Generation of effective referring expressions in situated context

  title={Generation of effective referring expressions in situated context},
  author={Konstantina Garoufi and Alexander Koller},
  journal={Language, Cognition and Neuroscience},
  pages={1001 - 986}
In task-oriented communication, references often need to be effective in their distinctive function, that is, help the hearer identify the referent correctly and as effortlessly as possible. However, it can be challenging for computational or empirical studies to capture referential effectiveness. Empirical findings indicate that human-produced references are not always optimally effective, and that their effectiveness may depend on different aspects of the situational context that can evolve… 
Models and empirical data for the production of referring expressions
This paper introduces a special issue of Language, Cognition and Neuroscience dedicated to Production of Referring Expressions: Models and Empirical Data, focusing on models of reference production
Computational Models of Referring
This chapter discusses computational models of the act of referring, focusing on limitations of the classic algorithms in this area, as illustrated by a number of common referential scenarios. After
Production of Referring Expressions for an Unknown Audience: A Computational Model of Communal Common Ground
A computational model composed of three complimentary heuristics based on an estimation of the recipient's knowledge, an estimate of the extent to which a property is unexpected, and the question of what is the optimum number of properties in a given situation is presented.
Rational Redundancy in Referring Expressions: Evidence from Event-related Potentials
Two event-related potential (ERP) experiments are presented, investigating the real-time comprehension of referring expressions that contain redundant adjectives in complex visual contexts and proposing a bounded-rational account of overspecification, according to which even redundant words can be beneficial to comprehension.
Reference Production as Search: The Impact of Domain Size on the Production of Distinguishing Descriptions.
It is shown that the time taken to plan a referring expression-as reflected by speech onset latencies-is influenced by distractor set size and by the number of properties required, but this crucially depends on the discriminability of the properties under consideration.
Production of referring expressions in Arabic
A comparative analysis of Arabic andEnglish descriptions reveals that overall both Arabic and English speakers produce similar linguistic descriptions under the identical conditions, implying that reference generation phenomena are not language specific.
Easy Things First: Installments Improve Referring Expression Generation for Objects in Photographs
It is shown that reference to be established in “installments” can also be advantageous in technical systems that only have uncertain access to object attributes and categories, and a solution inspired from human task-oriented interaction is proposed and implemented for avoiding and repairing semantically inaccurate words.
Zoom: a corpus of natural language descriptions of map locations
The resulting data set the Zoom corpus of natural language descriptions of map locations takes into account a domain that is significantly closer to real-world applications than what has been considered in previous work, and addresses more complex situations of reference.
Statistical NLG for Generating the Content and Form of Referring Expressions
It is argued that a new generic approach to statistical NLG can be made to perform Referring Expression Generation successfully, and the attribute selection aspect of the algorithm exceeds classic REG algorithms.
Talking about what is not there: Generating indefinite referring expressions in Minecraft
This work formalizes this problem and presents an algorithm for generating (indefinite) referring expressions to objects that do not exist yet, in the context of generating building instructions within the Minecraft video game.


Generation of Referring Expressions: Assessing the Incremental Algorithm
It turns out that the success of the IA depends substantially on the ''preference order'' (PO) employed by the IA, particularly in complex domains, and there are no compelling reasons for preferring the IA over some of its main competitors on these grounds.
The generation of natural descriptions: corpus-based investigations of referring expressions in visual domains
The main conclusion of the analyses and experiments in this thesis is that speaker-specific variation plays a much larger role in the generation of referring expressions than existing algorithms acknowledge.
Incremental speech production and referential overspecification
Speech is often produced incrementally: speakers start to articulate an utterance before knowing exactly what they are going to say. The time devoted to articulating first parts of an utterance is
Reference Management in Instructive Discourse
The effect of 2 language-in-use factors, implemented as conditions in an instructive production task, were the assumed visual identity for the reader of the objects or referents to be referred to in the instructions and the assumed goal of the reader (reading to do vs. reading to learn).
Computational Interpretations of the Gricean Maxims in the Generation of Referring Expressions
A recommended algorithm is described, along with a specification of the resources a host system must provide in order to make use of the algorithm, and an implementation used in the natural language generation component of the IDAS system.
Collaborating on Referring Expressions
A computational model of how conversational participants collaborate in order to make a referring action successful is presented, based on the view of language as goal-directed behavior and it is proposed that the content of a referring expression can be accounted for by the planning paradigm.
The use of visual context during the production of referring expressions
It is shown that even when the competitor had a different gender from the referent, its visual presence reduced pronoun use, indicating that visual context plays a role even if the use of a pronoun is unambiguous.
Partner-specific interpretation of maintained referential precedents during interactive dialog.
Do Speakers Avoid Ambiguities During Dialogue?
It is concluded that speakers pay attention to their beliefs about their addressees' ease of comprehension, in addition to considering ease of production for themselves, when making syntactic choices in dialogue.