A Contrastive Framework for Neural Text Generation

Authors: Yixuan Su, Tian Lan, Yan Wang, Dani Yogatama, Lingpeng Kong, Nigel Collier

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments and analyses on three benchmarks from two languages demonstrate that our proposed approach significantly outperforms current state-of-the-art text generation methods as evaluated by both human and automatic metrics.
Researcher Affiliation Collaboration Language Technology Lab, University of Cambridge Tencent AI Lab Deep Mind Department of Computer Science, The University of Hong Kong
Pseudocode No The paper describes the algorithms in text but does not provide formal pseudocode or algorithm blocks.
Open Source Code Yes Our code and models are publicly available at https://github.com/yxuansu/Sim CTG.
Open Datasets Yes We conduct experiments on the Wikitext-103 dataset [16]
Dataset Splits Yes The hyperparameters of different methods are selected based on their optimal MAUVE (detailed in 4.1.2) performance on the validation set.
Hardware Specification Yes All experiments are conducted on an NVIDIA Tesla A100 GPU.
Software Dependencies No The paper mentions 'Huggingface Library [28]' but does not specify version numbers for it or any other software dependencies.
Experiment Setup Yes For our Sim CTG and the MLE baseline, we fine-tune the models on Wikitext-103 for 40k training steps. The batch size is set as 128 and the training samples are truncated to a maximum length of 256. We optimize the model with Adam optimizer [12] and a learning rate of 2e-5.