A comprehensive review on feature set used for anaphora resolution

摘要

In linguistics, the Anaphora Resolution (AR) is the method of identifying the antecedent for anaphora. In simple terms, this is the problem that helps to solve what the expression referring to a referent refers to. It is considered to be one of the tedious tasks in Natural Language Processing (NLP). AR’s burgeoning popularity among researchers is attributable to its strong relevance to machine translation, text summarization, chatbot, question answering, and many others. This paper presents a review of AR approaches based on significant features utilized to perform this task and presents the evaluation metrics for this field. The feature is a relevant term related to AR that provides vital information regarding anaphor, antecedent, and relation between them. In this context, features represent the lexical, syntactical, semantical, and positional relationship between anaphor and its possible candidate antecedent. The performance of the Anaphora resolution system is profoundly dependent on the features used in the AR system. Hence, the selection of features for the AR system is highly significant. The main emphasis is to provide an overview of the various features needed to extract both the Anaphora and the Antecedent, respectively, used in different AR systems, present in literature. It is observed that syntactical information enhances the correctness of determining the properties for the existence of an anaphor and antecedent identification. Nowadays the trend is changing from hand-crafted feature dependent methods to deep learning approaches which try to learn feature representation. The performance of deep learning is progressing due to the accessibility of additional data and more powerful computing resources. This survey will provide the state-of art for the better understanding of solving AR problem from the feature selection perspective. The findings of this survey are useful to provide valuable insight into present trends and are helpful for researchers who are looking for developing AR system within given constraints.