Simultaneous speech translation (SimulST) translates partial speech inpu...
It remains a question that how simultaneous interpretation (SI) data aff...
A conversational recommender system (CRS) is a practical application for...
Discrete prompts have been used for fine-tuning Pre-trained Language Mod...
Simultaneous translation is a task in which translation begins before th...
Although the well-known MR-to-text E2E dataset has been used by many
res...
Word embedding is a fundamental technology in natural language processin...
Speech segmentation, which splits long speech into short segments, is
es...
This paper proposes visual-text to speech (vTTS), a method for synthesiz...
Simultaneous translation is a task in which translation begins before th...
Non-autoregressive neural machine translation (NAT) usually employs
sequ...
Human-assisting systems such as dialogue systems must take thoughtful,
a...
This paper presents a newly developed, simultaneous neural speech-to-spe...
We present our work in progress exploring the possibilities of a shared
...
Word embeddings, which often represent such analogic relations as king -...
Simultaneous machine translation is a variant of machine translation tha...
This document describes the findings of the Third Workshop on Neural
Gen...
We propose a novel method for selecting coherent and diverse responses f...
Although generation-based dialogue systems have been widely researched, ...
Multi-source translation systems translate from multiple languages to a
...
In neural machine translation (NMT), the computational cost at the outpu...
Multi-source translation is an approach to exploit multiple inputs (e.g....
Training of neural machine translation (NMT) models usually uses mini-ba...
One of the most important problems in machine translation (MT) evaluatio...
This paper introduces a novel neural network model for question answerin...