A Rule Based Approach for Anaphora Resolution
Varsha Singh1, Nisheeth Joshi2
1Varsha Singh, Department of Computer Science, Banasthali Vidyapith (Rajasthan), India.
2Nisheeth Joshi, Department of Computer Science, Banasthali Vidyapith (Rajasthan), India.
Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 2652-2657 | Volume-8 Issue-7, May 2019 | Retrieval Number: G5846058719/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In Natural Language Processing one of the challenges is how to determine which entity is referred in the discourse and how they correlate to each other? Anaphora resolution is one of the most important area in Natural Language Processing. In this paper, we present rule based approach to identify different types of anaphora and its antecedents for Hindi. We use Hidden Markov Model to POS tag the dataset and cases are used for the identification of preferred noun. At last, apply Centering algorithm for identification of pronoun and its referents. We have tested the system with 500 segments to resolve the anaphora
Keyword: Anaphora Resolution, Hidden Markov Model, Case Markers, Centering Algorithm.
Scope of the Article: Knowledge-based and Expert Systems