Translation, Brains and the Computer : A Neurolinguistic Solution to Ambiguity and Complexity in Machine Translation / / by Bernard Scott

• Record Nr.: UNINA9910299280503321
• Autore: Scott Bernard
• Pubbl/distr/stampa: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2018
• ISBN: 3-319-76629-5
• Edizione: [1st ed. 2018.]
• Descrizione fisica: 1 online resource (XVI, 241 p. 55 illus.)
• Collana: Machine Translation: Technologies and Applications, , 2522-8021 ; ; 2
• Disciplina: 006.35
• Soggetti: Natural language processing (Computer science); Computational linguistics; Psycholinguistics; Natural Language Processing (NLP); Computational Linguistics
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di contenuto: 1 Introduction -- 2 Background -- Logos Model Beginnings -- Advent of Statistical MT -- Overview of Logos Model Translation Process -- Psycholinguistic and Neurolinguistic Assumptions -- On Language and Grammar -- Conclusion -- 3 – Language and Ambiguity: Psycholinguistic Perspectives -- Levels of Ambiguity -- Language Acquisition and Translation -- Psycholinguistic Bases of Language Skills -- Practical Implications for Machine Translation -- Psycholinguistics in a Machine -- Conclusion -- 4– Language and Complexity: Neurolinguistic Perspectives -- Cognitive Complexity -- A Role for Semantic Abstraction -- Connectionism and Brain Simulation -- Logos Model as a Neural Network -- Language Processing in the Brain -- MT Performance and Underlying Competence -- Conclusion -- 5 – Syntax and Semantics: Dichotomy or Integration? -- Syntax versus Semantics: Is There a Third, Semantico- Syntactic Perspective? -- Recent Views of the Cerebral Process -- Syntax and Semantics: How Do They Relate? -- Conclusion -- 6 –Logos Model: Design and Performance -- The Translation Problem -- How Do You Represent Natural Language? -- How Do You Store Linguistic Knowledge? -- How Do You Apply Stored Knowledge To The Input Stream? -- How do you ; Effect Target Transfer and Generation? -- How Do You Deal with Complexity Issues? -- Conclusion -- 7 – Some limits on Translation Quality -- First Example -- Second Example -- Other Translation Examples -- Balancing the Picture -- Conclusion -- 8 – Deep Learning MT and Logos Model -- Points of Similarity and Differences -- Deep Learning, Logos Model and the Brain -- On Learning -- The Hippocampus Again -- Conclusion -- Part II -- The SAL Representation Language -- SAL Nouns -- SAL Verbs -- SAL Adjectives -- SAL Adverbs.
• Sommario/riassunto: This book is about machine translation (MT) and the classic problems associated with this language technology. It examines the causes of these problems and, for linguistic, rule-based systems, attributes the cause to language’s ambiguity and complexity and their interplay in logic-driven processes. For non-linguistic, data-driven systems, the book attributes translation shortcomings to the very lack of linguistics. It then proposes a demonstrable way to relieve these drawbacks in the shape of a working translation model (Logos Model) that has taken its inspiration from key assumptions about psycholinguistic and neurolinguistic function. The book suggests that this brain-based mechanism is effective precisely because it bridges both linguistically driven and data-driven methodologies. It shows how simulation of this cerebral mechanism has freed this one MT model from the all-important, classic problem of complexity when coping with the ambiguities of language. Logos Model accomplishes this by a data-driven process that does not sacrifice linguistic knowledge, but that, like the brain, integrates linguistics within a data-driven process. As a consequence, the book suggests that the brain-like mechanism embedded in this model has the potential to contribute to further advances in machine translation in all its technological instantiations.