Relevance-Promoting Language Model for Short-Text Conversation

Authors: Xin Li, Piji Li, Wei Bi, Xiaojiang Liu, Wai Lam8253-8260

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on a large Chinese STC dataset demonstrate the superiority of the proposed model on relevance metrics and diversity metrics.
Researcher Affiliation Collaboration Xin Li,1 Piji Li,2 Wei Bi,2 Xiaojiang Liu,2 Wai Lam1 1Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong 2Tencent AI Lab, Shenzhen, China
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes Code available at https://ai.tencent.com/ailab/nlp/dialogue/.
Open Datasets Yes We utilize the benchmark STC dataset (Liu et al. 2018) to evaluate the effectiveness of the proposed relevance-promoting transformer language model.
Dataset Splits Yes We split the dataset such that #train:#dev:#test is 7,024,156:2,000:800.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments, such as GPU models, CPU types, or memory specifications.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes Training details are provided in the appendix.