activity
20182023
most citedEmoGraph: Capturing Emotion Correlations using Graph Networks

27 citations · 140 across the 12 of their papers we have counts for

collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2022

Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset

Tiezheng Yu, Rita Frieske, Peng Xu +9

Automatic speech recognition (ASR) on low resource languages improves the access of linguistic minorities to technological advantages provided by artificial intelligence (AI). In t…

cs.CL2021

Contrastive Document Representation Learning with Graph Attention Networks

Peng Xu, Xinchi Chen, Xiaofei Ma +2

Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention…

cs.CL202111 cited

Attention-guided Generative Models for Extractive Question Answering

Peng Xu, Davis Liang, Zhiheng Huang +1

We propose a novel method for applying Transformer models to extractive question answering (QA) tasks. Recently, pretrained generative sequence-to-sequence (seq2seq) models have ac…

cs.CL20211 cited

Multiplicative Position-aware Transformer Models for Language Understanding

Zhiheng Huang, Davis Liang, Peng Xu +1

Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks. The self-attention mechanism…

cs.CL20202 cited

Cross-lingual Spoken Language Understanding with Regularized Representation Alignment

Zihan Liu, Genta Indra Winata, Peng Xu +2

Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments be…

cs.CL202011 cited

Improve Transformer Models with Better Relative Position Embeddings

Zhiheng Huang, Davis Liang, Peng Xu +1

Transformer architectures rely on explicit position encodings in order to preserve a notion of word order. In this paper, we argue that existing work does not fully utilize positio…