Referring Expression Generation: Taking Speakers' Preferences into Account
نویسندگان
چکیده
We describe a classification-based approach to referring expression generation (REG) making use of standard context-related features, and an extension that adds speaker-related features. Results show that taking speakers’ preferences into account outperforms the standard REG model in four test corpora of definite descriptions.
منابع مشابه
Preferences versus Adaptation during Referring Expression Generation
Current Referring Expression Generation algorithms rely on domain dependent preferences for both content selection and linguistic realization. We present two experiments showing that human speakers may opt for dispreferred properties and dispreferred modifier orderings when these were salient in a preceding interaction (without speakers being consciously aware of this). We discuss the impact of...
متن کاملThe special status of color in pragmatic reasoning: evidence from a language game
In current approaches to pragmatic reasoning the comprehension and production of referring expressions is modeled as a result of the interlocutors’ mutual perspective-taking. While such models of pragmatic reasoning have been empirically validated in referential language games experiments, empirical (and computational) work on the generation of referring expressions has shown that speakers do n...
متن کاملTrainable Speaker-Based Referring Expression Generation
Previous work in referring expression generation has explored general purpose techniques for attribute selection and surface realization. However, most of this work did not take into account: a) stylistic differences between speakers; or b) trainable surface realization approaches that combine semantic and word order information. In this paper we describe and evaluate several end-to-end referri...
متن کاملReferring Expression Generation Using Speaker-based Attribute Selection and Trainable Realization (ATTR)
In the first REG competition, researchers proposed several general-purpose algorithms for attribute selection for referring expression generation. However, most of this work did not take into account: a) stylistic differences between speakers; or b) trainable surface realization approaches that combine semantic and word order information. In this paper we describe and evaluate several end-to-en...
متن کاملTrainable Referring Expression Generation using Overspecification Preferences
Referring expression generation (REG)models that use speaker-dependent information require a considerable amount of training data produced by every individual speaker, or may otherwise perform poorly. In this work we present a simple REG experiment that allows the use of larger training data sets by grouping speakers according to their overspecification preferences. Intrinsic evaluation shows t...
متن کامل