Generation of repeated references to discourse entities

Anja Belz, Sebastian Varges

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

Abstract

Generation of Referring Expressions is a thriving subfield of Natural Language Generation which has traditionally focused on the task of selecting a set of attributes that unambiguously identify a given referent. In this paper, we address the complementary problem of generating repeated, potentially different referential expressions that refer to the same entity in the context of a piece of discourse longer than a sentence. We describe a corpus of short encyclopaedic texts we have compiled and annotated for reference to the main subject of the text, and report results for our experiments in which we set human subjects and automatic methods the task of selecting a referential expression from a wide range of choices in a full-text context. We find that our human subjects agree on choice of expression to a considerable degree, with three identical expressions selected in 50% of cases. We tested automatic selection strategies based on most frequent choice heuristics, involving different combinations of information about syntactic MSR type and domain type. We find that more information generally produces better results, achieving a best overall test set accuracy of 53.9% when both syntactic MSR type and domain type are known.
Original languageEnglish
Title of host publicationProceedings of the 11th European Workshop on Natural Language Generation (ENLG'07)
Place of PublicationSaarbrücken, Germany
PublisherDFKI GmbH
Pages9-16
Number of pages8
Publication statusPublished - 1 Jan 2007
EventProceedings of the 11th European Workshop on Natural Language Generation (ENLG'07) - Schloss Dagstuhl, Germany
Duration: 1 Jan 2007 → …

Workshop

WorkshopProceedings of the 11th European Workshop on Natural Language Generation (ENLG'07)
Period1/01/07 → …

Keywords

  • Natural language generation
  • Referring expressions

Fingerprint Dive into the research topics of 'Generation of repeated references to discourse entities'. Together they form a unique fingerprint.

Cite this