Channels Resources Recent Items Reading list HomeRegisterLoginSupportContact


Query: "coreference resolution" or "entity detection and tracking" or EDT
Status: updated [Success]
1-20 of 930: 12345...47
View PDF Domain Adaptation of Coreference Resolution for Radiology ReportsAbstract: In this paper we explore the applicability of existing coreference resolution systems to a biomedical genre: radiology reports. Analysis revealed that, due to the idiosyncrasies of the domain, both the formulation of the problem of coreference resolution and its solution need significant domain adaptation work. We reformulated the task and developed an unsupervised algorithm based on heuristics for coreference resolution in radiology reports. The algorithm is shown to perform well on a test dataset of 150 manually annotated radiology reports.
Emilia Apostolova, Noriko Tomuro, Pattanasak Mongkolwat, Dina Demner-Fushman
Google Scholar CiteSeer X DBLP Database
View PDF Combining Syntactic and Semantic Features by SVM for Unrestricted Coreference ResolutionAbstract: The paper presents a system for the CoNLL2011 share task of coreference resolution. The system composes of two components: one for mentions detection and another one for their coreference resolution. For mentions detection, we adopted a number of heuristic rules from syntactic parse tree perspective. For coreference resolution, we apply SVM by exploiting multiple syntactic and semantic features. The experiments on the CoNLL-2011 corpus show that our rule-based mention identification system obtains a recall of 87.69%, and the best result of the SVM-based coreference resolution system is an average F-score 50.92% of the MUC, B-CUBED and CEAFE metrics.
Huiwei Zhou , Yao Li , Degen Huang , Yan Zhang , Chunlong Wu , Yuansheng Yang
Google Scholar CiteSeer X DBLP Database
View PDF Transformation Based Chinese Entity Detection and TrackingAbstract: This paper proposes a unified Transformation Based Learning (TBL, Brill, 1995) framework for Chinese Entity Detection and Tracking (EDT). It consists of two sub models: a mention detection model and an entity tracking/coreference model. The first sub-model is used to adapt existing Chinese word segmentation and Named Entity (NE) recognition results to a specific EDT standard to find all the mentions. The second sub-model is used to find the coreference relation between the mentions. In addition, a feedback technique is proposed to further improve the performance of the system. We evaluated our methods on the Automatic Content Extraction (ACE, NIST, 2003) Chinese EDT corpus. Results show that it outperforms the baseline, and achieves comparable performance with the state-of-the-art methods.
Yaqian Zhou Changning Huang Jianfeng Gao Lide Wu
Google Scholar CiteSeer X DBLP Database
View PDF Joint Entity and Event Coreference Resolution across DocumentsAbstract: We introduce a novel coreference resolution system that models entities and events jointly. Our iterative method cautiously constructs clusters of entity and event mentions using linear regression to model cluster merge operations. As clusters are built, information flows between entity and event clusters through features that model semantic role dependencies. Our system handles nominal and verbal events as well as entities, and our joint formulation allows information from event coreference to help entity coreference, and vice versa. In a cross-document domain with comparable documents, joint coreference resolution performs significantly better (over 3 CoNLL F1 points) than two strong baselines that resolve entities and events separately.
Heeyoung Lee, Marta Recasens, Angel Chang, Mihai Surdeanu, Dan Jurafsky
Google Scholar CiteSeer X DBLP Database
View PDF Dependency-driven Anaphoricity Determination for CoreferenceAbstract: This paper proposes a dependency-driven scheme to dynamically determine the syntactic parse tree structure for tree kernel-based anaphoricity determination in coreference resolution. Given a full syntactic parse tree, it keeps the nodes and the paths related with current mention based on constituent dependencies from both syntactic and semantic perspectives, while removing the noisy information, eventually leading to a dependency-driven dynamic syntactic parse tree (D-DSPT). Evaluation on the ACE 2003 corpus shows that the D-DSPT outperforms all previous parse tree structures on anaphoricity determination, and that applying our anaphoricity determination module in coreference resolution achieves the so far best performance.
