Vocabulary Learning via Optimal Transport for Neural Machine Translation [paper] [code]
- All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text [paper]
- assess non-experts' ability to distinguish between human and machine-authored text
- Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning [paper]
- Why can we use relatively vanilla gradient descent algorithms to tune a model with hundreds of millions of parameters on datas with only hundreds or thousands of labeled examples?
- Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering [paper]
- Neural Machine Translation with Monolingual Translation Memory [paper]
- Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers
- UnNatural Language Inference
- Directed Acyclic Graph Network for Conversational Emotion Recognition [paper] [code]
- Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction [paper]
- Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection [paper]
- Structured Sentiment Analysis as Dependency Graph Parsing [paper]
- Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting [paper]