activity
20172022
most citedEfficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog

29 citations · 145 across the 24 of their papers we have counts for

collaborators

63 papers

eess.AS2022

Does Joint Training Really Help Cascaded Speech Translation?

Viet Anh Khoa Tran, David Thulke, Yingbo Gao +2

Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results. However, fundamental…

cs.CL2022

Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token

Baohao Liao, David Thulke, Sanjika Hewavitharana +2

The pre-training of masked language models (MLMs) consumes massive computation to achieve good results on downstream NLP tasks, resulting in a large carbon footprint. In the vanill…

cs.CL2022

Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model

Nico Daheim, David Thulke, Christian Dugast +1

In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes theorem. One component is a tradition…

cs.CL2022

Monotonic segmental attention for automatic speech recognition

Albert Zeyer, Robin Schmitt, Wei Zhou +2

We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, bette…

cs.CL20222 cited

Is Encoder-Decoder Redundant for Neural Machine Translation?

Yingbo Gao, Christian Herold, Zijian Yang +1

Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. For machine translation, despite the evolution from long short-term memory networks to Trans…

cs.CL20222 cited

Revisiting Checkpoint Averaging for Neural Machine Translation

Yingbo Gao, Christian Herold, Zijian Yang +1

Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that…