activity
20172022
most citedContext-Aware Self-Attention Networks

28 citations · 117 across the 16 of their papers we have counts for

collaborators
Showing cs.CLShow all

21 papers · 1 filter

cs.CL2022

Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?

Pei Zhang, Baosong Yang, Haoran Wei +4

Neural machine translation (NMT) is often criticized for failures that happen without awareness. The lack of competency awareness makes NMT untrustworthy. This is in sharp contrast…

cs.CL20221 cited

Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis

Yiwei Wang, Muhao Chen, Wenxuan Zhou +6

Recent literature focuses on utilizing the entity information in the sentence-level relation extraction (RE), but this risks leaking superficial and spurious clues of relations. As…

cs.CL2022

Dangling-Aware Entity Alignment with Mixed High-Order Proximities

Juncheng Liu, Zequn Sun, Bryan Hooi +5

We study dangling-aware entity alignment in knowledge graphs (KGs), which is an underexplored but important problem. As different KGs are naturally constructed by different sets of…

cs.CL202220 cited

Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generation

Kexin Yang, Dayiheng Liu, Wenqiang Lei +4

Attribute-based Controlled Text Generation (CTG) refers to generating sentences that satisfy desirable attributes (e.g., emotions and topics). Existing works often utilize fine-tun…

cs.CL20227 cited

RoBLEURT Submission for the WMT2021 Metrics Task

Yu Wan, Dayiheng Liu, Baosong Yang +6

In this paper, we present our submission to Shared Metrics Task: RoBLEURT (Robustly Optimizing the training of BLEURT). After investigating the recent advances of trainable metrics…

cs.CL20221 cited

RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation

Yidan Zhang, Yu Wan, Dayiheng Liu +2

Beam search is the most widely used decoding method for neural machine translation (NMT). In practice, the top-1 candidate with the highest log-probability among the n candidates i…