The Clarity-Brevity Trade-off in Generating Referring Expressions
نویسندگان
چکیده
Existing algorithms for the Generation of Referring Expressions (GRE) aim at generating descriptions that allow a hearer to identify its intended referent uniquely; the length of the expression is also considered, usually as a secondary issue. We explore the possibility of making the trade-off between these two factors more explicit, via a general cost function which scores these two aspects separately. We sketch some more complex phenomena which might be amenable to this treatment.
منابع مشابه
Investigating the content and form of referring expressions in Mandarin: introducing the Mtuna corpus
East Asian languages are thought to handle reference differently from English, particularly in terms of the marking of definiteness and number. We present the first Data-Text corpus for Referring Expressions in Mandarin, and we use this corpus to test some initial hypotheses inspired by the theoretical linguistics literature. Our findings suggest that function words deserve more attention in Re...
متن کاملStochastic Congestion Alleviation with a Trade-off between Demand Response Resources and Load Shedding
Under the smart grid environments, Demand Response Resources (DRRs) as power system resources can effectively participate in and improve performance of electric systems. Congestion management is one of the technical challenges in which DRRs can play a significant role. Previously, congestion management is applied without considering the power system uncertainties. Therefore, a stochastic conges...
متن کاملIS-FBN, IS-FBS, IS-IAC: The Adaptation of Two Classic Algorithms for the Generation of Referring Expressions in order to Produce Expressions like Humans Do
The first algorithm is the full brevity algorithm combined with nearest neighbour learning technique which is used for the selection of the referring expression closest to training examples as uttered by humans. This algorithm obviously only imitates human behaviour with the goal to get high scores. With the Incremental Algorithm that is known and justified by its human like behaviour, we tried...
متن کاملManaging Ambiguity in Reference Generation: The Role of Surface Structure
This article explores the role of surface ambiguities in referring expressions, and how the risk of such ambiguities should be taken into account by an algorithm that generates referring expressions, if these expressions are to be optimally effective for a hearer. We focus on the ambiguities that arise when adjectives occur in coordinated structures. The central idea is to use statistical infor...
متن کاملThe 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 کامل