Pushpak Bhattacharyya - Böcker

Machine Translation and Transliteration involving Related, Low-resource Languages discusses an important aspect of natural language processing that has received lesser attention: translation and transliteration involving related languages in a low-resource setting. This is a very relevant real-world scenario for people living in neighbouring states/provinces/countries who speak similar languages and need to communicate with each other, but training data to build supporting MT systems is limited. The book discusses different characteristics of related languages with rich examples and draws connections between two problems: translation for related languages and transliteration. It shows how linguistic similarities can be utilized to learn MT systems for related languages with limited data. It comprehensively discusses the use of subword-level models and multilinguality to utilize these linguistic similarities. The second part of the book explores methods for machine transliteration involving related languages based on multilingual and unsupervised approaches. Through extensive experiments over a wide variety of languages, the efficacy of these methods is established. Features Novel methods for machine translation and transliteration between related languages, supported with experiments on a wide variety of languages. An overview of past literature on machine translation for related languages. A case study about machine translation for related languages between 10 major languages from India, which is one of the most linguistically diverse country in the world. The book presents important concepts and methods for machine translation involving related languages. In general, it serves as a good reference to NLP for related languages. It is intended for students, researchers and professionals interested in Machine Translation, Translation Studies, Multilingual Computing Machine and Natural Language Processing. It can be used as reference reading for courses in NLP and machine translation.Anoop Kunchukuttan is a Senior Applied Researcher at Microsoft India. His research spans various areas on multilingual and low-resource NLP. Pushpak Bhattacharyya is a Professor at the Department of Computer Science, IIT Bombay. His research areas are Natural Language Processing, Machine Learning and AI (NLP-ML-AI). Prof. Bhattacharyya has published more than 350 research papers in various areas of NLP.

Machine Translation and Transliteration involving Related, Low-resource Languages discusses an important aspect of natural language processing that has received lesser attention: translation and transliteration involving related languages in a low-resource setting. This is a very relevant real-world scenario for people living in neighbouring states/provinces/countries who speak similar languages and need to communicate with each other, but training data to build supporting MT systems is limited. The book discusses different characteristics of related languages with rich examples and draws connections between two problems: translation for related languages and transliteration. It shows how linguistic similarities can be utilized to learn MT systems for related languages with limited data. It comprehensively discusses the use of subword-level models and multilinguality to utilize these linguistic similarities. The second part of the book explores methods for machine transliteration involving related languages based on multilingual and unsupervised approaches. Through extensive experiments over a wide variety of languages, the efficacy of these methods is established. Features Novel methods for machine translation and transliteration between related languages, supported with experiments on a wide variety of languages. An overview of past literature on machine translation for related languages. A case study about machine translation for related languages between 10 major languages from India, which is one of the most linguistically diverse country in the world. The book presents important concepts and methods for machine translation involving related languages. In general, it serves as a good reference to NLP for related languages. It is intended for students, researchers and professionals interested in Machine Translation, Translation Studies, Multilingual Computing Machine and Natural Language Processing. It can be used as reference reading for courses in NLP and machine translation.Anoop Kunchukuttan is a Senior Applied Researcher at Microsoft India. His research spans various areas on multilingual and low-resource NLP. Pushpak Bhattacharyya is a Professor at the Department of Computer Science, IIT Bombay. His research areas are Natural Language Processing, Machine Learning and AI (NLP-ML-AI). Prof. Bhattacharyya has published more than 350 research papers in various areas of NLP.

