151 citations · 266 across the 27 of their papers we have counts for
46 papers
A Survey for Efficient Open Domain Question Answering
Qin Zhang, Shangsi Chen, Dongkuan Xu +4
Open domain question answering (ODQA) is a longstanding task aimed at answering factual questions from a large knowledge corpus without any explicit evidence in natural language pr…
Incorporating Constituent Syntax for Coreference Resolution
Fan Jiang, Trevor Cohn
Syntax has been shown to benefit Coreference Resolution from incorporating long-range dependencies and structured information captured by syntax trees, either in traditional statis…
It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data
Jinming Zhao, Philip Arthur, Gholamreza Haffari +2
Most existing simultaneous machine translation (SiMT) systems are trained and evaluated on offline translation corpora. We argue that SiMT systems should be trained and tested on r…
Unsupervised Cross-Lingual Transfer of Structured Predictors without Source Data
Kemal Kurniawan, Lea Frermann, Philip Schulz +1
Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalis…
Contrastive Learning for Fair Representations
Aili Shen, Xudong Han, Trevor Cohn +2
Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing me…
Fairness-aware Class Imbalanced Learning
Shivashankar Subramanian, Afshin Rahimi, Timothy Baldwin +2
Class imbalance is a common challenge in many NLP tasks, and has clear connections to bias, in that bias in training data often leads to higher accuracy for majority groups at the…