Recurrent Neural Network for Text Classification with Multi-Task Learning

Authors: Pengfei Liu, Xipeng Qiu, Xuanjing Huang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on four benchmark text classification tasks show that our proposed models can improve the performance of a task with the help of other related tasks.
Researcher Affiliation Academia Pengfei Liu Xipeng Qiu Xuanjing Huang Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University 825 Zhangheng Road, Shanghai, China {pfliu14,xpqiu,xjhuang}@fudan.edu.cn
Pseudocode No No clearly labeled pseudocode or algorithm blocks were found.
Open Source Code No The paper mentions "open source implementation of PV in Gensim" (a third-party tool) but does not state that the authors are releasing their own source code for the methodology described.
Open Datasets Yes SST-1 The movie reviews with five classes... in the Stanford Sentiment Treebank1 [Socher et al., 2013]. ... SST-2 The movie reviews with binary classes. It is also from the Stanford Sentiment Treebank. ... SUBJ Subjectivity data set... [Pang and Lee, 2004]. ... IMDB The IMDB dataset2... [Maas et al., 2011]. ... 1http://nlp.stanford.edu/sentiment. 2http://ai.stanford.edu/~amaas/data/sentiment/
Dataset Splits Yes For datasets without development set, we use 10-fold crossvalidation (CV) instead. ... Table 1: Statistics of the four datasets used in this paper. (includes Dev. Size column)
Hardware Specification No No specific hardware details (e.g., CPU, GPU models, memory specifications) used for running the experiments are provided in the paper.
Software Dependencies No The paper mentions using "word2vec [Mikolov et al., 2013]" and the "Adagrad update rule [Duchi et al., 2011]" for optimization, and refers to "Gensim" for PV, but it does not specify version numbers for any software dependencies required to replicate the experimental environment.
Experiment Setup Yes The final hyper-parameters are as follows. The embedding size for specific task and shared layer are 64. For Model-I, there are two embeddings for each word, and both their sizes are 64. The hidden layer size of LSTM is 50. The initial learning rate is 0.1. The regularization weight of the parameters is 10 5.