An Unsupervised Model With Attention Autoencoders for Question Retrieval

Authors: Minghua Zhang, Yunfang Wu

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct experiments on the open CQA datasets of Sem Eval-2016 and Sem Eval-2017.
Researcher Affiliation Academia Key Laboratory of Computational Linguistics, Peking University, MOE, China {zhangmh, wuyf}@pku.edu.cn
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access information (specific link, explicit statement, or mention in supplementary materials) to the source code for the methodology described.
Open Datasets Yes We conduct experiments on the open CQA datasets of Sem Eval-2016 and Sem Eval-2017. These datasets contain real data from the community-created Qatar Living Forums. ... We utilize the large amount of unlabeled data released by the organizers, which consists of 189,941 questions and 1,894,456 comments.
Dataset Splits Yes The labeled dataset is divided into three folders: training, development and test. Table 1 gives the statistics distribution of the dataset. ... Class Train Dev 2016-Test 2017-Test Original 267 50 70 88 Candidates 2669 500 700 880 Perfect Match 235 59 81 24 Relevant 648 155 152 139 Irrelevant 1586 286 467 717
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, or cloud instances) used for running the experiments.
Software Dependencies No The paper mentions the use of 'word2vec' and 'Adam algorithm' but does not specify any software names with version numbers for reproducibility.
Experiment Setup Yes For the attention autoencoders, the dimensionality of word embeddings was set to 200. ... Both the encoder and decoder consist of a stack of 2 identical layers. The dimension of hidden representation was set to 200... We applied the Adam algorithm... using shuffled mini-batches of size 48. The initial learning rate is 0.0004. The autoencoders learn until the performance in the development data stops improving, with patience p = 3... We set α in equation (18) to 0.035, which was tuned via grid search over the following range of values {0.01, 0.015, 0.02, . . . , 0.1}.