检索结果-内蒙古大学图书馆

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Chen, Yimeng Lan, Yanyan Xiong, Ruibin Pang, Liang Ma, Zhiming Cheng, Xueqi University of Chinese Academy of Sciences China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS China Academy of Mathematics and Systems Science CAS China

ISBN: (纸本)9780999241165

Embedding-based evaluation measures have shown promising improvements on the correlation with human judgments in natural language generation. In these measures, various intrinsic metrics are used in the computation, including generalized precision, recall, F-score and the earth mover's distance. However, the relations between these metrics are unclear, making it difficult to determine which measure to use in real applications. In this paper, we provide an in-depth study on the relations between these metrics. Inspired by the optimal transportation theory, we prove that these metrics correspond to the optimal transport problem with different hard marginal constraints. However, these hard marginal constraints may cause the problem of incomplete and noisy matching in the evaluation process. Therefore we propose a family of new evaluation metrics, namely Lazy Earth Mover's Distances, based on the more general unbalanced optimal transport problem. Experimental results on WMT18 and WMT19 show that our proposed metrics have the ability to produce more consistent evaluation results with human judgements, as compared with existing intrinsic metrics. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Modeling topical relevance for multi-turn dialogue generation 29

Modeling topical relevance for multi-turn dialogue generatio...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Zhang, Hainan Lan, Yanyan Pang, Liang Chen, Hongshen Ding, Zhuoye Yin, Dawei CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS China *** Beijing China University of Chinese Academy of Sciences China

ISBN: (纸本)9780999241165

Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention weights are computed based on the topic representation of each context. Finally, the attention weights and the topic distribution are utilized in the decoding process to generate the corresponding responses. Experimental results on both Chinese customer services data and English Ubuntu dialogue data show that STAR-BTM significantly outperforms several state-of-the-art methods, in terms of both metric-based and human evaluations. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

Neural or statistical: An empirical study on language models for Chinese input recommendation on mobile 23rd

Neural or statistical: An empirical study on language models...

引用

23rd China conference on Information Retrieval, CCIR 2017

作者： Zhang, Hainan Lan, Yanyan Guo, Jiafeng Xu, Jun Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783319686981

Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications. The fundamental problem is to predict the conditional probability of the next word given the sequence of previous words. Therefore, statistical language models, i.e.n-grams based models, have been extensively used on this task in real application. However, the characteristics of extremely different typing behaviors usually lead to serious sparsity problem, even n-gram with smoothing will fail. A reasonable approach to tackle this problem is to use the recently proposed neural models, such as probabilistic neural language model, recurrent neural network and word2vec. They can leverage more semantically similar words for estimating the probability. However, there is no conclusion on which approach of the two will work better in real application. In this paper, we conduct an extensive empirical study to show the differences between statistical and neural language models. The experimental results show that the two different approach have individual advantages, and a hybrid approach will bring a significant improvement. © Springer International Publishing AG 2017.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Beyond Precision: A Study on Recall of Initial Retrieval with Neural Representations 1

引用

28th China Conference on Information Retrieval, CCIR 2022

作者： Xiao, Yan Fan, Yixing Zhang, Ruqing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (数字)9783031247552

ISBN: (纸本)9783031247545

Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural representations have shown great success in capturing semantic relatedness, leading to new possibilities to alleviate the vocabulary mismatch problem in IR. However, most existing efforts in this direction have been devoted to the re-ranking stage. That is to leverage neural representations to help re-rank a set of candidate documents, which are typically obtained from an initial retrieval stage based on some symbolic index and search scheme (e.g., BM25 over the inverted index). This naturally raises a question: if the relevant documents have not been found in the initial retrieval stage due to vocabulary mismatch, there would be no chance to re-rank them to the top positions later. Therefore, in this paper, we study the problem how to employ neural representations to improve the recall of relevant documents in the initial retrieval stage. Specifically, to meet the efficiency requirement of the initial stage, we introduce a neural index for the neural representations of documents, and propose two hybrid search schemes based on both neural and symbolic indices, namely the parallel search scheme and the sequential search scheme. Our experiments show that both hybrid index and search schemes can improve the recall of the initial retrieval stage with small overhead. © 2023, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Academic access data analysis for literature recommendation 23rd

