Entity-based Coreference Resolution combined with Discourse-New Detection
نویسنده
چکیده
Anaphora and coreference resolution is a well-studied topic in NLP research, allowing a deeper understanding of the text than shallow methods by revealing discourse structures. Traditional systems reason over mentions, rather than entities, and perform clustering after the resolution process. In this work, general drawbacks with this approach are considered and related works employing knowledge about entities during the resolution are shown as an alternative. Based on these works, GlAnCoRe, an entity-based coreference resolution system is implemented and evaluated, which combines discourse new detection with coreference resolution to first extract entities from a text and then assign all mentions to corresponding entities based on a machine learning classifier. Both components are optimized separately using feature selection, before they are combined with a meta classifier to counterbalance errors of discourse new detection. The final setup is evaluated on automatically created annotations and true mentions and yields a promising averaged F-Score of 60.83% based on MUC, B-Cubed and CEAF as evaluation metrics, showing that the proposed architecture is capable of handling coreference resolution reasonably well and is worth to be enhanced and investigated to a greater extent in future.tionen und weitere Untersuchungen in Zukunft lohnen.
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 کاملSupervised Models for Coreference Resolution
Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of recent research have attempted to improve these mention-pair classifiers, one by learning a mentionranking model to rank preceding mentions for a given anaphor, and the other by training an entity-mention classifier to...
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 کاملCoreference-inspired Coherence Modeling
Research on coreference resolution and summarization has modeled the way entities are realized as concrete phrases in discourse. In particular there exist models of the noun phrase syntax used for discourse-new versus discourse-old referents, and models describing the likely distance between a pronoun and its antecedent. However, models of discourse coherence, as applied to information ordering...
متن کاملA Metric for Evaluating Discourse Coherence based on Coreference Resolution
We propose a simple and effective metric for automatically evaluating discourse coherence of a text using the outputs of a coreference resolution model. According to the idea that a writer tends to appropriately utilise coreference relations when writing a coherent text, we introduce a metric of discourse coherence based on automatically identified coreference relations. We empirically evaluate...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011