Referring expression generation in context PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Referring expression generation in context PDF full book. Access full book title Referring expression generation in context by Fahime Same. Download full books in PDF and EPUB format.
Author: Fahime Same Publisher: Language Science Press ISBN: 3961104719 Category : Language Arts & Disciplines Languages : en Pages : 276
Book Description
Reference production, often termed Referring Expression Generation (REG) in computational linguistics, encompasses two distinct tasks: (1) one-shot REG, and (2) REG-in-context. One-shot REG explores which properties of a referent offer a unique description of it. In contrast, REG-in-context asks which (anaphoric) referring expressions are optimal at various points in discourse. This book offers a series of in-depth studies of the REG-in-context task. It thoroughly explores various aspects of the task such as corpus selection, computational methods, feature analysis, and evaluation techniques. The comparative study of different corpora highlights the pivotal role of corpus choice in REG-in-context research, emphasizing its influence on all subsequent model development steps. An experimental analysis of various feature-based machine learning models reveals that those with a concise set of linguistically-informed features can rival models with more features. Furthermore, this work highlights the importance of paragraph-related concepts, an area underexplored in Natural Language Generation (NLG). The book offers a thorough evaluation of different approaches to the REG-in-context task (rule-based, feature-based, and neural end-to-end), and demonstrates that well-crafted, non-neural models are capable of matching or surpassing the performance of neural REG-in-context models. In addition, the book delves into post-hoc experiments, aimed at improving the explainability of both neural and classical REG-in-context models. It also addresses other critical topics, such as the limitations of accuracy-based evaluation metrics and the essential role of human evaluation in NLG research. These studies collectively advance our understanding of REG-in-context. They highlight the importance of selecting appropriate corpora and targeted features. They show the need for context-aware modeling and the value of a comprehensive approach to model evaluation and interpretation. This detailed analysis of REG-in-context paves the way for developing more sophisticated, linguistically-informed, and contextually appropriate NLG systems.
Author: Fahime Same Publisher: Language Science Press ISBN: 3961104719 Category : Language Arts & Disciplines Languages : en Pages : 276
Book Description
Reference production, often termed Referring Expression Generation (REG) in computational linguistics, encompasses two distinct tasks: (1) one-shot REG, and (2) REG-in-context. One-shot REG explores which properties of a referent offer a unique description of it. In contrast, REG-in-context asks which (anaphoric) referring expressions are optimal at various points in discourse. This book offers a series of in-depth studies of the REG-in-context task. It thoroughly explores various aspects of the task such as corpus selection, computational methods, feature analysis, and evaluation techniques. The comparative study of different corpora highlights the pivotal role of corpus choice in REG-in-context research, emphasizing its influence on all subsequent model development steps. An experimental analysis of various feature-based machine learning models reveals that those with a concise set of linguistically-informed features can rival models with more features. Furthermore, this work highlights the importance of paragraph-related concepts, an area underexplored in Natural Language Generation (NLG). The book offers a thorough evaluation of different approaches to the REG-in-context task (rule-based, feature-based, and neural end-to-end), and demonstrates that well-crafted, non-neural models are capable of matching or surpassing the performance of neural REG-in-context models. In addition, the book delves into post-hoc experiments, aimed at improving the explainability of both neural and classical REG-in-context models. It also addresses other critical topics, such as the limitations of accuracy-based evaluation metrics and the essential role of human evaluation in NLG research. These studies collectively advance our understanding of REG-in-context. They highlight the importance of selecting appropriate corpora and targeted features. They show the need for context-aware modeling and the value of a comprehensive approach to model evaluation and interpretation. This detailed analysis of REG-in-context paves the way for developing more sophisticated, linguistically-informed, and contextually appropriate NLG systems.
