Search Results for author: Keqing He

Found 47 papers, 28 papers with code

A Finer-grain Universal Dialogue Semantic Structures based Model For Abstractive Dialogue Summarization

no code implementations Findings (EMNLP) 2021 Yuejie Lei, Fujia Zheng, Yuanmeng Yan, Keqing He, Weiran Xu

Although abstractive summarization models have achieved impressive results on document summarization tasks, their performance on dialogue modeling is much less satisfactory due to the crude and straight methods for dialogue encoding.

Abstractive Dialogue Summarization Abstractive Text Summarization +1

Adversarial Semantic Decoupling for Recognizing Open-Vocabulary Slots

no code implementations EMNLP 2020 Yuanmeng Yan, Keqing He, Hong Xu, Sihong Liu, Fanyu Meng, Min Hu, Weiran Xu

Open-vocabulary slots, such as file name, album name, or schedule title, significantly degrade the performance of neural-based slot filling models since these slots can take on values from a virtually unlimited set and have no semantic restriction nor a length limit.

Sentence slot-filling +1

Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection

no code implementations27 Feb 2024 Pei Wang, Keqing He, Yejie Wang, Xiaoshuai Song, Yutao Mou, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu

Out-of-domain (OOD) intent detection aims to examine whether the user's query falls outside the predefined domain of the system, which is crucial for the proper functioning of task-oriented dialogue (TOD) systems.

Intent Detection Transfer Learning

PreAct: Predicting Future in ReAct Enhances Agent's Planning Ability

1 code implementation18 Feb 2024 Dayuan Fu, Jianzhao Huang, Siyuan Lu, Guanting Dong, Yejie Wang, Keqing He, Weiran Xu

Addressing the discrepancies between predictions and actual outcomes often aids individuals in expanding their thought processes and engaging in reflection, thereby facilitating reasoning in the correct direction.

Language Modelling Large Language Model

Knowledge Editing on Black-box Large Language Models

1 code implementation13 Feb 2024 Xiaoshuai Song, Zhengyang Wang, Keqing He, Guanting Dong, Yutao Mou, Jinxu Zhao, Weiran Xu

Knowledge editing (KE) aims to efficiently and precisely modify the behavior of large language models (LLMs) to update specific knowledge without negatively influencing other knowledge.

knowledge editing

What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning

1 code implementation25 Dec 2023 Wei Liu, Weihao Zeng, Keqing He, Yong Jiang, Junxian He

We present deita (short for Data-Efficient Instruction Tuning for Alignment), a series of models fine-tuned from LLaMA and Mistral models using data samples automatically selected with our proposed approach.

APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection

no code implementations20 Oct 2023 Pei Wang, Keqing He, Yutao Mou, Xiaoshuai Song, Yanan Wu, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu

Detecting out-of-domain (OOD) intents from user queries is essential for a task-oriented dialogue system.

Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT

1 code implementation16 Oct 2023 Xiaoshuai Song, Keqing He, Pei Wang, Guanting Dong, Yutao Mou, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu

The tasks of out-of-domain (OOD) intent discovery and generalized intent discovery (GID) aim to extend a closed intent classifier to open-world intent sets, which is crucial to task-oriented dialogue (TOD) systems.

In-Context Learning Intent Discovery

Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task

1 code implementation10 Oct 2023 Guanting Dong, Jinxu Zhao, Tingfeng Hui, Daichi Guo, Wenlong Wan, Boqi Feng, Yueyan Qiu, Zhuoma Gongque, Keqing He, Zechen Wang, Weiran Xu

To address these challenges, we propose a unified robustness evaluation framework based on the slot-filling task to systematically evaluate the dialogue understanding capability of LLMs in diverse input perturbation scenarios.

Data Augmentation Dialogue Understanding +3

Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations

no code implementations5 Oct 2023 Jiachi Liu, LiWen Wang, Guanting Dong, Xiaoshuai Song, Zechen Wang, Zhengyang Wang, Shanglin Lei, Jinzheng Zhao, Keqing He, Bo Xiao, Weiran Xu

The proposed dataset contains five types of human-annotated noise, and all those noises are exactly existed in real extensive robust-training methods of slot filling into the proposed framework.

slot-filling Slot Filling

Generative Zero-Shot Prompt Learning for Cross-Domain Slot Filling with Inverse Prompting

1 code implementation6 Jul 2023 Xuefeng Li, LiWen Wang, Guanting Dong, Keqing He, Jinzheng Zhao, Hao Lei, Jiachi Liu, Weiran Xu

Zero-shot cross-domain slot filling aims to transfer knowledge from the labeled source domain to the unlabeled target domain.

slot-filling Slot Filling

Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation

1 code implementation17 Jun 2023 Weihao Zeng, Lulu Zhao, Keqing He, Ruotong Geng, Jingang Wang, Wei Wu, Weiran Xu

In this paper, we explore the compositional generalization for multi-attribute controllable dialogue generation where a model can learn from seen attribute values and generalize to unseen combinations.

Attribute Dialogue Generation +1

GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model

1 code implementation11 Jun 2023 Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Yang Yang, Hongyin Tang, Keqing He, Jiahao Liu, Jingang Wang, Shu Zhao, Peng Zhang, Jie Tang

Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices.

