activity
20162026
most citedLearning Pixel-Distribution Prior with Wider Convolution for Image Denoising

16 citations · 79 across the 29 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL20221 cited

Quantifying syntax similarity with a polynomial representation of dependency trees

Pengyu Liu, Tinghao Feng, Rui Liu

We introduce a graph polynomial that distinguishes tree structures to represent dependency grammar and a measure based on the polynomial representation to quantify syntax similarit…

cs.CL20227 cited

Towards a Unified Multi-Dimensional Evaluator for Text Generation

Ming Zhong, Yang Liu, Da Yin +6

Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimen…

cs.CL2022

Balancing Multi-Domain Corpora Learning for Open-Domain Response Generation

Yujie Xing, Jinglun Cai, Nils Barlaug +2

Open-domain conversational systems are assumed to generate equally good responses on multiple domains. Previous work achieved good performance on the single corpus, but training an…

cs.CL20212 cited

How well do you know your summarization datasets?

Priyam Tejaswin, Dhruv Naik, Pengfei Liu

State-of-the-art summarization systems are trained and evaluated on massive datasets scraped from the web. Despite their prevalence, we know very little about the underlying charac…

cs.CL202111 cited

SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization

Yixin Liu, Pengfei Liu

In this paper, we present a conceptually simple while empirically powerful framework for abstractive summarization, SimCLS, which can bridge the gap between the learning objective…