Author: Manfred Stede
Publisher: National Library of Canada = Bibliothèque nationale du Canada
ISBN: 9780612118607
Category : Computational linguistics
Languages : en
Pages : 215

View

Book Description

Author: Manfred Stede
Publisher: Springer Science & Business Media
ISBN: 146155179X
Category : Computers
Languages : en
Pages : 230

View

Book Description
In knowledge-based natural language generation, issues of formal knowledge representation meet with the linguistic problems of choosing the most appropriate verbalization in a particular situation of utterance. Lexical Semantics and Knowledge Representation in Multilingual Text Generation presents a new approach to systematically linking the realms of lexical semantics and knowledge represented in a description logic. For language generation from such abstract representations, lexicalization is taken as the central step: when choosing words that cover the various parts of the content representation, the principal decisions on conveying the intended meaning are made. A preference mechanism is used to construct the utterance that is best tailored to parameters representing the context. Lexical Semantics and Knowledge Representation in Multilingual Text Generation develops the means for systematically deriving a set of paraphrases from the same underlying representation with the emphasis on events and verb meaning. Furthermore, the same mapping mechanism is used to achieve multilingual generation: English and German output are produced in parallel, on the basis of an adequate division between language-neutral and language-specific (lexical and grammatical) knowledge. Lexical Semantics and Knowledge Representation in Multilingual Text Generation provides detailed insights into designing the representations and organizing the generation process. Readers with a background in artificial intelligence, cognitive science, knowledge representation, linguistics, or natural language processing will find a model of language production that can be adapted to a variety of purposes.

Author: James Pustejovsky
Publisher:
ISBN: 9783662197332
Category :
Languages : en
Pages : 400

View

Book Description

Author: Philipp Cimiano
Publisher: Springer Nature
ISBN: 3030302253
Category : Computers
Languages : en
Pages : 286

View

Book Description
This is the first monograph on the emerging area of linguistic linked data. Presenting a combination of background information on linguistic linked data and concrete implementation advice, it introduces and discusses the main benefits of applying linked data (LD) principles to the representation and publication of linguistic resources, arguing that LD does not look at a single resource in isolation but seeks to create a large network of resources that can be used together and uniformly, and so making more of the single resource. The book describes how the LD principles can be applied to modelling language resources. The first part provides the foundation for understanding the remainder of the book, introducing the data models, ontology and query languages used as the basis of the Semantic Web and LD and offering a more detailed overview of the Linguistic Linked Data Cloud. The second part of the book focuses on modelling language resources using LD principles, describing how to model lexical resources using Ontolex-lemon, the lexicon model for ontologies, and how to annotate and address elements of text represented in RDF. It also demonstrates how to model annotations, and how to capture the metadata of language resources. Further, it includes a chapter on representing linguistic categories. In the third part of the book, the authors describe how language resources can be transformed into LD and how links can be inferred and added to the data to increase connectivity and linking between different datasets. They also discuss using LD resources for natural language processing. The last part describes concrete applications of the technologies: representing and linking multilingual wordnets, applications in digital humanities and the discovery of language resources. Given its scope, the book is relevant for researchers and graduate students interested in topics at the crossroads of natural language processing / computational linguistics and the Semantic Web / linked data. It appeals to Semantic Web experts who are not proficient in applying the Semantic Web and LD principles to linguistic data, as well as to computational linguists who are used to working with lexical and linguistic resources wanting to learn about a new paradigm for modelling, publishing and exploiting linguistic resources.

Author: Piek Vossen
Publisher: Springer Science & Business Media
ISBN: 9401714916
Category : Computers
Languages : en
Pages : 180

View

Book Description
This book describes the main objective of EuroWordNet, which is the building of a multilingual database with lexical semantic networks or wordnets for several European languages. Each wordnet in the database represents a language-specific structure due to the unique lexicalization of concepts in languages. The concepts are inter-linked via a separate Inter-Lingual-Index, where equivalent concepts across languages should share the same index item. The flexible multilingual design of the database makes it possible to compare the lexicalizations and semantic structures, revealing answers to fundamental linguistic and philosophical questions which could never be answered before. How consistent are lexical semantic networks across languages, what are the language-specific differences of these networks, is there a language-universal ontology, how much information can be shared across languages? First attempts to answer these questions are given in the form of a set of shared or common Base Concepts that has been derived from the separate wordnets and their classification by a language-neutral top-ontology. These Base Concepts play a fundamental role in several wordnets. Nevertheless, the database may also serve many practical needs with respect to (cross-language) information retrieval, machine translation tools, language generation tools and language learning tools, which are discussed in the final chapter. The book offers an excellent introduction to the EuroWordNet project for scholars in the field and raises many issues that set the directions for further research in semantics and knowledge engineering.

