Publications (30)
BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric
Mingda Chen, Paul-Ambroise Duquenne, Pierre Andrews +4
End-to-End speech-to-speech translation (S2ST) is generally evaluated with text-based metrics. This means that generated speech has to be automatically transcribed, making the eval…
Learning Probabilistic Sentence Representations from Paraphrases
Mingda Chen, Kevin Gimpel
Probabilistic word embeddings have shown effectiveness in capturing notions of generality and entailment, but there is very little work on doing the analogous type of investigation…
Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering
Mingda Chen, Xilun Chen, Wen-tau Yih
Few-shot learning for open domain multi-hop question answering typically relies on the incontext learning capability of large language models (LLMs). While powerful, these LLMs usu…
A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations
Mingda Chen, Qingming Tang, Sam Wiseman +1
We propose a generative model for a sentence that uses two latent variables, with one intended to represent the syntax of the sentence and the other to represent its semantics. We…
A Survey on Diffusion Language Models
Tianyi Li, Mingda Chen, Bowei Guo +1
Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through…
How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed Questions
Zewei Chu, Mingda Chen, Jing Chen +4
We present a large-scale dataset for the task of rewriting an ill-formed natural language question to a well-formed one. Our multi-domain question rewriting MQR dataset is construc…