%0 Journal Article %1 soon2001machine %A Soon, Wee Meng %A Ng, Hwee Tou %A Lim, Daniel Chung Yong %C Cambridge, MA, USA %D 2001 %I MIT Press %J Computational Linguistics %K coreference machine_learning %N 4 %P 521--544 %R 10.1162/089120101753342653 %T A machine learning approach to coreference resolution of noun phrases %U citeseer.ist.psu.edu/soon01machine.html %V 27 %X In this paper, we present a learning approach to coreference resolution of noun phrases in unrestricted text. The approach learns from a small, annotated corpus and the task includes resolving not just a certain type of noun phrase (e.g., pronouns) but rather general noun phrases. It also does not restrict the entity types of the noun phrases; that is, coreference is assigned whether they are of “organization,” “person,” or other types. We evaluate our approach on common data sets (namely, the MUC-6 and MUC-7 coreference corpora) and obtain encouraging results, indicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches. Our system is the first learning-based system that offers performance comparable to that of state-of-the-art nonlearning systems on these data sets.

@article{soon2001machine, abstract = {In this paper, we present a learning approach to coreference resolution of noun phrases in unrestricted text. The approach learns from a small, annotated corpus and the task includes resolving not just a certain type of noun phrase (e.g., pronouns) but rather general noun phrases. It also does not restrict the entity types of the noun phrases; that is, coreference is assigned whether they are of “organization,” “person,” or other types. We evaluate our approach on common data sets (namely, the MUC-6 and MUC-7 coreference corpora) and obtain encouraging results, indicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches. Our system is the first learning-based system that offers performance comparable to that of state-of-the-art nonlearning systems on these data sets.}, added-at = {2009-11-24T10:52:05.000+0100}, address = {Cambridge, MA, USA}, author = {Soon, Wee Meng and Ng, Hwee Tou and Lim, Daniel Chung Yong}, biburl = {https://www.bibsonomy.org/bibtex/2cbc700a0cbeaf7d23fa49eacd9e2a2c7/lama}, description = {A Machine Learning Approach to Coreference Resolution of Noun Phrases - Soon, Ng, Lim (ResearchIndex)}, doi = {10.1162/089120101753342653}, interhash = {b3dd9acc4f6821b2414eae2694b270b6}, intrahash = {cbc700a0cbeaf7d23fa49eacd9e2a2c7}, issn = {0891-2017}, journal = {Computational Linguistics}, keywords = {coreference machine_learning}, number = 4, pages = {521--544}, publisher = {MIT Press}, text = {W. M. Soon, H. T. Ng, and D. C. Y. Lim. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4):521--544, 2001.}, timestamp = {2009-11-24T10:52:05.000+0100}, title = {A machine learning approach to coreference resolution of noun phrases}, url = {citeseer.ist.psu.edu/soon01machine.html}, volume = 27, year = 2001 }