Simple Maximum Entropy Models for Multilingual Coreference Resolution
نویسندگان
چکیده
This paper describes our system participating in the CoNLL-2012 shared task: Modeling Multilingual Unrestricted Coreference in Ontonotes. Maximum entropy models are used for our system as classifiers to determine the coreference relationship between every two mentions (usually noun phrases and pronouns) in each document. We exploit rich lexical, syntactic and semantic features for the system, and the final features are selected using a greedy forward and backward strategy from an initial feature set. Our system participated in the closed track for both English and Chinese languages.
منابع مشابه
BART: A Multilingual Anaphora Resolution System
BART (Versley et al., 2008) is a highly modular toolkit for coreference resolution that supports state-of-the-art statistical approaches and enables efficient feature engineering. For the SemEval task 1 on Coreference Resolution, BART runs have been submitted for German, English, and Italian. BART relies on a maximum entropy-based classifier for pairs of mentions. A novel entitymention approach...
متن کاملA Mention-Synchronous Coreference Resolution Algorithm Based On the Bell Tree
This paper proposes a new approach for coreference resolution which uses the Bell tree to represent the search space and casts the coreference resolution problem as finding the best path from the root of the Bell tree to the leaf nodes. A Maximum Entropy model is used to rank these paths. The coreference performance on the 2002 and 2003 Automatic Content Extraction (ACE) data will be reported. ...
متن کاملCoreference Resolution System using Maximum Entropy Classifier
In this paper, we present our supervised learning approach to coreference resolution in ConLL corpus. The system relies on a maximum entropy-based classifier for pairs of mentions, and adopts a rich linguisitically motivated feature set, which mostly has been introduced by Soon et al (2001), and experiment with alternaive resolution process, preprocessing tools,and classifiers. We optimize the ...
متن کاملA Multigraph Model for Coreference Resolution
This paper presents HITS’ coreference resolution system that participated in the CoNLL2012 shared task on multilingual unrestricted coreference resolution. Our system employs a simple multigraph representation of the relation between mentions in a document, where the nodes correspond to mentions and the edges correspond to relations between the mentions. Entities are obtained via greedy cluster...
متن کاملCorpus based coreference resolution for Farsi text
"Coreference resolution" or "finding all expressions that refer to the same entity" in a text, is one of the important requirements in natural language processing. Two words are coreference when both refer to a single entity in the text or the real world. So the main task of coreference resolution systems is to identify terms that refer to a unique entity. A coreference resolution tool could be...
متن کامل