检索结果-内蒙古大学图书馆

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Yunchang Pang, Liang Lan, Yanyan Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Cas University of Chinese Academy of Sciences Beijing China Data Intelligence System Research Center Institute of Computing Technology Cas Beijing China Institute for Ai Industry Research Tsinghua University Beijing China Cas Key Lab of Network Data Science and Technology Institute of Computing Technology Cas University of Chinese Academy of Sciences Beijing China

Pseudo-relevance feedback (PRF) has proven to be an effective query reformulation technique to improve retrieval accuracy. It aims to alleviate the mismatch of linguistic expressions between a query and its potential relevant documents. Existing PRF methods independently treat revised queries originating from the same query but using different numbers of feedback documents, resulting in severe query drift. Without comparing the effects of two different revisions from the same query, a PRF model may incorrectly focus on the additional irrelevant information increased in the more feedback, and thus reformulate a query that is less effective than the revision using the less feedback. Ideally, if a PRF model can distinguish between irrelevant and relevant information in the feedback, the more feedback documents there are, the better the revised query will be. To bridge this gap, we propose the Loss-over-Loss (LoL) framework to compare the reformulation losses between different revisions of the same query during training. Concretely, we revise an original query multiple times in parallel using different amounts of feedback and compute their reformulation losses. Then, we introduce an additional regularization loss on these reformulation losses to penalize revisions that use more feedback but gain larger losses. With such comparative regularization, the PRF model is expected to learn to suppress the extra increased irrelevant information by comparing the effects of different revised queries. Further, we present a differentiable query reformulation method to implement this framework. This method revises queries in the vector space and directly optimizes the retrieval performance of query vectors, applicable for both sparse and dense retrieval models. Empirical evaluation demonstrates the effectiveness and robustness of our method for two typical sparse and dense retrieval models. © 2022, CC BY.

关键词： Feedback

An In-Context Schema Understanding Method for Knowledge Base Question Answering

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yantao Li, Zixuan Jin, Xiaolong Guo, Yucao Bai, Long Guan, Saiping Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

The Knowledge Base Question Answering (KBQA) task aims to answer natural language questions based on a given knowledge base. Recently, Large Language Models (LLMs) have shown strong capabilities in language understanding and can be used to solve this task. In doing so, a major challenge for LLMs is to overcome the immensity and heterogeneity of knowledge base schemas. Existing methods bypass this challenge by initially employing LLMs to generate drafts of logic forms without schema-specific details. Then, an extra module is used to inject schema information to these drafts. In contrast, in this paper, we propose a simple In-Context Schema Understanding (ICSU) method that enables LLMs to directly understand schemas by leveraging in-context learning. Specifically, ICSU provides schema information to LLMs using schema-related annotated examples. We investigate three example retrieval strategies based on raw questions, anonymized questions, and generated SPARQL queries. Experimental results show that ICSU demonstrates competitive performance compared to baseline methods on both the KQA Pro and WebQSP datasets. © 2023, CC BY.

关键词： Knowledge based systems

Social evolutionary games

学校读者我要写书评

暂无评论

Social evolutionary games

International Conference on Game Theory for networks, GameNets

作者： Jianye Yu Yuanzhuo Wang Xiao!ong Jin Xueqi Cheng CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

In this paper, we introduce a framework of social evolutionary games (SEG) for investigating the evolution of social networks. In a SEG, a coevolutionary mechanism is adopted by agents who aim to improve his short-term utility and long-term reputation. Two examples are presented to demonstrate SEG, prisoner's dilemma game for pairwise interaction and public goods game for group interaction. Numerical simulations are performed on the two examples with different parameter settings, and the results indicates that SEG can be used as a metaphor for investigating the evolution of social networks in some scenarios.