Author: Kees Van Deemter Publisher: MIT Press ISBN: 0262335336 Category : Computers Languages : en Pages : 350
Book Description
An argument that computational models can shed light on referring, a fundamental and much-studied aspect of communication. To communicate, speakers need to make it clear what they are talking about. The act of referring, which anchors words to things, is a fundamental aspect of language. In this book, Kees van Deemter shows that computational models of reference offer attractive tools for capturing the complexity of referring. Indeed, the models van Deemter presents cover many issues beyond the basic idea of referring to an object, including reference to sets, approximate descriptions, descriptions produced under uncertainty concerning the hearer's knowledge, and descriptions that aim to inform or influence the hearer. The book, which can be read as a case study in cognitive science, draws on perspectives from across the cognitive sciences, including philosophy, experimental psychology, formal logic, and computer science. Van Deemter advocates a combination of computational modeling and careful experimentation as the preferred method for expanding these insights. He then shows this method in action, covering a range of algorithms and a variety of methods for testing them. He shows that the method allows us to model logically complicated referring expressions, and demonstrates how we can gain an understanding of reference in situations where the speaker's knowledge is difficult to assess or where the referent resists exact definition. Finally, he proposes a program of research that addresses the open questions that remain in this area, arguing that this program can significantly enhance our understanding of human communication.
Author: Robert Dale Publisher: CRC Press ISBN: 9780824790004 Category : Business & Economics Languages : en Pages : 974
Book Description
This study explores the design and application of natural language text-based processing systems, based on generative linguistics, empirical copus analysis, and artificial neural networks. It emphasizes the practical tools to accommodate the selected system.
Author: Anja Belz Publisher: Springer ISBN: 3540278230 Category : Computers Languages : en Pages : 227
Book Description
The Third International Conference on Natural Language Generation (INLG 2004) was held from 14th to 16th July 2004 at Careys Manor, Brockenhurst, UK. Supported by the Association for Computational Linguistics Special - terest Group on Generation, the conference continued a twenty-year tradition of biennial international meetings on research into natural language generation. Recent conference venues have included Mitzpe Ramon, Israel (INLG 2000) and New York, USA (INLG 2002). It was our pleasure to invite the thriving and friendly NLG research community to the beautiful New Forest in the south of England for INLG 2004. INLG is the leading international conference in the ?eld of natural language generation. It provides a forum for the presentation and discussion of original research on all aspects of the generation of language, including psychological modelling of human language production as well as computational approaches to the automatic generation of language. This volume includes a paper by the keynote speaker, Ardi Roelofs of the Max Planck Institute for Psycholingu- tics and the F. C. Donders Centre for CognitiveNeuroimaging,18 regular papers reportingthelatestresearchresultsanddirections,and4studentpapersdescr- ing doctoral work in progress. These papers reveal a particular concentration of current research e?ort on statistical and machine learning methods, on referring expressions, and on variation in surface realisation. The papers were selected from 46 submissions from all over the world (27 from Europe, 13 from North America, 6 from elsewhere), which were subjected to a rigorous double-blind reviewing process undertaken by our hard-working programme committee.
Author: Kees van Deemter Publisher: Frontiers Media SA ISBN: 2889451607 Category : Communication Languages : en Pages : 245
Book Description
To communicate, speakers need to make it clear what they are talking about. Referring expressions play a crucial part in achieving this, by anchoring utterances to things. Examples of referring expressions include noun phrases such as “this phenomenon”, “it” and “the phenomenon to which this Topic is devoted”. Reference is studied throughout the Cognitive Sciences (from philosophy and logic to neuro-psychology, computer science and linguistics), because it is thought to lie at the core of all of communication. Recent years have seen a new wave of work on models of referring, as witnessed by a number of recent research projects, books, and journal Special Issues. The Research Topic “Models of Reference” in Frontiers in Psychology is a new milestone, focusing on contributions from Psycholinguistics and Computational Linguistics. The articles in it are concerned with such issues as audience design, overspecification, visual perception, and variation between speakers.
Author: Robert Dale Publisher: Bradford Book ISBN: Category : Computers Languages : en Pages : 304
Book Description
Robert Dale presents a detailed description of the development of algorithms for the generation of referring expressions, and of the underlying structures that motivate these algorithms, in a dynamic domain. He provides a number of novel results in both knowledge representation and natural language generation that should have straightforward applications in other domains. Dale describes EPICURE, a natural language generating system, and its capacity to create referring expressions in a domain embodying several interesting features: The entities in the domain consist of masses and sets as well as the more usual singular individuals; during the development of a discourse, the entities may take on new properties, existing entities may be destroyed, and new entities may be created; and the discourses within which the entities appear are hierarchically structured, allowing for the integration of discourse-structural constraints on the use of anaphoric expressions. EPICURE is designed to generate text from underlying plans. Dale uses cooking recipes as examples, showing how the system must determine what level of explanation is required and how the events in the plan must be modeled to ensure that the references generated are accurate.