General Knowledge Knowledge Distillation +1

Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery

1 code implementation28 May 2023 Yutao Mou, Xiaoshuai Song, Keqing He, Chen Zeng, Pei Wang, Jingang Wang, Yunsen Xian, Weiran Xu

Previous methods suffer from a coupling of pseudo label disambiguation and representation learning, that is, the reliability of pseudo labels relies on representation learning, and representation learning is restricted by pseudo labels in turn.

Intent Discovery Pseudo Label +1

A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition

no code implementations27 Feb 2023 Guanting Dong, Zechen Wang, LiWen Wang, Daichi Guo, Dayuan Fu, Yuxiang Wu, Chen Zeng, Xuefeng Li, Tingfeng Hui, Keqing He, Xinyue Cui, QiXiang Gao, Weiran Xu

Specifically, we decouple class-specific prototypes and contextual semantic prototypes by two masking strategies to lead the model to focus on two different semantic information for inference.

Contrastive Learning few-shot-ner +4

Revisit Out-Of-Vocabulary Problem for Slot Filling: A Unified Contrastive Frameword with Multi-level Data Augmentations

no code implementations27 Feb 2023 Daichi Guo, Guanting Dong, Dayuan Fu, Yuxiang Wu, Chen Zeng, Tingfeng Hui, LiWen Wang, Xuefeng Li, Zechen Wang, Keqing He, Xinyue Cui, Weiran Xu

In real dialogue scenarios, the existing slot filling model, which tends to memorize entity patterns, has a significantly reduced generalization facing Out-of-Vocabulary (OOV) problems.

Contrastive Learning slot-filling +1

UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning

1 code implementation19 Oct 2022 Yutao Mou, Pei Wang, Keqing He, Yanan Wu, Jingang Wang, Wei Wu, Weiran Xu

Specifically, we design a K-nearest neighbor contrastive learning (KNCL) objective for representation learning and introduce a KNN-based scoring function for OOD detection.

Contrastive Learning Out of Distribution (OOD) Detection +2

Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning

no code implementations17 Oct 2022 Yanan Wu, Zhiyuan Zeng, Keqing He, Yutao Mou, Pei Wang, Yuanmeng Yan, Weiran Xu

In this paper, we propose a simple but strong energy-based score function to detect OOD where the energy scores of OOD samples are higher than IND samples.

Intent Detection Out of Distribution (OOD) Detection

Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery

1 code implementation17 Oct 2022 Yutao Mou, Keqing He, Pei Wang, Yanan Wu, Jingang Wang, Wei Wu, Weiran Xu

For OOD clustering stage, we propose a KCC method to form compact clusters by mining true hard negative samples, which bridges the gap between clustering and representation learning.

Clustering Contrastive Learning +3

Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems

1 code implementation17 Oct 2022 Weihao Zeng, Keqing He, Zechen Wang, Dayuan Fu, Guanting Dong, Ruotong Geng, Pei Wang, Jingang Wang, Chaobo Sun, Wei Wu, Weiran Xu

Recent advances in neural approaches greatly improve task-oriented dialogue (TOD) systems which assist users to accomplish their goals.

Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation

1 code implementation COLING 2022 Yanan Wu, Zhiyuan Zeng, Keqing He, Yutao Mou, Pei Wang, Weiran Xu

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.

Out of Distribution (OOD) Detection

Unified Knowledge Prompt Pre-training for Customer Service Dialogues

no code implementations31 Aug 2022 Keqing He, Jingang Wang, Chaobo Sun, Wei Wu

In this paper, we propose a novel unified knowledge prompt pre-training framework, UFA (\textbf{U}nified Model \textbf{F}or \textbf{A}ll Tasks), for customer service dialogues.

Natural Language Understanding Text Generation

Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization

1 code implementation NAACL 2022 Lulu Zhao, Fujia Zheng, Weihao Zeng, Keqing He, Weiran Xu, Huixing Jiang, Wei Wu, Yanan Wu

The most advanced abstractive dialogue summarizers lack generalization ability on new domains and the existing researches for domain adaptation in summarization generally rely on large-scale pre-trainings.

Domain Adaptation

TODSum: Task-Oriented Dialogue Summarization with State Tracking

no code implementations25 Oct 2021 Lulu Zhao, Fujia Zheng, Keqing He, Weihao Zeng, Yuejie Lei, Huixing Jiang, Wei Wu, Weiran Xu, Jun Guo, Fanyu Meng

Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues, while summarization datasets for the broadly used task-oriented dialogue haven't been explored yet.

Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack

1 code implementation NAACL 2021 LiWen Wang, Yuanmeng Yan, Keqing He, Yanan Wu, Weiran Xu

In this paper, we propose an adversarial disentangled debiasing model to dynamically decouple social bias attributes from the intermediate representations trained on the main task.

Adversarial Attack Representation Learning

DAN-SNR: A Deep Attentive Network for Social-Aware Next Point-of-Interest Recommendation

1 code implementation25 Apr 2020 Liwei Huang, Yutao Ma, Yanbo Liu, Keqing He

In particular, the DAN-SNR makes use of the self-attention mechanism instead of the architecture of recurrent neural networks to model sequential influence and social influence in a unified manner.

Cannot find the paper you are looking for? You can Submit a new open access paper.