55 citations · 208 across the 27 of their papers we have counts for
27 papers
Disentangled Phonetic Representation for Chinese Spelling Correction
Zihong Liang, Xiaojun Quan, Qifan Wang
Chinese Spelling Correction (CSC) aims to detect and correct erroneous characters in Chinese texts. Although efforts have been made to introduce phonetic information (Hanyu Pinyin)…
Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog
Fanqi Wan, Weizhou Shen, Ke Yang +2
Retrieving proper domain knowledge from an external database lies at the heart of end-to-end task-oriented dialog systems to generate informative responses. Most existing systems b…
AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression
Siyue Wu, Hongzhan Chen, Xiaojun Quan +2
Knowledge distillation has attracted a great deal of interest recently to compress pre-trained language models. However, existing knowledge distillation methods suffer from two lim…
Clustering-Aware Negative Sampling for Unsupervised Sentence Representation
Jinghao Deng, Fanqi Wan, Tao Yang +2
Contrastive learning has been widely studied in sentence representation learning. However, earlier works mainly focus on the construction of positive examples, while in-batch sampl…
Generic Dependency Modeling for Multi-Party Conversation
Weizhou Shen, Xiaojun Quan, Ke Yang
To model the dependencies between utterances in multi-party conversations, we propose a simple and generic framework based on the dependency parsing results of utterances. Particul…
Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detection
Tao Yang, Jinghao Deng, Xiaojun Quan +1
Predicting personality traits based on online posts has emerged as an important task in many fields such as social network analysis. One of the challenges of this task is assemblin…
AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning
Tao Yang, Jinghao Deng, Xiaojun Quan +2
Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective…
XPrompt: Exploring the Extreme of Prompt Tuning
Fang Ma, Chen Zhang, Lei Ren +5
Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner. While prompt tuning has gr…
Autoregressive Entity Generation for End-to-End Task-Oriented Dialog
Guanhuan Huang, Xiaojun Quan, Qifan Wang
Task-oriented dialog (TOD) systems often require interaction with an external knowledge base to retrieve necessary entity (e.g., restaurant) information to support the response gen…
UBARv2: Towards Mitigating Exposure Bias in Task-Oriented Dialogs
Yunyi Yang, Hong Ding, Qingyi Liu +1
This paper studies the exposure bias problem in task-oriented dialog systems, where the model's generated content over multiple turns drives the dialog context away from the ground…
Joint Generator-Ranker Learning for Natural Language Generation
Weizhou Shen, Yeyun Gong, Yelong Shen +4
Generate-then-rank is a widely used mechanism for text generation, where a generator produces multiple text candidates and a ranker chooses the best one among the text candidates.…
GL-RG: Global-Local Representation Granularity for Video Captioning
Liqi Yan, Qifan Wang, Yiming Cui +4
Video captioning is a challenging task as it needs to accurately transform visual understanding into natural language description. To date, state-of-the-art methods inadequately mo…
Deep Partial Multiplex Network Embedding
Qifan Wang, Yi Fang, Anirudh Ravula +5
Network embedding is an effective technique to learn the low-dimensional representations of nodes in networks. Real-world networks are usually with multiplex or having multi-view r…
WebFormer: The Web-page Transformer for Structure Information Extraction
Qifan Wang, Yi Fang, Anirudh Ravula +3
Structure information extraction refers to the task of extracting structured text fields from web pages, such as extracting a product offer from a shopping page including product t…
Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
Yunhao Li, Yunyi Yang, Xiaojun Quan +1
Dialogue policy learning, a subtask that determines the content of system response generation and then the degree of task completion, is essential for task-oriented dialogue system…
Psycholinguistic Tripartite Graph Network for Personality Detection
Tao Yang, Feifan Yang, Haolan Ouyang +1
Most of the recent work on personality detection from online posts adopts multifarious deep neural networks to represent the posts and builds predictive models in a data-driven man…
Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene
Ruikun Luo, Guanhuan Huang, Xiaojun Quan
The major paradigm of applying a pre-trained language model to downstream tasks is to fine-tune it on labeled task data, which often suffers instability and low performance when th…
Directed Acyclic Graph Network for Conversational Emotion Recognition
Weizhou Shen, Siyue Wu, Yunyi Yang +1
The modeling of conversational context plays a vital role in emotion recognition from conversation (ERC). In this paper, we put forward a novel idea of encoding the utterances with…
DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition
Weizhou Shen, Junqing Chen, Xiaojun Quan +1
This paper presents our pioneering effort for emotion recognition in conversation (ERC) with pre-trained language models. Unlike regular documents, conversational utterances appear…
Syntax-Enhanced Pre-trained Model
Zenan Xu, Daya Guo, Duyu Tang +7
We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre…
UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2
Yunyi Yang, Yunhao Li, Xiaojun Quan
This paper presents our task-oriented dialog system UBAR which models task-oriented dialogs on a dialog session level. Specifically, UBAR is acquired by fine-tuning the large pre-t…
Embedding Dynamic Attributed Networks by Modeling the Evolution Processes
Zenan Xu, Zijing Ou, Qinliang Su +3
Network embedding has recently emerged as a promising technique to embed nodes of a network into low-dimensional vectors. While fairly successful, most existing works focus on the…
Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation
Kun Li, Chengbo Chen, Xiaojun Quan +2
Aspect term extraction aims to extract aspect terms from review texts as opinion targets for sentiment analysis. One of the big challenges with this task is the lack of sufficient…
Multi-Domain Dialogue Acts and Response Co-Generation
Kai Wang, Junfeng Tian, Rui Wang +2
Generating fluent and informative responses is of critical importance for task-oriented dialogue systems. Existing pipeline approaches generally predict multiple dialogue acts firs…