6 citations · 16 across the 7 of their papers we have counts for
7 papers
Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization
Chenhui Shen, Liying Cheng, Xuan-Phi Nguyen +2
With the recent undeniable advancement in reasoning abilities in large language models (LLMs) like ChatGPT and GPT-4, there is a growing trend for using LLMs on various tasks. One…
A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization
Chenhui Shen, Liying Cheng, Xuan-Phi Nguyen +2
Pre-trained language models (PLMs) have achieved outstanding achievements in abstractive single-document summarization (SDS). However, such benefits may not fully extend to multi-d…
Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention
Xiao Liu, Jian Zhang, Heng Zhang +2
Compared with standard text, understanding dialogue is more challenging for machines as the dynamic and unexpected semantic changes in each turn. To model such inconsistent semanti…
Inconsistencies in Masked Language Models
Tom Young, Yunan Chen, Yang You
Learning to predict masked tokens in a sequence has been shown to be a helpful pretraining objective for powerful language models such as PaLM2. After training, such masked languag…
GPTR: Gestalt-Perception Transformer for Diagram Object Detection
Xin Hu, Lingling Zhang, Jun Liu +3
Diagram object detection is the key basis of practical applications such as textbook question answering. Because the diagram mainly consists of simple lines and color blocks, its v…
SentBS: Sentence-level Beam Search for Controllable Summarization
Chenhui Shen, Liying Cheng, Lidong Bing +2
A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting researc…
MReD: A Meta-Review Dataset for Structure-Controllable Text Generation
Chenhui Shen, Liying Cheng, Ran Zhou +3
When directly using existing text generation datasets for controllable generation, we are facing the problem of not having the domain knowledge and thus the aspects that could be c…