78 citations · 176 across the 7 of their papers we have counts for
7 papers
Lip-reading with Hierarchical Pyramidal Convolution and Self-Attention
Hang Chen, Jun Du, Yu Hu +3
In this paper, we propose a novel deep learning architecture to improving word-level lip-reading. On the one hand, we first introduce the multi-scale processing into the spatial fe…
Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing
Run-Ze Wang, Zhen-Hua Ling, Jing-Bo Zhou +1
The task of multi-turn text-to-SQL semantic parsing aims to translate natural language utterances in an interaction into SQL queries in order to answer them using a database which…
Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement
Hang Chen, Jun Du, Yu Hu +3
In this paper, we propose a visual embedding approach to improving embedding aware speech enhancement (EASE) by synchronizing visual lip frames at the phone and place of articulati…
Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge
Quan Liu, Hui Jiang, Zhen-Hua Ling +3
In this paper, we propose commonsense knowledge enhanced embeddings (KEE) for solving the Pronoun Disambiguation Problems (PDP). The PDP task we investigate in this paper is a comp…
Part-of-Speech Relevance Weights for Learning Word Embeddings
Quan Liu, Zhen-Hua Ling, Hui Jiang +1
This paper proposes a model to learn word embeddings with weighted contexts based on part-of-speech (POS) relevance weights. POS is a fundamental element in natural language. Howev…
Probabilistic Reasoning via Deep Learning: Neural Association Models
Quan Liu, Hui Jiang, Andrew Evdokimov +4
In this paper, we propose a new deep learning approach, called neural association model (NAM), for probabilistic reasoning in artificial intelligence. We propose to use neural netw…
Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
Shiliang Zhang, Cong Liu, Hui Jiang +3
In this paper, we propose a novel neural network structure, namely \emph{feedforward sequential memory networks (FSMN)}, to model long-term dependency in time series without using…