Learning-based multi-sieve co-reference resolution with knowledge
|Learning-based multi-sieve co-reference resolution with knowledge|
|Author(s)||Ratinov L., Roth D.|
|Published in||EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference|
|Keyword(s)||Unknown (Extra: Co-reference resolutions, End systems, Free texts, State-of-the-art system, Wikipedia, Sieves, Natural language processing systems)|
|Article||BASE, CiteSeerX, Google Scholar|
|Web||Ask, Bing, Google (PDF), Yahoo!|
|Download and mirrors|
|Local copy||Not available|
|Remote mirror(s)||Not available|
|Export and share|
|BibTeX, CSV, RDF, JSON|
|Browse properties · List of conference papers|
Learning-based multi-sieve co-reference resolution with knowledge is a 2012 conference paper written in English by Ratinov L., Roth D. and published in EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference.
We explore the interplay of knowledge and structure in co-reference resolution. To inject knowledge, we use a state-of-the-art system which cross-links (or "grounds") expressions in free text to Wikipedia. We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system. To maximize the utility of the injected knowledge, we deploy a learning-based multi-sieve approach and develop novel entity-based features. Our end system outperforms the state-of-the-art baseline by 2 B3 F1 points on non-transcript portion of the ACE 2004 dataset.
- This section requires expansion. Please, help!
Probably, this publication is cited by others, but there are no articles available for them in WikiPapers.