Author: Sabine Bergler
Publisher:
ISBN:
Category : Computational linguistics
Languages : en
Pages : 274

View

Book Description

Author: Su Wang
Publisher:
ISBN:
Category :
Languages : en
Pages : 228

View

Book Description
We are interested in the computational modeling of lexico-conceptual and narrative knowledge (e.g. how to represent the meaning of cat to reflect facts such as: it is similar to a dog, and it is typically larger than a mouse; how to characterize story, and how to identify different narratives on the same topic). On the lexico-conceptual front, we learn lexical representations with strong interpretability, as well as integrate commonsense knowledge into lexical representations. For narrative modeling, we study how to identify, extract, and generate narratives/stories acceptable to human intuition. As a methodological framework we apply the methods of Distributional Semantics (DS) — “a subfield of Natural Language Processing that learns meaning from word usages” (Herbelot, 2019) — where semantic representations (on any levels such as word, phrases, sentences, etc.) are learned at scale from data through machine learning models (Erk and Padó, 2008; Baroni and Lenci, 2010; Mikolov et al., 2013; Pennington et al., 2014). To infuse interpretability and commonsense into semantic representations (specifically lexical and event), which are typically lacking in previous works (Doran et al., 2017; Gusmao et al., 2018; Carvalho et al., 2019), we complement the data-driven scalability with a minimal amount of human knowledge annotation on a selected set of tasks and have obtained empirical evidence in support of our techniques. For narrative modeling, we draw insights from the rich body of work on scripts and narratives started from Schank and Abelson (1977) and Mooney and DeJong (1985) to Chambers and Jurafsky (2008, 2009), and proposed distributional models for the tasks narrative identification, extraction, and generation which produced state-of-the-art performance. Symbolic approaches to lexical semantics (Wierzbicka, 1996; Goddard and Wierzbicka, 2002) and narrative modeling (Schank and Abelson, 1977; Mooney and DeJong, 1985) have been fruitful on the front of theoretical studies. For example, in theoretical linguistics, Wierzbicka defined a small set of lexical semantic primitives from which complex meaning can be built compositionally; in Artificial Intelligence, Schank and Abelson formulated primitive acts which are conceptualized into semantic episodes (i.e. scripts) understandable by humans. Our focus, however, is primarily on computational approaches that need wide lexical coverage, for which DS provides a better toolkit, especially in practical applications. In this thesis, we innovate by building on the “vanilla” DS techniques (Landauer and Dumais, 1997; Mikolov et al., 2013) to address the issues listed above. Specifically, we present empirical evidence that • On the building block level, with the framework of DS, it is possible to learn highly interpretable lexical and event representations at scale and introduce human commonsense knowledge at low cost. • On the narrative level, well-designed DS modeling offers a balance of precision and scalability, solutions which are empirically stronger to complex narrative modeling questions (e.g. narrative identification, extraction and generation). Further, conducting case-studies on lexical and narrative modeling, we showcase the viability of integrating DS with traditional methods in complementation to retain the strengths of both approaches Concretely, the contributions of this thesis are summarized as follows: • Evidence from analyzing/modeling a small set of common concepts which indicates that interpretable representations can be learned for lexical concepts with minimal human annotation to realize one/few-shot learning. • Commonsense integration in lexical semantics: with carefully designed crowdsourcing, and combined with distributional methods, it is possible to substantially improve inference related to physical knowledge of the world. • Neural distributional methods perform strongly in complex narrative modeling tasks, where we demonstrate that the following techniques are particularly useful: 1) human intuition inspired iterative algorithms; 2) integration of graphical and distributional modeling; pre-trained large-scale language models

Author: Raymond Kozlowski
Publisher:
ISBN: 9780542458019
Category : Computational linguistics
Languages : en
Pages :

View

Book Description
It is desirable for a sentence generation architecture to utilize diverse lexical and grammatical forms of expression, especially for multilingual generation and paraphrasing. This work presents a generation architecture capable of generating such variety in a uniform manner. Central to our approach are lexico-grammatical resources which pair elementary semantic structures with their syntactic realization and all lexico-grammatical consequences. Since the resources, contained in the lexicon for the given language, encapsulate all information necessary to produce the realizations of a semantic input, the generation methodology itself is simple and free from exceptional processing. Consistent with the traditional approach to sentence generation, our methodology consists of three parts: the decomposition of the semantic input into non-overlapping pieces to be realized by separate lexico-grammatical resources, the independent realization of the semantic pieces, and putting the realizations together to form a grammatical sentence in the language. The independence of the realization of semantic pieces is an important aspect of the simplicity of the methodology. There exist linguistic phenomena that raise issues with respect to this independence. They include constraints a lexical item might impose on the type of arguments (traditionally called selectional restrictions) and constraints a lexical item might impose on other lexical items with which it co-occurs (resulting in so-called collocations). We investigate the role of these phenomena in generation in a way that has not been done before. We also conclude that they do not pose complications to the independent realization of semantic pieces or to our generation architecture in general.

Author: Michael Richard Brent
Publisher:
ISBN:
Category :
Languages : en
Pages : 368

View

Book Description

Author: Martin Hoelter
Publisher:
ISBN:
Category : Computational linguistics
Languages : en
Pages : 228

View

Book Description