183 citations · 1.2k across the 49 of their papers we have counts for
49 papers
DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering
Pei Ke, Fei Huang, Fei Mi +4
Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability. Specifically, most of the well-performed…
KPT: Keyword-guided Pre-training for Grounded Dialog Generation
Qi Zhu, Fei Mi, Zheng Zhang +6
Incorporating external knowledge into the response generation process is essential to building more helpful and reliable dialog agents. However, collecting knowledge-grounded conve…
Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization
Yuxian Gu, Pei Ke, Xiaoyan Zhu +1
Training language models to learn from human instructions for zero-shot cross-task generalization has attracted much attention in NLP communities. Recently, instruction tuning (IT)…
Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation
Pei Ke, Haozhe Ji, Zhenyu Yang +4
Despite the success of text-to-text pre-trained models in various natural language generation (NLG) tasks, the generation performance is largely restricted by the number of labeled…
Rethinking and Refining the Distinct Metric
Siyang Liu, Sahand Sabour, Yinhe Zheng +3
Distinct- score\cite{Li2016} is a widely used automatic metric for evaluating diversity in language generation tasks. However, we observed that the original approach for calcula…
CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation
Pei Ke, Hao Zhou, Yankai Lin +4
Existing reference-free metrics have obvious limitations for evaluating controlled text generation models. Unsupervised metrics can only provide a task-agnostic evaluation result w…
Continual Prompt Tuning for Dialog State Tracking
Qi Zhu, Bing Li, Fei Mi +2
A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle. However, continua…
EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
Yuxian Gu, Jiaxin Wen, Hao Sun +8
Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems. However, previous works mainly focus on showing and evaluating the conversationa…
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
Hao Sun, Guangxuan Xu, Jiawen Deng +6
Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety pro…
EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
Hao Zhou, Pei Ke, Zheng Zhang +11
Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue dat…
CPM-2: Large-scale Cost-effective Pre-trained Language Models
Zhengyan Zhang, Yuxian Gu, Xu Han +16
In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-…
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
Pei Ke, Haozhe Ji, Yu Ran +5
Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which la…
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
Fei Huang, Zikai Chen, Chen Henry Wu +3
Autoregressive models have been widely used in unsupervised text style transfer. Despite their success, these models still suffer from the content preservation problem that they us…
A Semantic-based Method for Unsupervised Commonsense Question Answering
Yilin Niu, Fei Huang, Jiaming Liang +3
Unsupervised commonsense question answering is appealing since it does not rely on any labeled task data. Among existing work, a popular solution is to use pre-trained language mod…
CPM: A Large-scale Generative Chinese Pre-trained Language Model
Zhengyan Zhang, Xu Han, Hao Zhou +22
Pre-trained Language Models (PLMs) have proven to be beneficial for various downstream NLP tasks. Recently, GPT-3, with 175 billion parameters and 570GB training data, drew a lot o…
Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph
Haozhe Ji, Pei Ke, Shaohan Huang +3
Despite the success of generative pre-trained language models on a series of text generation tasks, they still suffer in cases where reasoning over underlying commonsense knowledge…
A Large-Scale Chinese Short-Text Conversation Dataset
Yida Wang, Pei Ke, Yinhe Zheng +4
The advancements of neural dialogue generation models show promising results on modeling short-text conversations. However, training such models usually needs a large-scale high-qu…
Knowledge-Aided Open-Domain Question Answering
Mantong Zhou, Zhouxing Shi, Minlie Huang +1
Open-domain question answering (QA) aims to find the answer to a question from a large collection of documents.Though many models for single-document machine comprehension have ach…
Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness
Zheng Zhang, Lizi Liao, Xiaoyan Zhu +4
Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy…
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
Hao Zhou, Chujie Zheng, Kaili Huang +2
The research of knowledge-driven conversational systems is largely limited due to the lack of dialog data which consist of multi-turn conversations on multiple topics and with know…
Recent Advances and Challenges in Task-oriented Dialog System
Zheng Zhang, Ryuichi Takanobu, Qi Zhu +2
Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academi…
CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
Qi Zhu, Kaili Huang, Zheng Zhang +2
To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cro…
CoTK: An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation
Fei Huang, Dazhen Wan, Zhihong Shao +5
In text generation evaluation, many practical issues, such as inconsistent experimental settings and metric implementations, are often ignored but lead to unfair evaluation and unt…
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
Qi Zhu, Zheng Zhang, Yan Fang +7
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and di…