A Coreference Resolution Model on Excerpts from a Novel
نویسندگان
چکیده
This paper describes a model for coreference resolution integrated within a general anaphora resolution engine. We focus on finding coreference chains in unrestricted text, considering all mentions of entities, expressed as noun-phrases, different types of pronouns (including demonstratives and wh-pronouns) and even numerals. We have experimented with texts from the belletristic register. We have created a specialized corpus for coreference resolution research. While the interannotator agreement (in terms of measure) was, for some texts, as low as 60%, our system output achieves scores between 63% and 70%.
منابع مشابه
Corpus 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 کاملCorefrence resolution with deep learning in the Persian Labnguage
Coreference resolution is an advanced issue in natural language processing. Nowadays, due to the extension of social networks, TV channels, news agencies, the Internet, etc. in human life, reading all the contents, analyzing them, and finding a relation between them require time and cost. In the present era, text analysis is performed using various natural language processing techniques, one ...
متن کاملA Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution
We present a novel hierarchical distancedependent Bayesian model for event coreference resolution. While existing generative models for event coreference resolution are completely unsupervised, our model allows for the incorporation of pairwise distances between event mentions — information that is widely used in supervised coreference models to guide the generative clustering processing for be...
متن کاملCoreference resolution via hypergraph partitioning
Coreference resolution is one of the most fundamental Natural Language Processing tasks, aiming to identify the coreference relation in texts. The task is to group mentions (i.e. phrases of interest) into sets, so that all mentions in one set refer to the same entity (i.e. a real world object). Mentions are conventionally proper names, common nouns and pronouns. Lately, the coreference task has...
متن کاملEnd-to-End Coreference Resolution via Hypergraph Partitioning
We describe a novel approach to coreference resolution which implements a global decision via hypergraph partitioning. In constrast to almost all previous approaches, we do not rely on separate classification and clustering steps, but perform coreference resolution globally in one step. Our hypergraph-based global model implemented within an endto-end coreference resolution system outperforms t...
متن کامل