Instance-based natural language generation

Varges, Sebastian; Mellish, Chris

doi:10.3115/1073336.1073337

Cited by 33 publications

(31 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A dominant methodology uses corpus-based metrics, either for ranking possible outputs in an over-generation architecture (Langkilde, 2000;Varges and Mellish, 2001), or to compare outputs to a corpus 'gold standard' (Papineni et al, 2002). The present paper is similar in spirit, insofar as our algorithm uses corpus-derived similarity estimates (following Lin, 1998b, andKilgarriff, 2003).…”

Section: Discussionmentioning

confidence: 99%

Lexical Choice and Conceptual Perspective in the Generation of Plural Referring Expressions

Gatt¹,

Deemter²

2007

J of Log Lang and Inf

View full text Add to dashboard Cite

Abstract. A fundamental part of the process of referring to an entity is to categorise it (for instance, as the woman). Where multiple categorisations exist, this implicitly involves the adoption of a conceptual perspective. A challenge for the automatic Generation of Referring Expressions is to identify a set of referents coherently, adopting the same conceptual perspective. We describe and evaluate an algorithm to achieve this. The design of the algorithm is motivated by the results of psycholinguistic experiments.

show abstract

Section: Discussionmentioning

confidence: 99%

Lexical Choice and Conceptual Perspective in the Generation of Plural Referring Expressions

Gatt¹,

Deemter²

2007

J of Log Lang and Inf

View full text Add to dashboard Cite

show abstract

“…In surface realization, the focus has been on filtering a potential set of syntactic forms for a complete utterance using corpus probabilities to filter the possibilities Knight & Hatzivassiloglou, 1995;Langkilde, 1998;Langkilde & Knight, 1998;Varges, 2001), although there has also been research on selection of the form of a nominal expression using a classifier trained on a corpus of nominal expressions (Cheng, Poesio, Henschel, & Mellish, 2001;Poesio, 2000). Classifiers have also been trained on corpora labelled for TOBI accents to predict the appropriate prosody to output; these prosodic predictors have used various types of input features such as rhetorical structure, semantic features and syntactic features (Hitzeman, Black, Taylor, Mellish, & Oberlander, 1998;Pan & McKeown, 1998).…”

Section: Related Workmentioning

confidence: 99%

Training a sentence planner for spoken dialogue using boosting

Walker

Rambow

Rogati

2002

Computer Speech & Language

View full text Add to dashboard Cite

In the past few years, as the number of dialogue systems has increased, there has been an increasing interest in the use of natural language generation in spoken dialogue. Our research assumes that trainable natural language generation is needed to support more flexible and customized dialogues with human users. This paper focuses on methods for automatically training the sentence planning module of a spoken language generator. Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e., the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences. The paper first presents SPOT, a trainable sentence planner, and a new methodology for automatically training SPOT on the basis of feedback provided by human judges. Our methodology is unique in neither depending on hand-crafted rules nor on the existence of a domain-specific corpus. SPOT first randomly generates a candidate set of sentence plans and then selects one. We show that SPOT learns to select a sentence plan whose rating on average is only 5% worse than the top human-ranked sentence plan. We then experimentally evaluate SPOT by asking human judges to compare SPOT's output with a hand-crafted template-based generation component, two rule-based sentence planners, and two baseline sentence planners. We show that SPoT performs better than the rule-based systems and the baselines, and as well as the hand-crafted system.

show abstract

“…The second and third methods involve integrating n-gram scoring of possible realizations into the chart realization algorithm, as proposed by Varges and Mellish (2001), rather than ranking all complete realizations by their n-gram score as a post-process, as in e.g. (Langkilde and Knight, 1998;Langkilde-Geary, 2002).…”

Section: Introductionmentioning

confidence: 99%

Efficient Realization of Coordinate Structures in Combinatory Categorial Grammar

White

2006

Res Lang Comput

View full text Add to dashboard Cite

Abstract. We describe a chart realization algorithm for Combinatory Categorial Grammar (CCG), and show how it can be used to efficiently realize a wide range of coordination phenomena, including argument cluster coordination and gapping. The algorithm incorporates three novel methods for improving the efficiency of chart realization: (i) using rules to chunk the input logical form into sub-problems to be solved independently prior to further combination; (ii) pruning edges from the chart based on the n-gram score of the edge's string, in comparison to other edges with equivalent categories; and (iii) formulating the search as a best-first anytime algorithm, using n-gram scores to sort the edges on the agenda. The algorithm has been implemented as an extension to the OpenCCG open source CCG parser, and initial performance tests indicate that the realizer is fast enough for practical use in natural language dialogue systems.

show abstract

Instance-based natural language generation

Cited by 33 publications

References 74 publications

Lexical Choice and Conceptual Perspective in the Generation of Plural Referring Expressions

Lexical Choice and Conceptual Perspective in the Generation of Plural Referring Expressions

Training a sentence planner for spoken dialogue using boosting

Efficient Realization of Coordinate Structures in Combinatory Categorial Grammar

Contact Info

Product

Resources

About