Commonsense Knowledge Enhanced Sentiment Dependency Graph for Sarcasm Detection

Authors: Zhe Yu, Di Jin, Xiaobao Wang, Yawen Li, Longbiao Wang, Jianwu Dang

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on several benchmark datasets reveal that our proposed method beats the state-of-the-art methods in sarcasm detection, and has a stronger interpretability.
Researcher Affiliation Collaboration Zhe Yu1 , Di Jin1,2 , Xiaobao Wang2 , Yawen Li3 , Longbiao Wang2,4 and Jianwu Dang5,2 1School of New Media and Communication, Tianjin University, Tianjin, China 2Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China 3School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, China 4Huiyan Technology (Tianjin) Co., Ltd, Tianjin, China 5Peng Cheng Laboratory, Shenzhen, China
Pseudocode No The paper describes the model architecture and processes in text and with equations, but it does not include a clearly labeled pseudocode or algorithm block.
Open Source Code No The paper does not provide any explicit statements about open-sourcing the code for the described methodology or links to a code repository.
Open Datasets Yes We evaluate our model on three datasets, including Twitter datasets proposed by Ghosh et al. [Ghosh and Veale, 2017], Pt acek et al. [Pt aˇcek et al., 2014], and Riloff et al. [Riloff et al., 2013]. We denote the three datasets as Twitter (Ghosh), Twitter (Pt acek), and Twitter (Riloff). In our work, each sample consists of a sequence of text with associated commonsense knowledge generated by COMET. Detailed statistics are summarized in Table 1.
Dataset Splits No The paper provides 'Train' and 'Test' splits for the datasets in Table 1, but it does not explicitly mention a 'validation' split or specify any cross-validation methodology.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory, etc.) used to run the experiments.
Software Dependencies No The paper mentions 'Adam' as the optimizer and 'pre-trained cased BERT-base', but it does not specify version numbers for these or any other key software dependencies.
Experiment Setup Yes In our experiments, the number of GCN layers is set to 3. The coefficient λ of L2 regularization is set to 0.01. Adam is utilized as the optimizer with the default learning rate of 0.001 to train the model, and the mini-batch size is 256 for Twitter (Ghosh), 64 for Twitter (Pt acek), and 8 for Twitter (Riloff). We use the pre-trained cased BERT-base [Devlin et al., 2018] with 768-dimensional embedding.