependency Labeling Across Domains." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.10353

Markdown

[Stoyanchev et al. "Evaluation of Semantic Dependency Labeling Across Domains." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/stoyanchev2016aaai-evaluation/) doi:10.1609/AAAI.V30I1.10353

BibTeX

@inproceedings{stoyanchev2016aaai-evaluation,
  title     = {{Evaluation of Semantic Dependency Labeling Across Domains}},
  author    = {Stoyanchev, Svetlana and Stent, Amanda and Bangalore, Srinivas},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {2814-2820},
  doi       = {10.1609/AAAI.V30I1.10353},
  url       = {https://mlanthology.org/aaai/2016/stoyanchev2016aaai-evaluation/}
}