Learning to Mediate Perceptual Differences in Situated Human-Robot Dialogue

Authors: Changsong Liu, Joyce Chai

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our empirical evaluation has shown that this weight-learning approach can successfully adjust the weights to reflect the robot s perceptual limitations. The learned weights, together with updated word models, can lead to a significant improvement for referential grounding in future dialogues. ... To evaluate our weight-learning approach, we used the data collected from an earlier study that investigated collaborative efforts in human-robot dialogue (Chai et al. 2014).
Researcher Affiliation Academia Changsong Liu and Joyce Y. Chai Department of Computer Science and Engineering Michigan State University East Lansing, Michigan 48824 {cliu, jchai}@cse.msu.edu
Pseudocode No No pseudocode or clearly labeled algorithm blocks were found.
Open Source Code No The paper does not provide any concrete access information (e.g., repository link, explicit statement of code release, or mention of supplementary materials containing code) for the methodology described.
Open Datasets Yes To evaluate our weight-learning approach, we used the data collected from an earlier study that investigated collaborative efforts in human-robot dialogue (Chai et al. 2014).
Dataset Splits No The paper describes training and testing sets, but no explicit validation dataset split is mentioned.
Hardware Specification No The paper mentions the NAO robot being equipped with components, but does not specify any hardware (CPU, GPU models, memory, etc.) used for running the experiments or simulations described in the paper.
Software Dependencies No The paper mentions components like "computer vision, language understanding and dialogue management" but does not specify any software names with version numbers required to replicate the experiments.
Experiment Setup Yes gamma is a step-size parameter set to be 0.5). We started with uniform weights (i.e., all being 1), and repeated the weight learning process throughout the sequence of the selected 20 training dialogues.