activity
20202025
most citedFaithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods

28 citations · 72 across the 12 of their papers we have counts for

collaborators
Showing 2022Show all

7 papers · 1 filter

cs.CL2022★ 1 cited

WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning

Wenhao Wu, Wei Li, Xinyan Xiao +3

A crucial issue of current text generation models is that they often uncontrollably generate factually inconsistent text with respective of their inputs. Limited by the lack of ann…

cs.CL2022★ 2 cited

FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness

Wenhao Wu, Wei Li, Jiachen Liu +4

Despite being able to generate fluent and grammatical text, current Seq2Seq summarization models still suffering from the unfaithful generation problem. In this paper, we study the…

cs.CL2022

Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation

Wenhao Wu, Wei Li, Jiachen Liu +3

Though model robustness has been extensively studied in language understanding, the robustness of Seq2Seq generation remains understudied. In this paper, we conduct the first quant…

cs.CL2022

PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation

Zhe Hu, Hou Pong Chan, Jiachen Liu +3

Despite recent progress of pre-trained language models on generating fluent text, existing methods still suffer from incoherence problems in long-form text generation tasks that re…

cs.CV2022★ 2 cited

UNIMO-2: End-to-End Unified Vision-Language Grounded Learning

Wei Li, Can Gao, Guocheng Niu +5

Vision-Language Pre-training (VLP) has achieved impressive performance on various cross-modal downstream tasks. However, most existing methods can only learn from aligned image-cap…

cs.CV2022

DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training

Luyang Huang, Guocheng Niu, Jiachen Liu +2

Due to the limitations of the model structure and pre-training objectives, existing vision-and-language generation models cannot utilize pair-wise images and text through bi-direct…