Search Results for author:
Found 4 papers, 2 papers with code
Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction
Recent mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring the correlations among multiple events.
Revisiting Self-Training for Few-Shot Learning of Language Model
In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM.
DynaEval: Unifying Turn and Dialogue Level Evaluation
Effective evaluation metrics should reflect the dynamics of such interaction.
End-to-End Code-Switching ASR for Low-Resourced Language Pairs
In this work, we describe an E2E ASR pipeline for the recognition of CS speech in which a low-resourced language is mixed with a high resourced language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