Three paradigms have dominated machine translation (MT)—rule-based machine translation (RBMT), statistical machine translation (SMT), and example-based machine translation (EBMT). These paradigms differ in the way they handle the three fundamental processes in MT—analysis, transfer, and generation (ATG). In its pure form, RBMT uses rules, while SMT uses data. EBMT tries a combination—data supplies translation parts that rules recombine to produce translation.Machine Translation compares and contrasts the salient principles and practices of RBMT, SMT, and EBMT. Offering an exposition of language phenomena followed by modeling and experimentation, the text: Introduces MT against the backdrop of language divergence and the Vauquois trianglePresents expectation maximization (EM)-based word alignment as a turning point in the history of MTDiscusses the most important element of SMT—bilingual word alignment from pairs of parallel translationsExplores the IBM models of MT, explaining how to find the best alignment given a translation pair and how to find the best translation given a new input sentenceCovers the mathematics of phrase-based SMT, phrase-based decoding, and the Moses SMT environmentProvides complete walk-throughs of the working of interlingua-based and transfer-based RBMTAnalyzes EBMT, showing how translation parts can be extracted and recombined to translate a new input, all automaticallyIncludes numerous examples that illustrate universal translation phenomena through the usage of specific languagesMachine Translation is designed for advanced undergraduate-level and graduate-level courses in machine translation and natural language processing. The book also makes a handy professional reference for computer engineers.Print Versions of this book also include access to the ebook version.

This contributed volume discusses in detail the process of construction of a WordNet of 18 Indian languages, called “Indradhanush” (rainbow) in Hindi. It delves into the major challenges involved in developing a WordNet in a multilingual country like India, where the information spread across the languages needs utmost care in processing, synchronization and representation. The project has emerged from the need of millions of people to have access to relevant content in their native languages, and it provides a common interface for information sharing and reuse across the Indian languages. The chapters discuss important methods and strategies of language computation, language data processing, lexical selection and management, and language-specific synset collection and representation, which are of utmost value for the development of a WordNet in any language. The volume overall gives a clear picture of how WordNet is developed in Indian languages and how this canbe utilized in similar projects for other languages. It includes illustrations, tables, flowcharts, and diagrams for easy comprehension.   This volume is of interest to researchers working in the areas of language processing, machine translation, word sense disambiguation, culture studies, language corpus generation, language teaching, dictionary compilation, lexicographic queries, cross-lingual knowledge sharing, e-governance, and many other areas of linguistics and language technology.

This book describes the authors’ investigations of computational sarcasm based on the notion of incongruity. In addition, it provides a holistic view of past work in computational sarcasm and the challenges and opportunities that lie ahead. Sarcastic text is a peculiar form of sentiment expression and computational sarcasm refers to computational techniques that process sarcastic text. To first understand the phenomenon of sarcasm, three studies are conducted: (a) how is sarcasm annotation impacted when done by non-native annotators? (b) How is sarcasm annotation impacted when the task is to distinguish between sarcasm and irony? And (c) can targets of sarcasm be identified by humans and computers. Following these studies, the book proposes approaches for two research problems: sarcasm detection and sarcasm generation. To detect sarcasm, incongruity is captured in two ways: ‘intra-textual incongruity’ where the authors look at incongruity within the text to be classified (i.e., target text) and ‘context incongruity’ where the authors incorporate information outside the target text. These approaches use machine-learning techniques such as classifiers, topic models, sequence labelling, and word embeddings. These approaches operate at multiple levels: (a) sentiment incongruity (based on sentiment mixtures), (b) semantic incongruity (based on word embedding distance), (c) language model incongruity (based on unexpected language model), (d) author’s historical context (based on past text by the author), and (e) conversational context (based on cues from the conversation). In the second part of the book, the authors present the first known technique for sarcasm generation, which uses a template-based approach to generate a sarcastic response to user input. This book will prove to be a valuable resource for researchers working on sentiment analysis, especially as applied to automation in social media.

The two-volume set CCIS 827 and 828 constitutes the thoroughly refereed proceedings of the Third International Conference on Next Generation Computing Technologies, NGCT 2017, held in Dehradun, India, in October 2017.The 135 full papers presented were carefully reviewed and selected from 948 submissions. There were organized in topical sections named: Smart and Innovative Trends in Communication Protocols and Standards; Smart and Innovative Trends in Computational Intelligence and Data Science; Smart and Innovative Trends in Image Processing and Machine Vision; Smart Innovative Trends in Natural Language Processing for Indian Languages; Smart Innovative Trends in Security and Privacy.

