Unsupervised, knowledge-free, and interpretable word sense disambiguation

Panchenko, Alexander ; Marten, Fide ; Ruppert, Eugen ; Faralli, Stefano ; Ustalov, Dmitry ; Ponzetto, Simone Paolo ; Biemann, Chris

Preview

PDF
D17-2016.pdf - Published
Download (881kB)

URL:	https://madoc.bib.uni-mannheim.de/43326
Additional URL:	http://aclweb.org/anthology/D17-2
URN:	urn:nbn:de:bsz:180-madoc-433264
Document Type:	Conference or workshop publication
Year of publication:	2017
Book title:	The Conference on Empirical Methods in Natural Language Processing - proceedings of System Demonstrations : September 9-11, 2017, Copenhagen, Denmark : EMNLP 2017
Page range:	91-96
Conference title:	2017 Conference on Empirical Methods in Natural Language Processing
Location of the conference venue:	Copenhagen, Denmark
Date of the conference:	September 7-11, 2017
Publisher:	Specia, Lucia
Place of publication:	Stroudsburg, PA
Publishing house:	Association for Computational Linguistics
ISBN:	978-1-945626-97-5
Publication language:	English
Institution:	School of Business Informatics and Mathematics > Information Systems III: Enterprise Data Analysis (Ponzetto 2016-)
Subject:	004 Computer science, internet
Abstract:	Interpretability of a predictive model is a powerful feature that gains the trust of users in the correctness of the predictions. In word sense disambiguation (WSD), knowledge-based systems tend to be much more interpretable than knowledge-free counterparts as they rely on the wealth of manually-encoded elements representing word senses, such as hypernyms, usage examples, and images. We present a WSD system that bridges the gap between these two so far disconnected groups of methods. Namely, our system, providing access to several state-of-the-art WSD models, aims to be interpretable as a knowledge-based system while it remains completely unsupervised and knowledge-free. The presented tool features a Web interface for all-word disambiguation of texts that makes the sense predictions human readable by providing interpretable word sense inventories, sense representations, and disambiguation results. We provide a public API, enabling seamless integration.