Learning Joint Semantic Parsers from Disjoint Data
@inproceedings{Peng2018LearningJS, title={Learning Joint Semantic Parsers from Disjoint Data}, author={Hao Peng and Sam Thomson and Swabha Swayamdipta and Noah A. Smith}, booktitle={NAACL-HLT}, year={2018} }
We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not overlap. We handle such "disjoint" data by treating annotations for unobserved formalisms as latent structured variables. Building on state-of-the-art baselines, we show improvements both in frame-semantic parsing and semantic dependency parsing by modeling them jointly.
Supplemental Content
Github Repo
Via Papers with Code
COLING 2018 Tutorial on Multilingual FrameNet: Automatic semantic role labeling for FrameNet
Presentation Slides
Figures, Tables, and Topics from this paper
39 Citations
Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies
- Computer Science
- EMNLP
- 2020
- PDF
Encoding Syntactic Constituency Paths for Frame-Semantic Parsing with Graph Convolutional Networks
- Computer Science
- ArXiv
- 2020
- Highly Influenced
- PDF
Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies
- Computer Science
- ACL
- 2019
- 10
- PDF
References
SHOWING 1-10 OF 59 REFERENCES
The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies
- Computer Science
- CoNLL
- 2008
- 490
- Highly Influential
- PDF
A Joint Sequential and Relational Model for Frame-Semantic Parsing
- Computer Science
- EMNLP
- 2017
- 40
- Highly Influential
- PDF
LTH: Semantic Structure Extraction using Nonprojective Dependency Trees
- Computer Science
- SemEval@ACL
- 2007
- 96
- PDF
Improving NLP through Marginalization of Hidden Syntactic Structure
- Computer Science
- EMNLP-CoNLL
- 2012
- 31
- PDF