Fang Kong Guodong Zhou Longhua Qian Qiaoming Zhu
Google Scholar CiteSeer X DBLP Database
View PDF Coreference Resolution using Expressive Logic ModelsAbstract: Coreference resolution is regarded as a crucial step for acquiring linkages among pieces of information extracted. Traditionally, coreference resolution models make use of independent attribute-value features over pairs of noun phrases. However, dependency and deeper relations between features can more adequately describe the properties of coreference relations between noun phrases. In this paper, we pro-pose a framework of coreference resolution based on firstorder logic and probabilistic graphical model, the Markov Logic Network. The proposed framework enables the use of background knowledge and captures more complex coreference linkage properties through rich expression of conditions. Moreover, the proposed conditions can capture the structural pattern within a noun phrase as well as contextual information between noun phrases. Our experiments show improvement with the use of the expressive logic models and the use of pattern-based conditions. Categories and Subject Descriptors: H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval--Clustering; I.2.7 [Artificial Intelligence]: Natural Language Processing--Text analysis General Terms: Design, Experimentation Keywords: coreference resolution, natural language pro-cessing
Ki Chan, Wai Lam, Xiaofeng Yu
Google Scholar CiteSeer X DBLP Database
2. Entity-based Local Coherence
Google Scholar CiteSeer X DBLP Database
View PDF Creating a Coreference Resolution System for ItalianAbstract: This paper summarizes our work on creating a full-scale coreference resolution (CR) system for Italian, using BART--an open-source modular CR toolkit initially developed for English corpora. We discuss our experiments on language-specific issues of the task. As our evaluation experiments show, a language-agnostic system (designed primarily for English) can achieve a performance level in high forties (MUC F-score) when re-trained and tested on a new language, at least on gold mention boundaries. Compared to this level, we can improve our F-score by around 10% introducing a small number of language-specific changes. This shows that, with a modular coreference resolution platform, such as BART, one can straightforwardly develop a family of robust and reliable systems for various languages. We hope that our experiments will encourage researchers working on coreference in other languages to create their own full-scale coreference resolution systems--as we have mentioned above, at the moment such modules exist only for very few languages other than English.
Massimo Poesio , Olga Uryupina , Yannick Versley
Google Scholar CiteSeer X DBLP Database
Ryu I ida Takenobu Tokunaga
Google Scholar CiteSeer X DBLP Database
Heeyoung Lee Angel Chang Yves Peirsman Nathanael Chambers Mihai Surdeanu Dan Jurafsky
Google Scholar CiteSeer X DBLP Database
Heeyoung Lee Angel Chang Yves Peirsman Nathanael Chambers Mihai Surdeanu Dan Jurafsky
Google Scholar CiteSeer X DBLP Database
Emili Sapena Lluis Padro Jordi Turmo
Google Scholar CiteSeer X DBLP Database
View PDF Creating a Coreference Resolution System for PolishAbstract: Although the availability of the natural language processing tools and the development of metrics to evaluate them increases, there is a certain gap to fill in that field for the less-resourced languages, such as Polish. Therefore the projects which are designed to extend the existing tools for diverse languages are the best starting point for making these languages more and more covered. This paper presents the results of the first attempt of the coreference resolution for Polish using statistical methods. It presents the conclusions from the process of adapting the Beautiful Anaphora Resolution Toolkit (BART; a system primarily designed for the English language) for Polish and collates its evaluation results with those of the previously implemented rule-based system. Finally, we describe our plans for the future usage of the tool and highlight the upcoming research to be conducted, such as the experiments of a larger scale and the comparison with other machine learning tools. Keywords: coreference resolution, BART, anaphora resolution, machine learning
Mateusz Kopec, Maciej Ogrodniczuk
Google Scholar CiteSeer X DBLP Database
View PDF Extending BART to Provide a Coreference Resolution System for GermanAbstract: We present a flexible toolkit-based approach to automatic coreference resolution on German text. We start with our previous work aimed at reimplementing the system from Soon et al. (2001) for English, and extend it to duplicate a version of the state-of-the-art proposal from Klenner and Ailloud (2009). Evaluation performed on a benchmarking dataset, namely the TuBa-D/Z corpus (Hinrichs et al., 2005b), shows that machine learning based coreference resolution can be robustly performed in a language other than English.