关键词： Microscopy

How to use open-pFind in deep proteomics data analysis?—A protocol for rigorous identification and quantitation of peptides and proteins from mass spectrometry data

学校读者我要写书评

暂无评论

Biophysics Reports 2021年第3期7卷 207-226页

作者： Guangcan Shao Yong Cao Zhenlin Chen Chao Liu Shangtong Li Hao Chi Meng-Qiu Dong School of Life Sciences Peking University National Institute of Biological Sciences Beijing Tsinghua Institute of Multidisciplinary Biomedical Research Tsinghua University Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) University of CASInstitute of Computing TechnologyCAS University of Chinese Academy of Sciences Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Medicine and EngineeringBeihang University

High-throughput proteomics based on mass spectrometry（MS） analysis has permeated biomedical science and propelled numerous research projects. p Find 3 is a database search engine for high-speed and in-depth proteomics data analysis. p Find 3 features a swift open search workflow that is adept at uncovering less obvious information such as unexpected modifications or mutations that would have gone unnoticed using a conventional data analysis pipeline. In this protocol, we provide step-by-step instructions to help users mastering various types of data analysis using p Find 3 in conjunction with p Parse for data pre-processing and if needed, p Quant for quantitation. This streamlined p Parse-p Findp Quant workflow offers exceptional sensitivity, precision, and speed. It can be easily implemented in any laboratory in need of identifying peptides, proteins, or post-translational modifications, or of quantitation based on15N-labeling, SILAC-labeling, or TMT/i TRAQ labeling.

关键词： Mass spectrometry Protein identification Search engine Open-pFind Quantitation

PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Chen Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China University of Amsterdam Netherlands

Neural ranking models (NRMs) have shown remarkable success in recent years, especially with pre-trained language models. However, deep neural models are notorious for their vulnerability to adversarial examples. Adversarial attacks may become a new type of web spamming technique given our increased reliance on neural information retrieval models. Therefore, it is important to study potential adversarial attacks to identify vulnerabilities of NRMs before they are deployed. In this paper, we introduce the Word Substitution Ranking Attack (WSRA) task against NRMs, which aims to promote a target document in rankings by adding adversarial perturbations to its text. We focus on the decision-based black-box attack setting, where the attackers cannot directly get access to the model information, but can only query the target model to obtain the rank positions of the partial retrieved list. This attack setting is realistic in real-world search engines. We propose a novel Pseudo Relevance-based ADversarial ranking Attack method (PRADA) that learns a surrogate model based on Pseudo Relevance Feedback (PRF) to generate gradients for finding the adversarial perturbations. Experiments on two web search benchmark datasets show that PRADA can outperform existing attack strategies and successfully fool the NRM with small indiscernible perturbations of text. Copyright © 2022, The Authors. All rights reserved.

关键词： Search engines

A Unified Causal View of Instruction Tuning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Lu Huang, Wei Zhang, Ruqing Chen, Wei Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Instruction tuning on a mixture of tasks has improved zero-shot capabilities in natural language processing (NLP) . Nevertheless, existing methods often learn features that exhibit correlations between instruction-formatted samples and target labels, rather than causal relationships. Termed as "spurious correlation" in statistics, such a correlation may change drastically in a new task, making the effect from the learned features to be misleading. To this end, we develop a meta Structural Causal Model (meta-SCM) to integrate different NLP tasks under a single causal structure of the data. Specifically, the meta-SCM introduces multiple latent factors that represent properties of source context, only some of which causally influence the target labels for a specific task. The key idea is to learn task-required causal factors and only use those to make predictions for a given task. Theoretically, we prove the causal factor can be identified without mixing information from others. Guided by the identifiability, we propose a Structural Instruction Tuning (SIT) method to learn the task-required causal representations that can mimic the causal factors for each task. The utility of our approach is verified by improvements of zero-shot ability on a range of unseen datasets and tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

Aceso: Efficient Parallel DNN Training through Iterative Bottleneck Alleviation 24

学校读者我要写书评

暂无评论

Aceso: Efficient Parallel DNN Training through Iterative Bot...

