Planning english referring expressions

Appelt, Douglas E.

doi:10.1016/0004-3702(85)90011-6

Cited by 104 publications

(67 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results also have important implications for computational models designed to generate referring expressions produced by human speakers (Van Deemter, Gatt, Van Gompel, & Krahmer, 2012). As discussed earlier, computational theories of reference (e.g., Appelt, 1985a;Dale & Reiter, 1995) are often designed to model referring expressions that are optimally helpful to addressees, but they tend to pay little attention to the fact that speakers do not always choose referring expressions that are adapted for the addressee's comprehension, as shown in our current study.…”

Section: Discussionmentioning

confidence: 69%

Producing Pronouns and Definite Noun Phrases: Do Speakers Use the Addressee’s Discourse Model?

Fukumura

Gompel

2012

Cognitive Science

View full text Add to dashboard Cite

We report two experiments that investigated the widely held assumption that speakers use the addressee's discourse model when choosing referring expressions (e.g., Ariel, 1990;Chafe, 1994;Givón, 1983;Prince, 1985), by manipulating whether the addressee could hear the immediately preceding linguistic context. Experiment 1 showed that speakers increased pronoun use (and decreased noun phrase use) when the referent was mentioned in the immediately preceding sentence compared to when it was not, even though the addressee did not hear the preceding sentence, indicating that speakers used their own, privileged discourse model when choosing referring expressions. The same pattern of results was found in Experiment 2. Speakers produced more pronouns when the immediately preceding sentence mentioned the referent than when it mentioned a referential competitor, regardless of whether the sentence was shared with their addressee. Thus, we conclude that choice of referring expression is determined by the referent's accessibility in the speaker's own discourse model rather than the addressee's.

show abstract

Section: Discussionmentioning

confidence: 69%

Producing Pronouns and Definite Noun Phrases: Do Speakers Use the Addressee’s Discourse Model?

Fukumura

Gompel

2012

Cognitive Science

View full text Add to dashboard Cite

show abstract

“…Referring expressions have been analysed in terms of the plan-based approach to dialogue (Appelt, 1983) and have been used to argue for the reality of mutual beliefs amongst human conversants (Clark and Marshall, 1981). In both arguments the possibility is brought up that individual PDNBs play a role in their generation and interpretation.…”

Section: Beliefs and Referring Expressionsmentioning

confidence: 99%

Requirements for belief models in cooperative dialogue

Taylor¹,

Carletta²,

Mellish³

1996

User Model User-Adap Inter

View full text Add to dashboard Cite

Models of rationality typically rely on underlying logics that allow simulated agents to entertain beliefs about one another to any depth of nesting. Such models seem to be overly complex when used for belief modelling in environments in which cooperation between agents can be assumed, Le., most HCI contexts. We examine some existing dialogue systems and find that deeply-nested beliefs are seldom supported, and that where present they appear to be unnecessary except in some situations involving deception.Use of nested beliefs is associated with nested reasoning (i.e., reasoning about other agents' reasoning). We argue that for cooperative dialogues, representations of individual nested beliefs of the third level (i.e., what A thinks B thinks A thinks B thinks) and beyond are in principle unnecessary unless directly available from the environment, because the corresponding nested reasoning is redundant.Since cooperation sometimes requires that agents reason about what is mutually believed, we propose a representation in which the second and all subsequent nesting levels are merged into a single category. In situations affording individual deeply-nested beliefs, such a representation restricts agents to human-like referring and repair strategies, where an unrestricted agent might make an unrealistic and perplexing utterance.

show abstract

“…In the early days of AI planning, some researchers saw that marrying speech act theory and AI planning together could have great potential for NL generation, and they began to represent speech acts using the STRIPS (Fikes and Nilsson, 1971) operator (Bruce, 1975;Cohen and Perrault, 1979;Allen and Perrault, 1980;Appelt, 1985). Different angles on the 'speech acts with STRIPS' approach have been tried, but the approach is fraught with well-documented difficulties (Cohen and Levesque, 1990;Grosz and Sidner, 1990;Pollack, 1990;Bunt, 2000;Ramsay, 2000), all of which relate to the inability of participants in a conversation to observe each other's beliefs and intentions.…”

Section: Motivation: Problems With Speech Actsmentioning

confidence: 99%

Sarcasm, Deception, and Stating the Obvious: Planning Dialogue without Speech Acts

Field

Ramsay

2004

Artif Intell Rev

View full text Add to dashboard Cite

This paper presents an alternative to the 'speech acts with STRIPS' approach to implementing dialogue: a fully implemented AI planner which generates and analyses the semantics of utterances using a single linguistic act for all contexts. Using this act, the planner can model problematic conversational situations, including felicitous and infelicitous instances of bluffing, lying, sarcasm, and stating the obvious. The act has negligible effects, and its precondition can always be proved. 'Speaker maxims' enable the speaker to plan to deceive, as well as to generate implicatures, while 'hearer maxims' enable the hearer to recognise deceptions, and interpret implicatures. The planner proceeds by achieving parts of the constructive proof of a goal. It incorporates an epistemic theorem prover, which embodies a deduction model of belief, and a constructive logic.

show abstract

Planning english referring expressions

Cited by 104 publications

References 5 publications

Producing Pronouns and Definite Noun Phrases: Do Speakers Use the Addressee’s Discourse Model?

Producing Pronouns and Definite Noun Phrases: Do Speakers Use the Addressee’s Discourse Model?

Requirements for belief models in cooperative dialogue

Sarcasm, Deception, and Stating the Obvious: Planning Dialogue without Speech Acts

Contact Info

Product

Resources

About