← authors · overview

• Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking
  2026
• Learning Distributed Representations of Sentences from Unlabelled Data
  2016
• Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity
  2019
• Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory
  2020
• Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders
  2021
• MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models
  2021
• Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation
  2022
• Improving Word Translation via Two-Stage Contrastive Learning
  2022
• Probing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders
  2022
• MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue
  2022
• Language-Agnostic Bias Detection in Language Models with Bias Probing
  2023
• Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems
  2023
• DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models
  2024