Search Results for author: Zhao Cao

Found 36 papers, 23 papers with code

Visual Prompt Tuning for Few-Shot Text Classification

no code implementations COLING 2022 Jingyuan Wen, Yutian Luo, Nanyi Fei, Guoxing Yang, Zhiwu Lu, Hao Jiang, Jie Jiang, Zhao Cao

In few-shot text classification, a feasible paradigm for deploying VL-PTMs is to align the input samples and their category names via the text encoders.

Few-Shot Learning Few-Shot Text Classification +3

ICLEval: Evaluating In-Context Learning Ability of Large Language Models

1 code implementation21 Jun 2024 Wentong Chen, Yankai Lin, ZhenHao Zhou, HongYun Huang, Yantao Jia, Zhao Cao, Ji-Rong Wen

In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs.

In-Context Learning

An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models

no code implementations20 Mar 2024 Qi Liu, Gang Guo, Jiaxin Mao, Zhicheng Dou, Ji-Rong Wen, Hao Jiang, Xinyu Zhang, Zhao Cao

Based on these findings, we then propose several simple document pruning methods to reduce the storage overhead and compare the effectiveness of different pruning methods on different late-interaction models.


Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation

1 code implementation21 Dec 2023 Jiayu Lin, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei

The results show the competitiveness of our proposed framework and evaluator in counter-argument generation tasks.


IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions

no code implementations30 Nov 2023 Zhebin Zhang, Xinyu Zhang, Yuanhang Ren, Saijiang Shi, Meng Han, Yongkang Wu, Ruofei Lai, Zhao Cao

In this paper, we propose an Induction-Augmented Generation (IAG) framework that utilizes inductive knowledge along with the retrieved documents for implicit reasoning.

Knowledge Distillation RAG +2

Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection

no code implementations30 Aug 2023 Hongjin Qian, Zhicheng Dou, Jiejun Tan, Haonan Chen, Haoqi Gu, Ruofei Lai, Xinyu Zhang, Zhao Cao, Ji-Rong Wen

Previous methods use external knowledge as references for text generation to enhance factuality but often struggle with the knowledge mix-up(e. g., entity mismatch) of irrelevant references.

Decoder Text Generation

Alleviating the Long-Tail Problem in Conversational Recommender Systems

1 code implementation21 Jul 2023 Zhipeng Zhao, Kun Zhou, Xiaolei Wang, Wayne Xin Zhao, Fan Pan, Zhao Cao, Ji-Rong Wen

Conversational recommender systems (CRS) aim to provide the recommendation service via natural language conversations.

Diversity Recommendation Systems +1

Improving Conversational Recommendation Systems via Counterfactual Data Simulation

1 code implementation5 Jun 2023 Xiaolei Wang, Kun Zhou, Xinyu Tang, Wayne Xin Zhao, Fan Pan, Zhao Cao, Ji-Rong Wen

To develop our approach, we characterize user preference and organize the conversation flow by the entities involved in the dialogue, and design a multi-stage recommendation dialogue simulator based on a conversation flow language model.

counterfactual Data Augmentation +2

Plug-and-Play Document Modules for Pre-trained Models

1 code implementation28 May 2023 Chaojun Xiao, Zhengyan Zhang, Xu Han, Chi-Min Chan, Yankai Lin, Zhiyuan Liu, Xiangyang Li, Zhonghua Li, Zhao Cao, Maosong Sun

By inserting document plugins into the backbone PTM for downstream tasks, we can encode a document one time to handle multiple tasks, which is more efficient than conventional encoding-task coupling methods that simultaneously encode documents and input queries using task-specific encoders.

Question Answering

Generative Retrieval via Term Set Generation

1 code implementation23 May 2023 Peitian Zhang, Zheng Liu, Yujia Zhou, Zhicheng Dou, Fangchao Liu, Zhao Cao

On top of the term-set DocID, we propose a permutation-invariant decoding algorithm, with which the term set can be generated in any permutation yet will always lead to the corresponding document.

Information Retrieval Natural Questions +1

RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models

1 code implementation4 May 2023 Shitao Xiao, Zheng Liu, Yingxia Shao, Zhao Cao

It is designed to improve the quality of semantic representation where all contextualized embeddings of the pre-trained model can be leveraged.

Information Retrieval Open-Domain Question Answering +2

Constructing Tree-based Index for Efficient and Effective Dense Retrieval

1 code implementation24 Apr 2023 Haitao Li, Qingyao Ai, Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Zheng Liu, Zhao Cao

Unfortunately, while ANN can improve the efficiency of DR models, it usually comes with a significant price on retrieval performance.

Contrastive Learning Retrieval

EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction

1 code implementation21 Apr 2023 Zhen Tian, Ting Bai, Wayne Xin Zhao, Ji-Rong Wen, Zhao Cao

EulerNet converts the exponential powers of feature interactions into simple linear combinations of the modulus and phase of the complex features, making it possible to adaptively learn the high-order feature interactions in an efficient way.

Click-Through Rate Prediction

Rethinking Dense Retrieval's Few-Shot Ability

1 code implementation12 Apr 2023 Si Sun, Yida Lu, Shi Yu, Xiangyang Li, Zhonghua Li, Zhao Cao, Zhiyuan Liu, Deiming Ye, Jie Bao

Moreover, the dataset is disjointed into base and novel classes, allowing DR models to be continuously trained on ample data from base classes and a few samples in novel classes.


FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-training

1 code implementation CVPR 2023 Yunpeng Han, Lisai Zhang, Qingcai Chen, Zhijian Chen, Zhonghua Li, Jianxin Yang, Zhao Cao

We propose a method for fine-grained fashion vision-language pre-training based on fashion Symbols and Attributes Prompt (FashionSAP) to model fine-grained multi-modalities fashion attributes and characteristics.


WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus

1 code implementation10 Apr 2023 Hongjing Qian, Yutao Zhu, Zhicheng Dou, Haoqi Gu, Xinyu Zhang, Zheng Liu, Ruofei Lai, Zhao Cao, Jian-Yun Nie, Ji-Rong Wen

In this paper, we introduce a new NLP task -- generating short factual articles with references for queries by mining supporting evidence from the Web.

Retrieval Text Generation

Rethinking Label Smoothing on Multi-hop Question Answering

2 code implementations19 Dec 2022 Zhangyue Yin, Yuxin Wang, Xiannian Hu, Yiguang Wu, Hang Yan, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

Multi-Hop Question Answering (MHQA) is a significant area in question answering, requiring multiple reasoning components, including document retrieval, supporting sentence prediction, and answer span extraction.

Image Classification Machine Reading Comprehension +6

Multi-Modal Experience Inspired AI Creation

1 code implementation2 Sep 2022 Qian Cao, Xu Chen, Ruihua Song, Hao Jiang, Guang Yang, Zhao Cao

To model such human capabilities, in this paper, we define and solve a novel AI creation problem based on human experiences.

Text Generation

Enhancing User Behavior Sequence Modeling by Generative Tasks for Session Search

1 code implementation23 Aug 2022 Haonan Chen, Zhicheng Dou, Yutao Zhu, Zhao Cao, Xiaohua Cheng, Ji-Rong Wen

To help the encoding of the current user behavior sequence, we propose to use a decoder and the information of future sequences and a supplemental query.

Decoder Session Search

RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder

1 code implementation24 May 2022 Shitao Xiao, Zheng Liu, Yingxia Shao, Zhao Cao

The sentence embedding is generated from the encoder's masked input; then, the original sentence is recovered based on the sentence embedding and the decoder's masked input via masked language modeling.

Decoder Information Retrieval +7

Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering

1 code implementation ACL 2022 Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen

To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR).

Open-Domain Question Answering Passage Retrieval +1

KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models

no code implementations28 Feb 2022 Daniel Gao, Yantao Jia, Lei LI, Chengzhen Fu, Zhicheng Dou, Hao Jiang, Xinyu Zhang, Lei Chen, Zhao Cao

However, to figure out whether PLMs can be reliable knowledge sources and used as alternative knowledge bases (KBs), we need to further explore some critical features of PLMs.

General Knowledge Memorization +1

Towards More Effective and Economic Sparsely-Activated Model

no code implementations14 Oct 2021 Hao Jiang, Ke Zhan, Jianwei Qu, Yongkang Wu, Zhaoye Fei, Xinyu Zhang, Lei Chen, Zhicheng Dou, Xipeng Qiu, Zikai Guo, Ruofei Lai, Jiawen Wu, Enrui Hu, Yinxia Zhang, Yantao Jia, Fan Yu, Zhao Cao

To increase the number of activated experts without an increase in computational cost, we propose SAM (Switch and Mixture) routing, an efficient hierarchical routing mechanism that activates multiple experts in a same device (GPU).

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline

1 code implementation NAACL 2022 Xiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

ELUE is dedicated to depict the Pareto Frontier for various language understanding tasks, such that it can tell whether and how much a method achieves Pareto improvement.

YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker

no code implementations14 Sep 2021 Ruizhi Pu, Xinyu Zhang, Ruofei Lai, Zikai Guo, Yinxia Zhang, Hao Jiang, Yongkang Wu, Yantao Jia, Zhicheng Dou, Zhao Cao

Finally, supervisory signal in rear compressor is computed based on condition probability and thus can control sample dynamic and further enhance the model performance.

Document Ranking Information Retrieval +1

Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need

1 code implementation20 Aug 2021 Zhengyi Ma, Zhicheng Dou, Wei Xu, Xinyu Zhang, Hao Jiang, Zhao Cao, Ji-Rong Wen

In this paper, we propose to leverage the large-scale hyperlinks and anchor texts to pre-train the language model for ad-hoc retrieval.

Language Modelling Retrieval

Answer Complex Questions: Path Ranker Is All You Need

3 code implementations Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval 2021 Xinyu Zhang, Ke Zhan, Enrui Hu, Chengzhen Fu, Lan Luo, Hao Jiang, Yantao Jia, Fan Yu, Zhicheng Dou, Zhao Cao, Lei Chen

Currently, the most popular method for open-domain Question Answering (QA) adopts "Retriever and Reader" pipeline, where the retriever extracts a list of candidate documents from a large set of documents followed by a ranker to rank the most relevant documents and the reader extracts answer from the candidates.

Open-Domain Question Answering

Early Exiting with Ensemble Internal Classifiers

no code implementations28 May 2021 Tianxiang Sun, Yunhua Zhou, Xiangyang Liu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

In this paper, we show that a novel objective function for the training of the ensemble internal classifiers can be naturally induced from the perspective of ensemble learning and information theory.

Diversity Ensemble Learning

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