Generating Contrastive Referring Expressions
نویسندگان
چکیده
The referring expressions (REs) produced by a natural language generation (NLG) system can be misunderstood by the hearer, even when they are semantically correct. In an interactive setting, the NLG system can try to recognize such misunderstandings and correct them. We present an algorithm for generating corrective REs that use contrastive focus (“no, the BLUE button”) to emphasize the information the hearer most likely misunderstood. We show empirically that these contrastive REs are preferred over REs without contrast marking.
منابع مشابه
The Prevalence of Descriptive Referring Expressions in News and Narrative
Generating referring expressions is a key step in Natural Language Generation. Researchers have focused almost exclusively on generating distinctive referring expressions, that is, referring expressions that uniquely identify their intended referent. While undoubtedly one of their most important functions, referring expressions can be more than distinctive. In particular, descriptive referring ...
متن کاملGenerating referring expressions containing quantifiers
Recent work on the Generation of Referring Expressions has increased the generating capability of algorithms in this area. This paper asks whether the models underlying these proposals can still be used if even more complex referring expressions are generated. To discuss this issue, we will investigate a variety of referring expressions that pose difficulties to current generation algorithms. I...
متن کاملOSU-2: Generating Referring Expressions with a Maximum Entropy Classifier
Selection of natural-sounding referring expressions is useful in text generation and information summarization (Kan et al., 2001). We use discourse-level feature predicates in a maximum entropy classifier (Berger et al., 1996) with binary and n-class classification to select referring expressions from a list. We find that while mention-type n-class classification produces higher accuracy of typ...
متن کاملGenerating One-Anaphoric Expressions: Where Does the Decision Lie?
Most natural language generation systems embody mechanisms for choosing whether to subsequently refer to an already-introduced entity by means of a pronoun or a definite noun phrase. Relatively few systems, however, consider referring to entites by means of one-anaphoric expressions such as the small green one. This paper looks at what is involved in generating referring expressions of this typ...
متن کاملGenerating Expressions that Refer to Visible Objects
We introduce a novel algorithm for generating referring expressions, informed by human and computer vision and designed to refer to visible objects. Our method separates absolute properties like color from relative properties like size to stochastically generate a diverse set of outputs. Expressions generated using this method are often overspecified and may be underspecified, akin to expressio...
متن کامل