LINGVISTIK CHEKLOVLAR – KOREFERENTLIKNI AVTOMATIK HAL ETISHNING ASOSI
Keywords:
NLP, coreference, antecedent, anaphor, linguistic feature, vector, pronoun, textAbstract
Natural Language Processing (NLP) is a subfield of Artificial Intelligence, that aims to facilitate interactions between computers and humans. It is known, that the specific features of the language create difficulties in the process of automatically extracting meaning from the text. The human mind is able to directly understand the content of the text. But in order for the Artificial Intelligence to interpret it correctly, the coreference must be resolved with high accuracy.
In addition, the development of fields such as Machine Translation, Question Answering, Text Summarization, Sentiment Analysis, Text Classification, Speech recognition, Named Entity Recognition, Chatbot is also related to the Coreference Resolution. In this article, the Coreference Resolution is a subfield of NLP, its importance is highlighted, problem of the participation of linguistic features in this process is investigated.
References
Vincent Ng. Machine Learning for Entity Coreference Resolution: A Retrospective Look at Two Decades of Research. / Proceedings of the Thirty-First AAAI, Conference on Artificial Intelligence (AAAI-17), pp.4877-4884.
Elango P. Coreference Resolution: A Survey. – University of Wisconsin, Madison, WI, pp.1-8, 2005.
Shi Chunqi, Verhagen Marc, Pustejovsky James. A Conceptual Framework of Natural Language Processing Pipeline Application. / Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT, pp.53-59, Dublin, Ireland, 2014.
Soon, W., H. Ng, and D. Lim (2001): A Machine Learning Approach to Coreference Resolution of Noun Phrases. / Computational Linguistics 27 (4), pp. 521–544.
Yimeng Zhang, Yangbo Zhu. Machine Learning for Coreference Resolution: Recent Developments, pp.1-23
https://www.cs.cmu.edu/~yimengz/papers/Coreference_survey.pdf
