Translations as Additional Contexts for Sentence Classification

Authors: Reinald Kim Amplayo, Kyungjae Lee, Jinyoung Yeo, Seung-won Hwang

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

Reproducibility Variable Result LLM Response
Research Type Experimental We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets.
Researcher Affiliation Academia Yonsei University, Seoul, South Korea Pohang University of Science and Technology, Pohang, South Korea
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes The code we use in this paper is publicly shared: https: //github.com/rktamplayo/MCFA
Open Datasets Yes (a) MR4 [Pang and Lee, 2005]: Movie reviews data... (b) SUBJ [Pang and Lee, 2004]: Subjectivity data... (c) CR5 [Hu and Liu, 2004]: Customer reviews... (d) TREC6 [Li and Roth, 2002]: TREC question data set...
Dataset Splits Yes If not, we use 10-fold cross validation (marked as CV) with random split. ... We perform early stopping using a random 10% of the training set as the development set.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions 'polyglot library' and 'Fast Text pre-trained vectors' but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes For our CNN, we use rectified linear units and three filters with different window sizes h = 3, 4, 5 with 100 feature maps each... We use dropout... with a dropout rate of 0.5. We also use an l2 constraint of 3... During training, we use mini-batch size of 50. Training is done via stochastic gradient descent over shuffled mini-batches with the Adadelta update rule.