47 citations · 178 across the 19 of their papers we have counts for
19 papers
UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning
Yutao Mou, Pei Wang, Keqing He +4
Detecting out-of-domain (OOD) intents from user queries is essential for avoiding wrong operations in task-oriented dialogue systems. The key challenge is how to distinguish in-dom…
Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery
Yutao Mou, Keqing He, Pei Wang +4
Discovering out-of-domain (OOD) intent is important for developing new skills in task-oriented dialogue systems. The key challenges lie in how to transfer prior in-domain (IND) kno…
Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning
Yanan Wu, Zhiyuan Zeng, Keqing He +4
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. Traditional softmax-based confidence scores are susceptible to the…
PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling
Guanting Dong, Daichi Guo, Liwen Wang +10
Most existing slot filling models tend to memorize inherent patterns of entities and corresponding contexts from training data. However, these models can lead to system failure or…
Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation
Yanan Wu, Zhiyuan Zeng, Keqing He +3
Out-of-Domain (OOD) detection is a key component in a task-oriented dialog system, which aims to identify whether a query falls outside the predefined supported intent set. Previou…
Generalized Intent Discovery: Learning from Open World Dialogue System
Yutao Mou, Keqing He, Yanan Wu +6
Traditional intent classification models are based on a pre-defined intent set and only recognize limited in-domain (IND) intent classes. But users may input out-of-domain (OOD) qu…
A Robust Contrastive Alignment Method For Multi-Domain Text Classification
Xuefeng Li, Hao Lei, Liwen Wang +5
Multi-domain text classification can automatically classify texts in various scenarios. Due to the diversity of human languages, texts with the same label in different domains may…
Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization
Lulu Zhao, Fujia Zheng, Weihao Zeng +5
The most advanced abstractive dialogue summarizers lack generalization ability on new domains and the existing researches for domain adaptation in summarization generally rely on l…
InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER
Liwen Wang, Rumei Li, Yang Yan +4
Recently, prompt-based methods have achieved significant performance in few-shot learning scenarios by bridging the gap between language model pre-training and fine-tuning for down…
TODSum: Task-Oriented Dialogue Summarization with State Tracking
Lulu Zhao, Fujia Zheng, Keqing He +7
Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues, while summarization datasets for the broadly used task-oriented dialogue haven't been explo…
Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling
Liwen Wang, Xuefeng Li, Jiachi Liu +3
Zero-shot cross-domain slot filling alleviates the data dependence in the case of data scarcity in the target domain, which has aroused extensive research. However, as most of the…
Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System
Yanan Wu, Zhiyuan Zeng, Keqing He +4
Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set. In the practical application, a reliable dialogue system should know what…
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning
Zhiyuan Zeng, Keqing He, Yuanmeng Yan +5
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is to learn discriminative semant…
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer
Yuanmeng Yan, Rumei Li, Sirui Wang +3
Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on…
Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
Pengda Qin, Xin Wang, Wenhu Chen +3
Large-scale knowledge graphs (KGs) are shown to become more important in current information systems. To expand the coverage of KGs, previous studies on knowledge graph completion…
Finding Salient Context based on Semantic Matching for Relevance Ranking
Yuanyuan Qi, Jiayue Zhang, Weiran Xu +1
In this paper, we propose a salient-context based semantic matching method to improve relevance ranking in information retrieval. We first propose a new notion of salient context a…
DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction
Pengda Qin, Weiran Xu, William Yang Wang
Distant supervision can effectively label data for relation extraction, but suffers from the noise labeling problem. Recent works mainly perform soft bag-level noise reduction stra…
Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning
Pengda Qin, Weiran Xu, William Yang Wang
Distant supervision has become the standard method for relation extraction. However, even though it is an efficient method, it does not come at no cost---The resulted distantly-sup…
PrisCrawler: A Relevance Based Crawler for Automated Data Classification from Bulletin Board
Pu Yang, Jun Guo, Weiran Xu
Nowadays people realize that it is difficult to find information simply and quickly on the bulletin boards. In order to solve this problem, people propose the concept of bulletin b…