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.

A comprehensive review on feature set used for anaphora resolution

Anaphora pronoun resolution is an active task of Natural Language Processing (NLP) that is necessary in many NLP applications. It allows revealing the ambiguity, verifying the coherence and understanding the context. The aim of this paper is how to combine salience factors in order to rich a best pronoun resolution in Arabic texts. The factors allow to disambiguate candidate antecedents and finding out, for each pronoun, the most likely one from the list of all potential antecedents. For this, we explore two approaches that use the same set of salience factors. Our first approach is based on reinforcement learning using a Markov Decision Process (MDP). It involves the combination subsets of salience factors. The second is an adaptation of our first approach according to multilingual robust approach of Mitkov. The comparative study shows that the performance of the same set of factors can change according to the resolution process and context. The evaluation of the two approaches is conducted on a corpus of literary texts.

How to Combine Salience Factors for Arabic Pronoun Anaphora Resolution

The anaphora resolution belongs to the attractive problems of the NLP field. In this paper, we treat the problem of resolving pronominal anaphora which are very abundant in Arabic texts. Our approach includes a set of steps; namely: the identification of anaphoric pronouns, removing the non-referential ones, identification of the lists of candidates from the context surrounding the identified anaphora and choosing the best candidate for each anaphoric pronoun. The last two steps could be seen as a dynamic and probabilistic process that consists of a sequence of decisions and could be modeled using a Markov Decision Process (MDP). In addition, we have opted for a reinforcement learning approach because it is an effective method for learning in an uncertain and stochastic environment like ours. Also, it could resolve the MDPs. In order to evaluate the proposed approach, we have developed a system that gives us encouraging results. The resolution accuracy reaches up to 80%.

Arabic Anaphora Resolution Using Markov Decision Process

A Generic approach for Pronominal Anaphora and Zero Anaphora resolution in Arabic language

No neural coreference resolver for Arabic exists, in fact we are not aware of any learning-based coreference resolver for Arabic since (Bjorkelund and Kuhn, 2014). In this paper, we introduce a coreference resolution system for Arabic based on Lee et al’s end-to-end architecture combined with the Arabic version of bert and an external mention detector. As far as we know, this is the first neural coreference resolution system aimed specifically to Arabic, and it substantially outperforms the existing state-of-the-art on OntoNotes 5.0 with a gain of 15.2 points conll F1. We also discuss the current limitations of the task for Arabic and possible approaches that can tackle these challenges.

Neural Coreference Resolution for Arabic

One of the challenges in natural language processing is to determine which pronouns to be referred to their intended referents in the discourse. Performing anaphora resolution is considered as an important task for a number of natural language processing applications such as information extraction, question answering and text summarization. Most of the earlier works of anaphora resolution have been applied to English and other languages. However, the work done in Arabic is not sufficiently studied. In this study, a hybrid approach that combines different architectures for resolving pronominal anaphora in Arabic language is presented. The hybrid model adopted the strategy based on the combination of a rule-based and machine learning approach. The collection of anaphora and respective possible antecedents was identified in a rule-based manner with morphological information taken into account. In addition, the selection of the most probable candidate as the antecedent of the anaphor was done by machine learning based on a k-Nearest Neighbor (k-NN) approach. In this study, the appropriate features to be used in this task were determined and their effect on the performance of anaphora resolution was investigated. Experiments of the proposed method were performed using the corpus of the Quran annotated with pronominal anaphora. The experimental results indicate that the proposed hybrid approach is completely reasonable and feasible for Arabic pronominal anaphora resolution.

/pdf/a-hybrid-approach-to-pronominal-anaphora-resolution-in-4w5l8c7w1n.pdf

Abdullatif Abolohom

Papers

A Hybrid Approach to Pronominal Anaphora Resolution in Arabic