Author: Arthur C. Graesser Publisher: Routledge ISBN: 1135659273 Category : Language Arts & Disciplines Languages : en Pages : 514
Book Description
This Handbook is a comprehensive overview of the multidisciplinary field of discourse processes. The editors hope to foster a more interdisciplinary approach to discourse processing with this Handbook, while simultaneously developing an appreciation within the field for multiple methods of establishing rigorous scientific claims. The field of discourse processes is currently fueled by seven dominant approaches: * discourse psychology; * corpus analysis; * computational discourse; * discourse technologies; * conversation analysis; * hybrid qualitative and quantitative approaches; and * cultural foundations. The contributors also discuss future trends in research, including corpus analyses, the integration of neuroscience with discourse research, and the development of more advanced computer technologies for analyzing discourse.
Author: Dimitris N. Christodoulakis Publisher: Springer ISBN: 3540451544 Category : Computers Languages : en Pages : 444
Book Description
This volume contains the papers prepared for the 2nd International Conference on Natural Language Processing, held 2-4 June in Patras, Greece. The conference program features invited talks and submitted papers, c- ering a wide range of NLP areas: text segmentation, morphological analysis, lexical knowledge acquisition and representation, grammar formalism and s- tacticparsing,discourse analysis,languagegeneration,man-machineinteraction, machine translation, word sense disambiguation, and information extraction. The program committee received 71 abstracts, of which unfortunately no more than 50% could be accepted. Every paper was reviewed by at least two reviewers. The fairness of the reviewing process is demonstrated by the broad spread of institutions and countries represented in the accepted papers. So many have contributed to the success of the conference. The primary credit, ofcourse, goes to theauthors andto the invitedspeakers. By theirpapers and their inspired talks they established the quality of the conference. Secondly, thanks should go to the referees and to the program committee members who did a thorough and conscientious job. It was not easy to select the papers to be presented. Last, but not least, my special thanks to the organizing committee for making this conference happen.
Author: WEI ZHAO Publisher: American Academic Press ISBN: 1631815466 Category : Education Languages : en Pages : 245
Book Description
This study mainly focuses on the revision and extension of two Rules of Standard Centering Theory (Pronoun Rule and Transition Rule) to develop the constraints on the generation algorithm of bridging anaphora (BA) in stream-of-consciousness (SOC) discourse from a revised Centering perspective by incorporating the revised neo-Gricean pragmatic M-principle into the standard Centering. The Centering Theory combined with the revised neo-Gricean pragmatic M-principle is supposed to impose some grammatical and pragmatic constraints on backward-looking center realization and movement. It provides theoretical rationale for an account of constraints on full noun phrase and elliptical zero pronoun bridging anaphora generation in terms of the interaction and the division of labor between syntax and pragmatics. As to both, one cannot alone handle bridging anaphora without the other. Even though syntax and pragmatics operate at distinct levels of linguistic explanation, they appear to interact systematically in the case of bridging anaphora generation. On the one hand, syntax sets certain restrictions on salience and distributions of bridging anaphora and regulates the part of interpretation which is related to grammatical structure. On the other hand, the choice of bridging anaphoric expressions by writers and their interpretation by readers heavily dependents on preference which is regulated by the M-principle of language use and communication. Hence, the bridging anaphora generation algorithm based on the incorporation of the revised neo-Gricean pragmatic M-principle of communication into Centering provides a neat and reasonable explanation for bridging full noun phrase and elliptical zero pronoun generation.
Author: Fahime Same
Author: Fahime Same
Author: Kees Van Deemter
Author: Robert Dale
Author: Anja Belz
Author: Kees van Deemter
Author: Robert Dale
Author: Nicolas Nicolov
Author: Arthur C. Graesser
Author: Dimitris N. Christodoulakis
Author: WEI ZHAO