China 
Africa 
Explore chapters and articles related to this topic
Natural Language Processing Associated with Expert Systems
Published in Jay Liebowitz, The Handbook of Applied Expert Systems, 2019
One of the hardiest problems in Computational Linguistic and NLP processing concerns finding algorithmic procedures for solving anaphora. Anaphora is a linguistic problem concerning the fact that pronouns (like “he,” “himself,” or “they”), possessive determiners (like “her” or “their”) and full noun phrases (like “the patient,” see below), can be used to denote implicitly entities already mentioned in the discourse; by “discourse” we mean here a coherent segment of text, either written or spoken. Examples can be, respectively, “John went to the party and he got drunk,” “this girl is very nice, and her brother is charming,” “Jack was admitted to the hospital early this morning. The patient complained of chest pain.” Solving anaphors implies then the following two steps: Realising that the pronoun, the possessive determiner, or the noun phrase (NP) represents an implicit reference (normally, an abbreviated reference) to some other entities — this first step is not so trivial, especially when the anaphora is constructed through an NP; not all the personal pronouns are necessarily anaphoric, etc.Disambiguating the reference, by substituting to this last one the entity (the “antecedent) that represents its real identity.
Natural Language Processing
Published in Vishal Jain, Akash Tayal, Jaspreet Singh, Arun Solanki, Cognitive Computing Systems, 2021
V. Vishnuprabha, Lino Murali, Daleesha M. Viswanathan
The linguistic action of referring back to a previously mentioned item in the text is termed as anaphora. The word or phrase “referring back” in the text is known as anaphor, and the thing which it refers to is its antecedent. When the anaphor refers to an antecedent, and when both have the same referent in the real world, they are termed coreferential. The interpretation of anaphors, known as anaphora resolution, has a vital role in the understanding of discourse.
A survey on non-factoid question answering systems
Published in International Journal of Computers and Applications, 2022
Manvi Breja, Sanjay Kumar Jain
Dataset preparationTo collect a corpus of non-factoid questions and their answers comprising a significant number of QA pairs having possible question patterns.To address incompleteness and ambiguity of questions in the corpus by preprocessing them with anaphora, coreference resolution and common sense reasoning mechanisms.To develop a sufficient training dataset with similar distribution of attributes in training and testing set where machine learning techniques are to be applied to prevent any overfitting or underfitting.
Inter-Subdomain Relation Extraction for Agriculture Domain
Published in IETE Technical Review, 2018
Niladri Chatterjee, Neha Kaushik, Bhavya Bansal
Figure 7 shows an example text where the “it” in the first line and “its” in the third line, both refer to the same entity, “sugarcane.” Identifying such occurrences in the text and resolving the anaphors is a well-known technique in the field of NLP and is called as co-reference resolution [15]. It involves identification of all the expressions referring to the same entity. Figure 8 shows the same text shown in Figure 7 with the terms highlighted that are obtained after the application of co-reference resolution.
Adjudication of coreference annotations via answer set optimisation
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2018
Note that anaphora resolution (Clark & González-Brenes, 2008; Hirst, 1981; Kehler, Kertz, Rohde, & Elman, 2008; Mitkov, 1999) is a different task than coreference resolution. The former deals only with references to earlier parts of a text and sometimes even only with references where a pronoun points to another phrase. Contrary to that, coreference resolution also deals with noun phrases that can refer to each other, and references can be in any direction within the text.