Knowledge and Cross-Pair Pattern Guided Semantic Matching for Question Answering

Authors: Zihan Xu, Hai-Tao Zheng, Shaopeng Zhai, Dong Wang9370-9377

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments show that KCG is robust against the diversity of Q-A pairs and outperforms the state-of-the-art systems on different answer selection tasks.
Researcher Affiliation Academia 1Tsinghua Shenzhen International Graduate School, Tsinghua University 2Department of Computer Science and Technology, Tsinghua University, Beijing, China 3School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University
Pseudocode No The paper describes algorithms but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain an explicit statement about the release of source code for the described methodology or a link to a code repository.
Open Datasets Yes We evaluate our model on two widely adopted QA benchmark datasets: Wiki QA (Yang, Yih, and Meek 2015) and Trec QA (Wang, Smith, and Mitamura 2007).
Dataset Splits Yes Wiki QA Train 873 8672 12.0 12.2K 21.9M Dev 126 1130 12.4 Test 243 2351 12.5
Hardware Specification No The paper does not specify any hardware details such as GPU models, CPU types, or memory used for running the experiments.
Software Dependencies No The paper mentions tools and models like GloVE, TransE, Freebase, BERT, and Adam, but does not specify any software versions for libraries, frameworks, or operating systems.
Experiment Setup Yes Table 2: Hyperparameters. Hyperparameter Method Name Definition Intra-Pair Cross-Pair λ Learning rate 0.001 0.01 p Dropout rate 0.2 0.5 L2 L2 normalization 0 0.0005 m Batch size 4 1 w Conv. size [1,2,3,4,5] 1 h Hidden layer size 300 (64) τ Edge threshold 0.95 r Neg. rate 1:1