PSYCHOLOGICAL SCIENCE Research Article Using Speakers ’ Referential Intentions to Model Early Cross-Situational Word Learning

Citations in the corpus

• Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “This is the underlying idea of the Greedy Heuristic algorithm (Dale, 1989, 1992), and it has more recently been revived in stochastic utility-based models such as Frank et al. (2009).”
• Learning From Others (2012, unknown): “Frank, Goodman, and Tenenbaum (2009) used a Bayesian model to capture this intuition in the context of associative word-learning tasks.”
• Leveraging Language to Learn Program Abstractions and Search Heuristics (2021, background): “This prior has been shown to play an important role in language learning in cognitive science (Frank et al., 2009; Markman & Wachtel, 1988), and in machine learning models (Gandhi & Lake, 2019).”
• Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech (2017, background): “However, these studies simplify the problem by using discrete labels to represent the visual context (R¨as¨anen and Rasilo, 2015), the spoken input (Gelderloos and Chrupała, 2016), or both (Siskind, 1996; Frank et al., 2009); infants do not have access to such idealised input.”
• Predicting the birth of a spoken word (2015, background): “Higher use frequency may allow children to make more accurate inferences about noun meaning just by virtue of increased contextual cooccurrence (25, 26).”
• Word learning emerges from the interaction of online referent selection and slow associative learning (2012, methodology): “There are several models of the word–referent mapping problem (Frank et al., 2009; Li et al., 2004; MacWhinney, 1987; Mayor & Plunkett, 2010; Merriman, 1999; Regier, 2005; Siskind, 1996; Xu & Tenenbaum, 2007).”
• Introduction to MAchine Learning & Knowledge Extraction (MAKE) (2017, background): “Moreover, there is empirical evidence that, in some cases, a representation of the speakers’ intentions is helpful [72], and there is agreement that understanding language (not mere language processing) is more than the use of fixed conventions and/or decoding combinatorial structures and that proba”
• Discovering linguistic structures in speech: models and applications (2014, unknown): “Various factors such as cross-situational learning that may contribute to learning word meaning were also investigated in previous work [170, 47].”
• Continual Adaptation for Efficient Machine Communication (2019, background): “term importantly incorporates such reasoning at the time of adaptation (i.e. when updating beliefs about θ based on previous actions; Frank et al., 2009; Smith et al., 2013).”