Resolving Over-Constrained Conditional Temporal Problems Using Semantically Similar Alternatives

Authors: Peng Yu, Jiaying Shen, Peter Z. Yeh, Brian Williams

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

Reproducibility Variable Result LLM Response
Research Type Experimental When evaluated empirically on a range of urban trip planning scenarios, CDSR demonstrates a substantial improvement in flexibility compared to temporal relaxation only approaches. To evaluate the usefulness of CDSR in such scenarios, we conducted a user study using the personal assistant built with the algorithm.
Researcher Affiliation Collaboration MIT yupeng@mit.edu; Jiaying Shen and Peter Z. Yeh, Nuance Communications, Inc. {Jiaying.Shen,Peter.Yeh}@nuance.com; Brian Williams, MIT williams@mit.edu
Pseudocode Yes Algorithm 1: An overview of the CDSR algorithm; Algorithm 2: Function EXPANDONCONFLICT; Algorithm 3: Function EXPANDDOMAINRELAXATION
Open Source Code No The paper refers to the Word2Vec tool's code (Word2Vec, 2013) but does not state that the code for CDSR itself is open-source or provided.
Open Datasets Yes The vector model of CDSR is trained by the continuous skip-gram algorithm in the Word2Vec package with a Google News dataset [Word2Vec, 2013].
Dataset Splits No The paper discusses scenarios and a user study but does not provide specific training, validation, or test splits for any dataset used for the main experimental evaluation of CDSR.
Hardware Specification No The paper mentions that components were deployed on 'separate servers' but does not provide specific hardware details such as CPU/GPU models or memory.
Software Dependencies No The paper mentions the 'Word2Vec package' but does not provide a specific version number for it or any other software dependencies.
Experiment Setup No The paper describes the user study setup and the algorithm but does not provide specific experimental setup details such as hyperparameters or system-level training settings for the CDSR algorithm itself.