PMID- 29441027
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240313
IS  - 1664-1078 (Print)
IS  - 1664-1078 (Electronic)
IS  - 1664-1078 (Linking)
VI  - 9
DP  - 2018
TI  - Pragmatically Framed Cross-Situational Noun Learning Using Computational 
      Reinforcement Models.
PG  - 5
LID - 10.3389/fpsyg.2018.00005 [doi]
LID - 5
AB  - Cross-situational learning and social pragmatic theories are prominent mechanisms 
      for learning word meanings (i.e., word-object pairs). In this paper, the role of 
      reinforcement is investigated for early word-learning by an artificial agent. 
      When exposed to a group of speakers, the agent comes to understand an initial set 
      of vocabulary items belonging to the language used by the group. Both 
      cross-situational learning and social pragmatic theory are taken into account. As 
      social cues, joint attention and prosodic cues in caregiver's speech are 
      considered. During agent-caregiver interaction, the agent selects a word from the 
      caregiver's utterance and learns the relations between that word and the objects 
      in its visual environment. The "novel words to novel objects" language-specific 
      constraint is assumed for computing rewards. The models are learned by maximizing 
      the expected reward using reinforcement learning algorithms [i.e., table-based 
      algorithms: Q-learning, SARSA, SARSA-lambda, and neural network-based algorithms: 
      Q-learning for neural network (Q-NN), neural-fitted Q-network (NFQ), and deep 
      Q-network (DQN)]. Neural network-based reinforcement learning models are chosen 
      over table-based models for better generalization and quicker convergence. 
      Simulations are carried out using mother-infant interaction CHILDES dataset for 
      learning word-object pairings. Reinforcement is modeled in two cross-situational 
      learning cases: (1) with joint attention (Attentional models), and (2) with joint 
      attention and prosodic cues (Attentional-prosodic models). Attentional-prosodic 
      models manifest superior performance to Attentional ones for the task of 
      word-learning. The Attentional-prosodic DQN outperforms existing word-learning 
      models for the same task.
FAU - Najnin, Shamima
AU  - Najnin S
AD  - Department of Electrical and Computer Engineering, University of Memphis, 
      Memphis, TN, United States.
FAU - Banerjee, Bonny
AU  - Banerjee B
AD  - Department of Electrical and Computer Engineering, University of Memphis, 
      Memphis, TN, United States.
AD  - Institute for Intelligent Systems, University of Memphis, Memphis, TN, United 
      States.
LA  - eng
PT  - Journal Article
DEP - 20180130
PL  - Switzerland
TA  - Front Psychol
JT  - Frontiers in psychology
JID - 101550902
PMC - PMC5797660
OTO - NOTNLM
OT  - Q-learning
OT  - cross-situational learning
OT  - deep reinforcement learning
OT  - joint attention
OT  - neural network
OT  - prosodic cue
EDAT- 2018/02/15 06:00
MHDA- 2018/02/15 06:01
PMCR- 2018/01/30
CRDT- 2018/02/15 06:00
PHST- 2017/07/01 00:00 [received]
PHST- 2018/01/03 00:00 [accepted]
PHST- 2018/02/15 06:00 [entrez]
PHST- 2018/02/15 06:00 [pubmed]
PHST- 2018/02/15 06:01 [medline]
PHST- 2018/01/30 00:00 [pmc-release]
AID - 10.3389/fpsyg.2018.00005 [doi]
PST - epublish
SO  - Front Psychol. 2018 Jan 30;9:5. doi: 10.3389/fpsyg.2018.00005. eCollection 2018.