1.5k citations · 1.9k across the 17 of their papers we have counts for
27 papers
Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis
Guanghui Xu, Wei Song, Zhengchen Zhang +3
Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which ma…
Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training
Yingyao Wang, Junwei Bao, Guangyi Liu +4
This paper aims to enhance the few-shot relation classification especially for sentences that jointly describe multiple relations. Due to the fact that some relations usually keep…
Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product
Tiangang Zhu, Yue Wang, Haoran Li +3
Product attribute values are essential in many e-commerce scenarios, such as customer service robots, product recommendations, and product retrieval. While in the real world, the a…
Selective Attention Based Graph Convolutional Networks for Aspect-Level Sentiment Classification
Xiaochen Hou, Jing Huang, Guangtao Wang +2
Aspect-level sentiment classification aims to identify the sentiment polarity towards a specific aspect term in a sentence. Most current approaches mainly consider the semantic inf…
Zero-shot Text-to-SQL Learning with Auxiliary Task
Shuaichen Chang, Pengfei Liu, Yun Tang +3
Recent years have seen great success in the use of neural seq2seq models on the text-to-SQL task. However, little work has paid attention to how these models generalize to realisti…
Multiple instance learning with graph neural networks
Ming Tu, Jing Huang, Xiaodong He +1
Multiple instance learning (MIL) aims to learn the mapping between a bag of instances and the bag-level label. In this paper, we propose a new end-to-end graph neural network (GNN)…