Evidence-Aware Hierarchical Interactive Attention Networks for Explainable Claim Verification

Authors: Lianwei Wu, Yuan Rao, Xiong Yang, Wanzhen Wang, Ambreen Nazir

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on two datasets demonstrate that EHIAN not only achieves the state-of-the-art performance but also secures effective evidence to explain the results.
Researcher Affiliation Academia Lianwei Wu , Yuan Rao , Xiong Yang , Wanzhen Wang and Ambreen Nazir Lab of Social Intelligence and Complexity Data Processing, School of Software Engineering, Xi an Jiaotong University, China Shannxi Joint Key Laboratory for Artifact Intelligence(Sub-Lab of Xi an Jiaotong University), China Research Institute of Xi an Jiaotong University, Shenzhen, China {stayhungry, youngpanda, kelyin0417, ambreen.nazir}@stu.xjtu.edu.cn, raoyuan@mail.xjtu.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 to its own source code (e.g., a specific repository link or an explicit code release statement).
Open Datasets Yes We use two public fact-checking datasets, i.e., Snopes and Politi Fact provided by Popat et al. [2018] for evaluation.
Dataset Splits Yes We hold out 10% of all data as validation data for parameter tuning, and conduct 5-fold cross-validation on the remaining 90% of the data.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions software like "pre-trained BERT-base model [Devlin et al., 2019]", "Adam optimizer [Kingma and Ba, 2014]", "Tensorflow4", and "Theano5". However, it does not provide specific version numbers for the software dependencies used in their implementation beyond the general references to TensorFlow and Theano.
Experiment Setup Yes For parameter configurations, we apply the pre-trained BERTbase model [Devlin et al., 2019] to initialize our token embeddings and their length is set to 300. In self-attention networks, attention heads and blocks are set to 6 and 2 respectively, and the dropout of multi-head attention is set to 0.7. Moreover, all the models are trained to use Adam optimizer [Kingma and Ba, 2014] with a learning rate of 0.002 and mini-batches of size 64 to minimize categorical cross-entropy loss. We employ L2-regularizers with the fully connected layer. Also, the dropout is 0.5.