Referring expression generation in context

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 whi...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Same, Fahime
Formato: Online
Lenguaje:inglés
Publicado: Language Science Press 2024
Materias:
Acceso en línea:https://library.oapen.org/handle/20.500.12657/93390
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1869513792826638336
author Same, Fahime
author_browse Same, Fahime
author_facet Same, Fahime
author_sort Same, Fahime
collection Directory of Open Access Books
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.
format Online
id doab-20.500.12854ir-145682
institution Directory of Open Access Books
language eng
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Language Science Press
publisherStr Language Science Press
record_format ojs
spelling doab-20.500.12854ir-1456822026-06-05T05:09:53Z Referring expression generation in context Same, Fahime Language Arts & Disciplines Linguistics bic Book Industry Communication::C Language::CF linguistics 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. 2024-09-20T04:02:19Z 2024-09-20T04:02:19Z 2024-09-19T05:36:27Z 2024 book https://library.oapen.org/handle/20.500.12657/93390 https://directory.doabooks.org/handle/20.500.12854/145682 eng open access image/jpeg image/jpeg image/jpeg n/a n/a n/a https://library.oapen.org/bitstream/20.500.12657/93390/1/external_content.pdf https://library.oapen.org/bitstream/20.500.12657/93390/1/external_content.pdf https://library.oapen.org/bitstream/20.500.12657/93390/1/external_content.pdf Language Science Press Language Science Press https://doi.org/10.5281/zenodo.11058114 https://doi.org/10.5281/zenodo.11058114 ed03121b-b998-4b50-8d58-1d0745565558 Knowledge Unlatched Knowledge Unlatched (KU) Language Science Press 2024-2026 Language Science Press open access
spellingShingle Language Arts & Disciplines
Linguistics
bic Book Industry Communication::C Language::CF linguistics
Same, Fahime
Referring expression generation in context
title Referring expression generation in context
title_full Referring expression generation in context
title_fullStr Referring expression generation in context
title_full_unstemmed Referring expression generation in context
title_short Referring expression generation in context
title_sort referring expression generation in context
topic Language Arts & Disciplines
Linguistics
bic Book Industry Communication::C Language::CF linguistics
topic_facet Language Arts & Disciplines
Linguistics
bic Book Industry Communication::C Language::CF linguistics
url https://library.oapen.org/handle/20.500.12657/93390
work_keys_str_mv AT samefahime referringexpressiongenerationincontext