A Probabilistic Computational Model of Cross-Situational Word Learning

By Afsaneh Fazly, Afra Alishahi, Suzanne Stevenson. 2010

192 citations recorded by the source corpus.

Subfields: Developmental and Educational 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 Developmental and Educational Psychology

In Natural Language Processing

Citations in the corpus

Grammar-Based Grounded Lexicon Learning (2022, background): “However, most previous computational models have focused only on explaining small-scale lab experiments and do not address grounding in visual perception [13, 15].”
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision (2019, background): “Humans are capable of learning visual concepts by jointly understanding vision and language (Fazly et al., 2010; Chrupała et al., 2015; Gauthier et al., 2018).”
A Competence-aware Curriculum for Visual Concepts Learning via Question Answering (2020, background): “Humans excel at learning visual concepts and their compositions in a questionanswering manner [16,10,18], which requires a joint understanding of vision and language.”
Fast Online Lexicon Learning for Grounded Language Acquisition (2012, methodology): “More recently, Fazly et al. (2010) proposed a probabilistic incremental model that can learn online similar to our algorithm and was tested on transcriptions of child-directed speech.”
Bootstrapping language acquisition. (2017, background): “Rather than choosing distractor logical forms at random, we follow Fazly et al. (2010) in choosing distractors from nearby utterances in the corpus, so they are likely to share some semantic content with correct logical forms (as they were uttered in a similar situation).”
Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations (2019, background): “Cross-situational learning, or learning from contrastive examples [12], uses contrastive examples in the dataset to resolve the referential ambiguity of objects: Looking at both Pair A and B in Fig.”
Word learning and the acquisition of syntactic-semantic overhypotheses (2018, unknown): “erence, for example, often leverage associationist or connectionist frameworks (Fazly et al., 2010; Chrupała et al., 2015; Yu and Ballard, 2004), while studies of abstract rule learning about syntax and object category structure often rely on hierarchical Bayesian inference (Kemp et al.”
Representations of language in a model of visually grounded speech signal (2017, background): “Often language input is given in the form of word symbols, and the context consists of a set of symbols representing possible referents (e.g. Siskind, 1996; Frank et al., 2007; Fazly et al., 2010).”
Is this a wampimuk? Cross-modal mapping between distributional semantics and the visual world (2014, background): “Computational models of meaning that rely on corpus-extracted context vectors, such as LSA (Landauer and Dumais, 1997), HAL (Lund and Burgess, 1996), Topic Models (Griffiths et al., 2007) and more recent neural-network approaches (Collobert and Weston, 2008; Mikolov et al., 2013b) have successfully ”