The Clarity-Brevity Trade-Off In Generating Referring Expressions (original) (raw)

Proceedings of the 22nd International Conference on Computational Linguistics - COLING '08, 2008

Existing algorithms for the Generation of Referring Expressions tend to generate distinguishing descriptions at the semantic level, disregarding the ways in which surface issues can affect their quality. This paper considers how these algorithms should deal with surface ambiguity, focussing on structural ambiguity. We propose that not all ambiguity is worth avoiding, and suggest some ways forward that attempt to avoid unwanted interpretations. We sketch the design of an algorithm motivated by our experimental findings.

Controlling redundancy in referring expressions

2008

graph-based framework provides an elegant and flexible approach to the generation of referring expressions. In this paper, we present the first reported study that systematically investigates how to tune the parameters of the graph-based framework on the basis of a corpus of human-generated descriptions. We focus in particular on replicating the redundant nature of human referring expressions, whereby properties not strictly necessary for identifying a referent are nonetheless included in descriptions. We show how statistics derived from the corpus data can be integrated to boost the framework's performance over a non-stochastic baseline.

Managing Lexical Ambiguity in the Generation of Referring Expressions

International Journal of Intelligent Systems and Applications, 2013

Most existing algorithms for the Generation of Referring Expressions (GRE) tend to produce distinguishing descriptions at the semantic level, disregarding the ways in which surface issues (e.g. linguistic ambiguity) can affect their quality. In this article, we highlight limitations in an existing GRE algorithm that takes lexical ambiguity into account, and put forward some ideas to address those limitations. The proposed ideas are implemented in a GRE algorithm. We show that the revised algorithm successfully generates optimal referring expressions without greatly increasing the computational complexity of the (original) algorithm.

A Fast Algorithm for the Generation of Referring Expressions

1992

We simplify previous work in the development of algorithms for the generation of referring expre~ sions while at the same time taking account of psycholinguistic findings and transcript data. The result is a straightforward algorithm that is computationally tractable, sensitive to the preferences of human users, and reasonably domain-independent. We provide a specification of the resources a host system must provide in order to make use of the algorithm, and describe an implementation used in the IDAS system.

Probabilistic Refinement Algorithms for the Generation of Referring Expressions

We propose an algorithm for the generation of referring expressions (REs) that adapts the approach of Areces et al. (2008, 2011) to include overspecification and probabilities learned from corpora. After introducing the algorithm, we discuss how probabilities required as input can be computed for any given domain for which a suitable corpus of REs is available, and how the probabilities can be adjusted for new scenes in the domain using a machine learning approach. We exemplify how to compute probabilities over the GRE3D7 corpus of Viethen (2011). The resulting algorithm is able to generate different referring expressions for the same target with a frequency similar to that observed in corpora. We empirically evaluate the new algorithm over the GRE3D7 corpus, and show that the probability distribution of the generated referring expressions matches the one found in the corpus with high accuracy.

Generation of Referring Expressions: Managing Structural Ambiguities

2008

Referring Expression Generation: Taking Speakers’ Preferences into Account

Lecture Notes in Computer Science, 2014

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.

Towards the evaluation of referring expression generation

2006

The Natural Language Generation com- munity is currently engaged in discussion as to whether and how to introduce one or several shared evaluation tasks, as are found in other fields of Natural Language Processing. As one of the most well- defined subtasks in NLG, the generation of referring expressions looks like a strong candidate for piloting such shared tasks. Based on our earlier evaluation of a num- ber of existing algorithms for the genera- tion of referring expressions, we explore in this paper some problems that arise in designing an evaluation task in this field, and try to identify general considerations that need to be met in evaluating genera- tion subtasks.

Algorithms for Generating Referring Expressions: Do They Do What People Do?

The natural language generation literature provides many algorithms for the generation of referring expressions. In this paper, we explore the question of whether these algorithms actually produce the kinds of expressions that people produce. We compare the output of three existing algorithms against a data set consisting of human-generated referring expressions, and identify a number of significant differences between what people do and what these algorithms do. On the basis of these observations, we suggest some ways forward that attempt to address these differences.

The Clarity-Brevity Trade-Off In Generating Referring Expressions (original) (raw)

Related papers