Dynamic Compositional Neural Networks over Tree Structure

Authors: Pengfei Liu, Xipeng Qiu, Xuanjing Huang

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

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate our models on two typical tasks: text classification and text semantic matching. The results show that our models are more expressive due to their learning to learn nature, yet without increasing the number of model s parameters. Moreover, we find certain composition operations can be learned implicitly by meta Tree NN, such as the composition of noun phrases and verb phrases.
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 The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement or link to open-source code for the described methodology.
Open Datasets Yes The word embeddings for all of the models are initialized with Glo Ve vectors [Pennington et al., 2014]. ... SST The movie reviews with two classes (negative, positive) in the Stanford Sentiment Treebank [Socher et al., 2013b]. MR The movie reviews with two classes [Pang and Lee, 2005]. QC The TREC questions dataset involves six different question types. [Li and Roth, 2002]. SUBJ Subjectivity dataset where the goal is to classify each instance (snippet) as being subjective or objective. [Pang and Lee, 2004] IE Idiom enhanced sentiment classification. [Williams et al., 2015]. ... We choose the dataset of Sentences Involving Compositional Knowledge (SICK), which is proposed by Marelli et al. [2014] aiming at evaluation of compositional distributional semantic models.
Dataset Splits Yes The dataset consists of 9927 sentence pairs in a 4500/500/4927 train/dev/test split, in which each sentence pairs are pre-defined into three labels: entailment , contradiction and neutral .
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 word embeddings (GloVe) and a constituency parser ([Klein and Manning, 2003]) but does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes The word embeddings for all of the models are initialized with Glo Ve vectors [Pennington et al., 2014]. The other parameters are initialized by randomly sampling from uniform distribution in [ 0.1, 0.1]. The final hyper-parameters are as follows. The initial learning rate is 0.1. The regularization weight of the parameters is 1E 5 and the others are listed as Table 1.