• Publications
  • Influence
Evaluating Vector-Space Models of Word Representation, or, The Unreasonable Effectiveness of Counting Words Near Other Words
TLDR
Vector-space models of semantics represent words as continuously-valued vectors and measure similarity based on the distance or angle between those vectors. Expand
  • 35
  • 4
  • PDF
A Computational Study of Late Talking in Word-Meaning Acquisition
TLDR
A Computational Study of Late Talking in Word-Meaning Acquisition Aida Nematzadeh , Afsaneh Fazly , and Suzanne Stevenson Department of Computer Science University of Toronto {aida,afsANEh,suzanne}@cs.toronto.edu Abstract and ambiguous context. Expand
  • 10
  • 1
  • PDF
Visual Grounding in Video for Unsupervised Word Translation
TLDR
We use visual grounding to improve unsupervised word mapping between languages by learning embeddings from unpaired instructional videos narrated in the native language. Expand
  • 6
  • 1
  • PDF
Calculating Probabilities Simplifies Word Learning
TLDR
We take a computational approach to investigate how the information present during each observation in a cross-situational framework can affect the overall acquisition of word meanings in various long-term word learning scenarios. Expand
  • 3
  • 1
  • PDF
Evaluating Theory of Mind in Question Answering
TLDR
We propose a new dataset for evaluating question answering models with respect to their capacity to reason about beliefs. Expand
  • 11
  • PDF
Simple Search Algorithms on Semantic Networks Learned from Language Use
TLDR
We show that it is plausible to learn rich representations from naturalistic data for which a very simple search algorithm (a random walk) can replicate the human patterns. Expand
  • 8
  • PDF
A Cognitive Model of Semantic Network Learning
TLDR
We present an algorithm for simultaneously learning word meanings and gradually growing a semantic network, which adheres to the cognitive plausibility requirements of incrementality and limited computations. Expand
  • 11
  • PDF
Interaction of Word Learning and Semantic Category Formation in Late Talking
TLDR
We use a compu- tational model of word learning to study how individual dif- ferences between LTs and NDs give rise to differences in ab- stract knowledge of categories emerging from learned words, and how this affects their subsequent word learning. Expand
  • 9
  • PDF
A Computational Model of Memory, Attention, and Word Learning
TLDR
We build an incremental probabilistic computational model of word learning that incorporates a forgetting and attentional mechanism. Expand
  • 8
  • PDF
Child Acquisition of Multiword Verbs: A Computational Investigation
TLDR
We show that simple statistics based on the linguistic properties of multiword verbs are informative for identifying them in a corpus of child-directed utterances, and that such statistics can be used within a word learning model to learn associations between meanings and sequences of words. Expand
  • 7