Machine learning methods for language

Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models

Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech

SADE: A Self-adaptive Expert for Multi-dataset Question Answering

Boosting Prompt-based Few-shot Learners through Out-of-domain Knowledge Distillation

Towards A Unified Training for Levenshtein Transformer

Improving Sentence Similarity Estimation for Unsupervised Extractive Summarization

Contextual Similarity is More Valuable than Character Similarity: An Empirical Study for Chinese Spell Checking

Prompt-Distiller: Few-shot Knowledge Distillation for Prompt-based Language Learners with Dual Contrastive Learning

Dialogue System with Missing Observation

Adversarially Robust Fairness-aware Regression