Referring Expression Generation through Attribute-Based Heuristics
نویسندگان
چکیده
In this paper, we explore a corpus of human-produced referring expressions to see to what extent we can learn the referential behaviour the corpus represents. Despite a wide variation in the way subjects refer across a set of ten stimuli, we demonstrate that component elements of the referring expression generation process appear to generalise across participants to a significant degree. This leads us to propose an alternative way of thinking of referring expression generation, where each attribute in a description is provided by a separate heuristic.
منابع مشابه
Referring 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 کاملCross-linguistic Attribute Selection for REG: Comparing Dutch and English
In this paper we describe a cross-linguistic experiment in attribute selection for referring expression generation. We used a graph-based attribute selection algorithm that was trained and cross-evaluated on English and Dutch data. The results indicate that attribute selection can be done in a largely language independent way.
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 کاملSerial Dependency: Is It a Characteristic of Human Referring Expression Generation?
A key characteristic of many existing referring expression generation (REG) algorithms is serial dependency: attributes are selected for inclusion one at a time, and the decision to include each attribute is dependent on the discriminatory ability of the set of attributes that have already been selected so far. We use a machine learning approach to explore whether serial dependency is a charact...
متن کاملCorpus-based Referring Expressions Generation
In Natural Language Generation, the task of attribute selection (AS) consists of determining the appropriate attribute-value pairs (or semantic properties) that represent the contents of a referring expression. Existing work on AS includes a wide range of algorithmic solutions to the problem, but the recent availability of corpora annotated with referring expressions data suggests that corpus-b...
متن کامل