A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning

Authors: Honglun Zhang, Liqiang Xiao, Yongkun Wang, Yaohui Jin

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on five benchmark datasets for text classification show that our model can significantly improve performances of related tasks with additional information from others.
Researcher Affiliation Academia Honglun Zhang1, Liqiang Xiao1, Yongkun Wang2, Yaohui Jin1,2 1State Key Lab of Advanced Optical Communication System and Network 2Network and Information Center Shanghai Jiao Tong University {ykw}@sjtu.edu.cn
Pseudocode Yes Algorithm 1 Task Oriented Sampling
Open Source Code No The paper does not provide any explicit statements about the release of source code or links to a code repository.
Open Datasets Yes As Table 1 shows, we select five benchmark datasets for text classification and design three experiment scenarios to evaluate the performances of our model. Multi-Cardinality Movie review datasets with different average lengths and class numbers, including SST1 [Socher et al., 2013], SST-2 and IMDB [Maas et al., 2011]. Multi-Domain Product review datasets on different domains from Multi-Domain Sentiment Dataset [Blitzer et al., 2007], including Books, DVDs, Electronics and Kitchen. Multi-Objective Classification datasets with different objectives, including IMDB, RN [Apt e et al., 1994] and QC [Li and Roth, 2002].
Dataset Splits Yes We apply 10-fold cross-validation and different combinations of hyperparameters are investigated, of which the best one, as shown in Table 2, is reserved for comparisons with state-of-the-art models.
Hardware Specification No The paper does not explicitly describe the hardware used for running its experiments (e.g., specific GPU/CPU models).
Software Dependencies No The paper mentions Word2Vec but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes Table 2: Hyperparameter settings Embedding size d = 300 Hidden layer size of LSTM n = 100 Initial learning rate η = 0.1 Regularization weight λ = 10-5