3 papers
cs.CL2022
Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual Samples
Chengyuan Liu, Leilei Gan, Kun Kuang +1
The aim of Logic2Text is to generate controllable and faithful texts conditioned on tables and logical forms, which not only requires a deep understanding of the tables and logical…
cs.CL2021
Dialogue Inspectional Summarization with Factual Inconsistency Awareness
Leilei Gan, Yating Zhang, Kun Kuang +5
Dialogue summarization has been extensively studied and applied, where the prior works mainly focused on exploring superior model structures to align the input dialogue and the out…
cs.CL2019
Investigating Self-Attention Network for Chinese Word Segmentation
Leilei Gan, Yue Zhang
Neural network has become the dominant method for Chinese word segmentation. Most existing models cast the task as sequence labeling, using BiLSTM-CRF for representing the input an…