no code implementations • 24 May 2023 • Yongqi Li, Mayi Xu, Xin Miao, Shen Zhou, Tieyun Qian
Based on this framework, we 1) investigate the strengths and weaknesses of LLMs as the counterfactual generator, and 2) disclose the factors that affect LLMs when generating counterfactuals, including both the intrinsic properties of LLMs and prompt designing.
1 code implementation • journal 2022 • Lingcong Feng, Biqing Zeng, Lewei He, Mayi Xu, Huimin Deng, Pengfei Chen, Zipeng Huang & Weihua Du
Aspect sentiment triplet extraction is a subtask of aspect based sentiment analysis, which has attracted considerable attention in recent years.
Aspect-Based Sentiment Analysis Aspect Sentiment Triplet Extraction
1 code implementation • journal 2022 • Jiatao Chen, Biqing Zeng, Zhibin Du, Huimin Deng, Mayi Xu, Zibang Gan & Meirong Ding
In general, the existing dialogue systems tend to generate generic responses due to lack of external knowledge.
1 code implementation • journal 2022 • Mayi Xu, Biqing Zeng, Heng Yang, Junlong Chi, Jiatao Chen, Hongye Liu a
The DLCF can dynamically capture the range of local context based on the different max distance from the target aspect term to its context words and the DCA allows the model to pay more attention to the cluster which is more critical for sentiment classification.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2