19th European Conference on Computer Systems, EuroSys 2024

作者： Liu, Guodong Miao, Youshan Lin, Zhiqi Shi, Xiaoxiang Maleki, Saeed Yang, Fan Bao, Yungang Wang, Sa State Key Lab of Processors Institute of Computing Technology Cas Univ. of Chinese Academy of Sciences China Microsoft Research United States University of Science and Technology of China China Shanghai Jiao Tong University China

ISBN: (纸本)9798400704376

Many parallel mechanisms, including data parallelism, tensor parallelism, and pipeline parallelism, have been proposed and combined together to support training increasingly large deep neural networks (DNN) on massive GPU devices. Given a DNN model and GPU cluster, finding the optimal configuration by combining these parallelism mechanisms is an NP-hard problem. Widely adopted mathematical programming approaches have been proposed to search in a configuration subspace, but they are still too costly when scaling to large models over numerous devices. Aceso is a scalable parallel-mechanism auto-configuring system that operates iteratively. For a given parallel configuration, Aceso identifies a performance bottleneck and then, by summarizing all possible configuration adjustments with their resource consumption changes, infers their performance impacts to the bottleneck and selects one that mitigates the bottleneck. This process repeats for many iterations until a desired final configuration is found. Unlike mathematical programming approaches that examine the configurations subspace to find the optimal solution, Aceso searches in the configuration space in a stochastic approach by repeatedly identifying and alleviating bottlenecks. Aceso significantly reduces configuration searching cost by taking the approach of resolving one bottleneck at a time. This allows Aceso to find configurations that would be usually missed in subspace search approaches. We implemented and tested Aceso on representative DNN models. Evaluations show that it can scale to 1K-layer models. Compared to state-of-the-art systems, Aceso achieves up to 1.33× throughput improvement with less than 5% of the searching cost. © 2024 ACM.

关键词： Deep neural networks

Continual domain adaptation for machine reading comprehension

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Su, Lixin Guo, Jiafeng Zhang, Ruqing Fan, Yixing Lan, Yanyan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China China University of Chinese Academy of Sciences Beijing China

Machine reading comprehension (MRC) has become a core component in a variety of natural language processing (NLP) applications such as question answering and dialogue systems. It becomes a practical challenge that an MRC model needs to learn in non-stationary environments, in which the underlying data distribution changes over time. A typical scenario is the domain drift, i.e. different domains of data come one after another, where the MRC model is required to adapt to the new domain while maintaining previously learned ability. To tackle such a challenge, in this work, we introduce the Continual Domain Adaptation (CDA) task for MRC. So far as we know, this is the first study on the continual learning perspective of MRC. We build two benchmark datasets for the CDA task, by re-organizing existing MRC collections into different domains with respect to context type and question type, respectively. We then analyze and observe the catastrophic forgetting (CF) phenomenon of MRC under the CDA setting. To tackle the CDA task, we propose several BERT-based continual learning MRC models using either regularization-based methodology or dynamic-architecture paradigm. We analyze the performance of different continual learning MRC models under the CDA task and show that the proposed dynamic-architecture based model achieves the best performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Memory architecture

L2R2: Leveraging ranking for abductive reasoning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhu, Yunchang Pang, Liang Lan, Yanyan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China China University of Chinese Academy of Sciences Beijing China

The abductive natural language inference task (αNLI) is proposed to evaluate the abductive reasoning ability of a learning system. In the αNLI task, two observations are given and the most plausible hypothesis is asked to pick out from the candidates. Existing methods simply formulate it as a classification problem, thus a cross-entropy log-loss objective is used during training. However, discriminating true from false does not measure the plausibility of a hypothesis, for all the hypotheses have a chance to happen, only the probabilities are different. To fill this gap, we switch to a ranking perspective that sorts the hypotheses in order of their plausibilities. With this new perspective, a novel L2R2 approach is proposed under the learning-to-rank framework. Firstly, training samples are reorganized into a ranking form, where two observations and their hypotheses are treated as the query and a set of candidate documents respectively. Then, an ESIM model or pre-trained language model, e.g. BERT or RoBERTa, is obtained as the scoring function. Finally, the loss functions for the ranking task can be either pair-wise or list-wise for training. The experimental results on the ART dataset reach the state-of-the-art on the public leaderboard. © 2020, CC BY.

关键词： Learning systems