Samuel Broscheit , Simone Paolo Ponzetto Yannick Versley , Massimo Poesio
Google Scholar CiteSeer X DBLP Database
View PDF Coreference Resolution with Loose Transitivity ConstraintsAbstract: Our system treats coreference resolution as an integer linear programming (ILP) problem. Extending Denis and Baldridge (2007) and Finkel and Manning (2008)'s work, we exploit loose transitivity constraints on coreference pairs. Instead of enforcing transitivity closure constraints, which brings complexity, we employ a strategy to reduce the number of constraints without large performance decrease, i.e., eliminating coreference pairs with probability below a threshold . Experimental results show that it achieves a better performance than pairwise classifiers.
Xinxin Li, Xuan Wang, Shuhan Qi
Google Scholar CiteSeer X DBLP Database
View PDF Critical Reflections on Evaluation Practices in Coreference ResolutionAbstract: In this paper we revisit the task of quantitative evaluation of coreference resolution systems. We review the most commonly used metrics ( MUC , B 3 , CEAF and BLANC ) on the basis of their evaluation of coreference resolution in five texts from the OntoNotes corpus. We examine both the correlation between the metrics and the degree to which our human judgement of coreference resolution agrees with the metrics. In conclusion we claim that loss of information value is an essential factor, insufficiently adressed in current metrics, in human perception of the degree of success or failure of coreference resolution. We thus conjecture that including a layer of mention information weight could improve both the coreference resolution and its evaluation.
Gordana Ilic Holen
Google Scholar CiteSeer X DBLP Database
View PDF Multigraph Clustering for Unsupervised Coreference ResolutionAbstract: We present an unsupervised model for coreference resolution that casts the problem as a clustering task in a directed labeled weighted multigraph. The model outperforms most systems participating in the English track of the CoNLL'12 shared task.
Sebastian Martschat
Google Scholar CiteSeer X DBLP Database
Simone Paolo Ponzetto Massimo Poesio
Google Scholar CiteSeer X DBLP Database
View PDF Same Referent, Different Words: Unsupervised Mining of Opaque Coreferent MentionsAbstract: Coreference resolution systems rely heavily on string overlap (e.g., Google Inc. and Google ), performing badly on mentions with very different words ( opaque mentions) like Google and the search giant . Yet prior attempts to resolve opaque pairs using ontologies or distributional semantics hurt precision more than improved recall. We present a new unsupervised method for mining opaque pairs. Our intuition is to restrict distributional semantics to articles about the same event, thus promoting referential match. Using an English comparable corpus of tech news, we built a dictionary of opaque coreferent mentions (only 3% are in WordNet). Our dictionary can be integrated into any coreference system (it increases the performance of a state-of-the-art system by 1% F1 on all measures) and is easily extendable by using news aggregators.
Marta Recasens , and Dan Jurafsky
Google Scholar CiteSeer X DBLP Database
View PDF Chinese Coreference Resolution via Ordered FilteringAbstract: We in this paper present the model for our participation (BCMI) in the CoNLL-2012 Shared Task. This paper describes a pure rule-based method, which assembles different filters in a proper order. Different filters handle different situations and the filtering strategies are designed manually. These filters are assigned to different ordered tiers from general to special cases. We participated in the Chinese and English closed tracks, scored 51.83 and 59.24 respectively.
Xiaotian Zhang Chunyang Wu Hai Zhao
Google Scholar CiteSeer X DBLP Database
1-20 of 930: 12345...47


1914 users, 665 channels, 347 resources, 56080 items