A Constraint-Based Hypergraph Partitioning Approach to Coreference Resolution
| Autor: | Lluís Padró, Jordi Turmo, Emili Sapena |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics, Universitat Politècnica de Catalunya. GPLN - Grup de Processament del Llenguatge Natural |
| Rok vydání: | 2013 |
| Předmět: |
Linguistics and Language
Hypergraph Computer science Computational linguistics Context (language use) 02 engineering and technology Hypergraphs computer.software_genre Language and Linguistics Task (project management) Artificial Intelligence 020204 information systems 0202 electrical engineering electronic engineering information engineering Tractament del llenguatge natural (Informàtica) Coreference Grafs Teoria de business.industry Constraint satisfaction Resolution (logic) Informàtica::Llenguatges de programació [Àrees temàtiques de la UPC] Computer Science Applications Constraint (information theory) 020201 artificial intelligence & image processing State (computer science) Artificial intelligence business computer Natural language processing |
| Zdroj: | UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) Recercat. Dipósit de la Recerca de Catalunya Universitat Jaume I |
| ISSN: | 1530-9312 0891-2017 |
| Popis: | This work is focused on research in machine learning for coreference resolution. Coreference resolution is a natural language processing task that consists of determining the expressions in a discourse that refer to the same entity. The main contributions of this article are (i) a new approach to coreference resolution based on constraint satisfaction, using a hypergraph to represent the problem and solving it by relaxation labeling; and (ii) research towards improving coreference resolution performance using world knowledge extracted from Wikipedia. The developed approach is able to use an entity-mention classification model with more expressiveness than the pair-based ones, and overcome the weaknesses of previous approaches in the state of the art such as linking contradictions, classifications without context, and lack of information evaluating pairs. Furthermore, the approach allows the incorporation of new information by adding constraints, and research has been done in order to use world knowledge to improve performances. RelaxCor, the implementation of the approach, achieved results at the state-of-the-art level, and participated in international competitions: SemEval-2010 and CoNLL-2011. RelaxCor achieved second place in CoNLL-2011. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|