activity
20172023
most citedTable-to-text Generation by Structure-aware Seq2seq Learning

39 citations · 79 across the 15 of their papers we have counts for

collaborators
Showing cs.CLShow all

13 papers · 1 filter

cs.CL2021

Explicit Interaction Network for Aspect Sentiment Triplet Extraction

Peiyi Wang, Tianyu Liu, Damai Dai +3

Aspect Sentiment Triplet Extraction (ASTE) aims to recognize targets, their sentiment polarities and opinions explaining the sentiment from a sentence. ASTE could be naturally divi…

cs.CL2021★ 5 cited

Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker

Runxin Xu, Tianyu Liu, Lei Li +1

Document-level event extraction aims to recognize event information from a whole piece of article. Existing methods are not effective due to two challenges of this task: a) the tar…

cs.CL2021

A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation

Tianyu Liu, Yizhe Zhang, Chris Brockett +4

Large pretrained generative models like GPT-3 often suffer from hallucinating non-existent or incorrect content, which undermines their potential merits in real applications. Exist…

cs.CL2021★ 6 cited

Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View

Tianyu Liu, Xin Zheng, Baobao Chang +1

In open domain table-to-text generation, we notice that the unfaithful generation usually contains hallucinated content which can not be aligned to any input table record. We thus…

cs.CL2021

First Target and Opinion then Polarity: Enhancing Target-opinion Correlation for Aspect Sentiment Triplet Extraction

Lianzhe Huang, Peiyi Wang, Sujian Li +5

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from a sentence, including target entities, associated sentiment polarities, and opinion spans which rationalize…

cs.CL2020

An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference

Tianyu Liu, Xin Zheng, Xiaoan Ding +2

The prior work on natural language inference (NLI) debiasing mainly targets at one or few known biases while not necessarily making the models more robust. In this paper, we focus…