Search Results for author:
Found 11 papers, 3 papers with code
Automating Behavioral Testing in Machine Translation
Behavioral testing in NLP allows fine-grained evaluation of systems by examining their linguistic capabilities through the analysis of input-output behavior.
One Wide Feedforward is All You Need
The Transformer architecture has two main non-embedding components: Attention and the Feed Forward Network (FFN).
Accurate Knowledge Distillation with n-best Reranking
We propose utilizing n-best reranking to enhance Sequence-Level Knowledge Distillation (Kim and Rush, 2016) where we extract pseudo-labels for student model's training data from top n-best hypotheses and leverage a diverse set of models with different inductive biases, objective functions or architectures, including some publicly-available large language models, to pick the highest-quality hypotheses as labels.
Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language.
End-to-End Speech Translation for Code Switched Speech
Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages.
Consistent Transcription and Translation of Speech
To address various shortcomings of this paradigm, recent work explores end-to-end trainable direct models that translate without transcribing.
Variational Neural Machine Translation with Normalizing Flows
Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables.
Statistical Machine Translation Features with Multitask Tensor Networks
We present a three-pronged approach to improving Statistical Machine Translation (SMT), building on recent success in the application of neural networks to SMT.
