Constraint Acquisition with Recommendation Queries

Authors: Abderrazak Daoudi, Younes Mechqrane, Christian Bessiere, Nadjib Lazaar, El Houssine Bouyakhf

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

Reproducibility Variable Result LLM Response
Research Type Experimental We experimentally compare the QUACQ system to an extended version boosted by the use of our recommendation queries. The results show that the extended version improves the basic QUACQ. (from abstract) and section 6 'Experimental Evaluation'
Researcher Affiliation Academia Abderrazak Daoudi U. Mohammed V Rabat, Morocco Younes Mechqrane U. Mohammed V Rabat, Morocco Christian Bessiere U. of Montpellier Nadjib Lazaar U. of Montpellier El Houssine Bouyakhf U. Mohammed V Rabat, Morocco
Pseudocode Yes Algorithm 1: PREDICT&ASK and Algorithm 2: P-QUACQ = QUACQ + PREDICT&ASK
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is openly available.
Open Datasets No The paper describes the benchmark problems (RLFAP, Vessel Loading, Murder, Zebra problem) used for experiments, but does not provide explicit links, DOIs, specific repository names, or formal citations for public access to the exact datasets or problem instances used. For RLFAP: 'Here we build a simplified version of RLFAP...'
Dataset Splits No The paper discusses constraint acquisition and problem modeling, but does not specify train/validation/test dataset splits (e.g., percentages or sample counts) for its experimental evaluation.
Hardware Specification Yes Our tests were conducted on an Intel Core i5-3320M CPU @ 2.60GHz 4 with 4 Gb of RAM.
Software Dependencies No The paper mentions the QUACQ system and constraint programming concepts, but does not list specific software dependencies with their version numbers required to replicate the experiments.
Experiment Setup Yes For P-QUACQ we report results when predicting links with AA or LHN, without cutoff (i.e, = +1) and also with four values for the cutoff (from 1 to 4). (from section 6.2 Results)