Thinking Like Humans: A New Approach to Machine Translation

Existing machine translation approaches do not adequately mimic how humans do translation from one natural language to another. This paper presents a novel approach to machine translation that is inspired by how humans translate natural languages. We have exploited the theory of psycholinguistic sentence-parsing to develop a human-like machine translation system. This approach has been modeled as a multi-agent system, named EnSiMaS, which translates an English sentence into Sinhala sentence. The multi-agent system has been implemented through the MaSMT framework with two manager agents and over 100 agents which deliberate on different aspects of machine translation. These agents are clustered into eight-agent swarms to consider morphological, syntactic, and semantic concerns of the source and the target languages. The EnSiMaS system has been tested with the different types of sentences and successful results were obtained.

[1]  Asoka S. Karunananda,et al.  Existing systems and approaches for machine translation : a review , 2016 .

[2]  Asoka S. Karunananda,et al.  MaSMT: A Multi-agent system development framework for English-Sinhala machine translation , 2018 .

[3]  D. I. De Silva,et al.  A Translator from Sinhala to English and English to Sinhala (SEES) , 2012, International Conference on Advances in ICT for Emerging Regions (ICTer2012).

[4]  A. S. Karunananda,et al.  Theoretical based approach to English to Sinhala machine translation , 2009, 2009 International Conference on Industrial and Information Systems (ICIIS).

[5]  Theodore Marinis,et al.  Psycholinguistic techniques in second language acquisition research , 2003 .

[6]  G. Rzevski,et al.  Multi-agent system technology for morphological analysis , 2019 .

[7]  A. Hollingworth,et al.  Thematic Roles Assigned along the Garden Path Linger , 2001, Cognitive Psychology.

[8]  G. Rzevski,et al.  Phrase-level English to Sinhala machine translation with multi-agent approach , 2017, 2017 IEEE International Conference on Industrial and Information Systems (ICIIS).

[9]  A. S. Karunananda,et al.  Computational model of grammar for English to Sinhala Machine Translation , 2011, 2011 International Conference on Advances in ICT for Emerging Regions (ICTer).

[10]  James H. Martin,et al.  Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd Edition , 2000, Prentice Hall series in artificial intelligence.

[11]  Ioan Cuza,et al.  Machine Translation and Computer-Assisted Translation: , 2010 .

[12]  Asoka S. Karunananda,et al.  A Multi-agent Solution For Managing Complexity In English To Sinhala Machine Translation , 2016 .

[13]  Asoka S. Karunananda,et al.  A novel approach for English to Sinhala machine translation , 2010 .

[14]  G. Rzevski,et al.  Managing Complexity , 2014 .

[15]  K Christianson,et al.  Misinterpretations of Garden-Path Sentences: Implications for Models of Sentence Processing and Reanalysis , 2001, Journal of psycholinguistic research.

[16]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[17]  L Frazier,et al.  Constraint satisfaction as a theory of sentence processing , 1995, Journal of psycholinguistic research.