The two-volume set CCIS 827 and 828 constitutes the thoroughly refereed proceedings of the Third International Conference on Next Generation Computing Technologies, NGCT 2017, held in Dehradun, India, in October 2017.The 135 full papers presented were carefully reviewed and selected from 948 submissions. There were organized in topical sections named: Smart and Innovative Trends in Communication Protocols and Standards; Smart and Innovative Trends in Computational Intelligence and Data Science; Smart and Innovative Trends in Image Processing and Machine Vision; Smart Innovative Trends in Natural Language Processing for Indian Languages; Smart Innovative Trends in Security and Privacy.

This contributed volume discusses in detail the process of construction of a WordNet of 18 Indian languages, called “Indradhanush” (rainbow) in Hindi. It delves into the major challenges involved in developing a WordNet in a multilingual country like India, where the information spread across the languages needs utmost care in processing, synchronization and representation. The project has emerged from the need of millions of people to have access to relevant content in their native languages, and it provides a common interface for information sharing and reuse across the Indian languages. The chapters discuss important methods and strategies of language computation, language data processing, lexical selection and management, and language-specific synset collection and representation, which are of utmost value for the development of a WordNet in any language. The volume overall gives a clear picture of how WordNet is developed in Indian languages and how this canbe utilized in similar projects for other languages. It includes illustrations, tables, flowcharts, and diagrams for easy comprehension.   This volume is of interest to researchers working in the areas of language processing, machine translation, word sense disambiguation, culture studies, language corpus generation, language teaching, dictionary compilation, lexicographic queries, cross-lingual knowledge sharing, e-governance, and many other areas of linguistics and language technology.

This book shows ways of augmenting the capabilities of Natural Language Processing (NLP) systems by means of cognitive-mode language processing. The authors employ eye-tracking technology to record and analyze shallow cognitive information in the form of gaze patterns of readers/annotators who perform language processing tasks. The insights gained from such measures are subsequently translated into systems that help us (1) assess the actual cognitive load in text annotation, with resulting increase in human text-annotation efficiency, and (2) extract cognitive features that, when added to traditional features, can improve the accuracy of text classifiers. In sum, the authors’ work successfully demonstrates that cognitive information gleaned from human eye-movement data can benefit modern NLP. Currently available Natural Language Processing (NLP) systems are weak AI systems: they seek to capture the functionality of human language processing, without worrying about how thisprocessing is realized in human beings’ hardware. In other words, these systems are oblivious to the actual cognitive processes involved in human language processing. This ignorance, however, is NOT bliss! The accuracy figures of all non-toy NLP systems saturate beyond a certain point, making it abundantly clear that “something different should be done.”

This book describes the authors’ investigations of computational sarcasm based on the notion of incongruity. In addition, it provides a holistic view of past work in computational sarcasm and the challenges and opportunities that lie ahead. Sarcastic text is a peculiar form of sentiment expression and computational sarcasm refers to computational techniques that process sarcastic text. To first understand the phenomenon of sarcasm, three studies are conducted: (a) how is sarcasm annotation impacted when done by non-native annotators? (b) How is sarcasm annotation impacted when the task is to distinguish between sarcasm and irony? And (c) can targets of sarcasm be identified by humans and computers. Following these studies, the book proposes approaches for two research problems: sarcasm detection and sarcasm generation. To detect sarcasm, incongruity is captured in two ways: ‘intra-textual incongruity’ where the authors look at incongruity within the text to be classified (i.e., target text) and ‘context incongruity’ where the authors incorporate information outside the target text. These approaches use machine-learning techniques such as classifiers, topic models, sequence labelling, and word embeddings. These approaches operate at multiple levels: (a) sentiment incongruity (based on sentiment mixtures), (b) semantic incongruity (based on word embedding distance), (c) language model incongruity (based on unexpected language model), (d) author’s historical context (based on past text by the author), and (e) conversational context (based on cues from the conversation). In the second part of the book, the authors present the first known technique for sarcasm generation, which uses a template-based approach to generate a sarcastic response to user input. This book will prove to be a valuable resource for researchers working on sentiment analysis, especially as applied to automation in social media.

This book shows ways of augmenting the capabilities of Natural Language Processing (NLP) systems by means of cognitive-mode language processing.

The book covers several entity and relation extraction techniques starting from the traditional feature-based techniques to the recent techniques using deep neural models.