From Entity Linking to Question Answering – Recent Progress on Semantic Grounding Tasks

Ming-Wei Chang


Abstract
Entity linking and semantic parsing have been shown to be crucial to important applications such as question answering and document understanding. These tasks often require structured learning models, which make predictions on multiple interdependent variables. In this talk, I argue that carefully designed structured learning algorithms play a central role in entity linking and semantic parsing tasks. In particular, I will present several new structured learning models for entity linking, which jointly detect mentions and disambiguate entities as well as capture non-textual information. I will then show how to use a staged search procedure to building a state-of-the-art knowledge base question answering system. Finally, if time permits, I will discuss different supervision protocols for training semantic parsers and the value of labeling semantic parses.
Anthology ID:
W16-3902
Volume:
Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Bo Han, Alan Ritter, Leon Derczynski, Wei Xu, Tim Baldwin
Venue:
WNUT
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
2
Language:
URL:
https://aclanthology.org/W16-3902
DOI:
Bibkey:
Cite (ACL):
Ming-Wei Chang. 2016. From Entity Linking to Question Answering – Recent Progress on Semantic Grounding Tasks. In Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), page 2, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
From Entity Linking to Question Answering – Recent Progress on Semantic Grounding Tasks (Chang, WNUT 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-3902.pdf