Dialog-based Language Learning

Authors: Jason E. Weston

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate a set of baseline learning strategies on these tasks, and show that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher s response.
Researcher Affiliation Industry Jason Weston Facebook AI Research, New York. jase@fb.com
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks (clearly labeled algorithm sections or code-like formatted procedures).
Open Source Code No The paper states that the datasets are available for download at http://fb.ai/babi, but it does not provide concrete access to the source code for the methodology described in the paper.
Open Datasets Yes In our experiments we constructed the ten supervision tasks for the two datasets which are all available for download at http://fb.ai/babi.
Dataset Splits Yes In all cases a training, validation and test set is provided. For the b Ab I dataset this consists of 1000, 100 and 1000 questions respectively per task, and for movie QA there are 96k, 10k and 10k respectively.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions using 'end-to-end memory network (Mem N2N)' but does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers).
Experiment Setup No The paper states 'Hyperparameters for all methods are optimized on the validation sets' but does not provide concrete hyperparameter values, training configurations, or system-level settings in the main text.