Why discourse affects speakers’ choice of referring expressions

By Naho Orita, Eliana Vornov, Naomi H Feldman, Hal Daumé Iii. 2015

30 citations recorded by the source corpus.

We propose a language production model that uses dynamic discourse information to account for speakers’ choices of referring expressions. Our model extends previous rational speech act models (Frank and Goodman, 2012) to more naturally distributed linguistic data, instead of assuming a controlled experimental setting. Simulations show a close match between speakers’ utterances and model predictions, indicating that speakers’ behavior can be modeled in a principled way by considering the probabilities of referents in the discourse and the information conveyed by each word.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Experimental and Cognitive Psychology

In Natural Language Processing

Citations in the corpus

Toward Gender-Inclusive Coreference Resolution (2019, background): “This speaker may use aer’s assumption of the listener to determine that “her” is sufficiently unambiguous in this case as to be an acceptable reference (trading off brevity and specificity; see, for instance [Arnold 2008; Frank and Goodman 2012; Orita et al. 2015]).”
Continual Adaptation for Efficient Machine Communication (2019, background): “Speakers can remain understandable while expending significantly fewer words (Krauss and Weinheimer, 1964; Orita et al., 2015; Staliūnaitė et al., 2018; Hawkins et al., 2020a; Stewart et al., 2020).”
Pragmatically Informative Text Generation (2019, background): “, 2009), and targeted analysis of linguistic phenomena (Orita et al., 2015), rational speech acts models have seen limited application in the natural language processing literature.”
Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle* (2021, methodology): “This speaker may use this assumption of the listener to determine that “her” is su ﬃ ciently unambiguous in this case as to be an acceptable reference (trading o ﬀ brevity and speciﬁcity; see, for instance (Arnold 2008; Frank and Goodman 2012; Orita et al. 2015a)).”
Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information (2018, background): “Such pragmatic principles have recently been shown to be useful in other tasks as well (Golland et al., 2010; Smith et al., 2013; Orita et al., 2015; Andreas and Klein, 2016).”