Academic access data analysis for literature recommendation

引用

23rd China conference on Information Retrieval, CCIR 2017

作者： Fan, Yixing Guo, Jiafeng Lan, Yanyan Xu, Jun Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783319686981

Academic reading plays an important role in researchers’ daily life. To alleviate the burden of seeking relevant literature from rapidly growing academic repository, different kinds of recommender systems have been introduced in recent years. However, most existing work focused on adopting traditional recommendation techniques, like content-based filtering or collaborative filtering, in the literature recommendation scenario. Little work has yet been done on analyzing the academic reading behaviors to understand the reading patterns and information needs of real-world academic users, which would be a foundation for improving existing recommender systems or designing new ones. In this paper, we aim to tackle this problem by carrying out empirical analysis over large scale academic access data, which can be viewed as a proxy of academic reading behaviors. We conduct global, group-based and sequence-based analysis to address the following questions: (1) Are there any regularities in users’ academic reading behaviors? (2) Will users with different levels of activeness exhibit different information needs? (3) How to correlate one’s future demands with his/her historical behaviors? By answering these questions, we not only unveil useful patterns and strategies for literature recommendation, but also identify some challenging problems for future development. © Springer International Publishing AG 2017.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Understanding and Improving Neural Ranking Models from a Term Dependence View 15th

Understanding and Improving Neural Ranking Models from a Ter...

引用

15th Asia Information Retrieval Societies Conference, AIRS 2019

作者： Fan, Yixing Guo, Jiafeng Lan, Yanyan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783030428341

Recently, neural information retrieval (NeuIR) has attracted a lot of interests, where a variety of neural models have been proposed for the core ranking problem. Beyond the continuous refresh of the state-of-the-art neural ranking performance, the community calls for more analysis and understanding of the emerging neural ranking models. In this paper, we attempt to analyze these new models from a traditional view, namely term dependence. Without loss of generality, most existing neural ranking models could be categorized into three categories with respect to their underlying assumption on query term dependence, i.e., independent models, dependent models, and hybrid models. We conduct rigorous empirical experiments over several representative models from these three categories on a benchmark dataset and a large click-through dataset. Interestingly, we find that no single type of model can achieve a consistent win over others on different search queries. An oracle model which can select the right model for each query can obtain significant performance improvement. Based on the analysis we introduce an adaptive strategy for neural ranking models. We hypothesize that the term dependence in a query could be measured through the divergence between its independent and dependent representations. We thus propose a dependence gate based on such divergence representation to softly select neural ranking models for each query accordingly. Experimental results verify the effectiveness of the adaptive strategy. © Springer Nature Switzerland AG 2020.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Generative Retrieval Meets Multi-Graded Relevance 38

Generative Retrieval Meets Multi-Graded Relevance

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Tang, Yubao Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Chen, Wei Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS China University of Chinese Academy of Sciences China University of Amsterdam Netherlands

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches are limited to scenarios with binary relevance data, overlooking the potential for documents to have multi-graded relevance. Extending generative retrieval to accommodate multi-graded relevance poses challenges, including the need to reconcile likelihood probabilities for docid pairs and the possibility of multiple relevant documents sharing the same identifier. To address these challenges, we introduce a framework called GRaded Generative Retrieval (GR2). GR2 focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training. First, we create identifiers that are both semantically relevant and sufficiently distinct to represent individual documents effectively. This is achieved by jointly optimizing the relevance and distinctness of docids through a combination of docid generation and autoencoder models. Second, we incorporate information about the relationship between relevance grades to guide the training process. We use a constrained contrastive training strategy to bring the representations of queries and the identifiers of their relevant documents closer together, based on their respective relevance grades. Extensive experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A rejection sampling algorithm for off-centered discrete Gaussian distributions over the integers

引用

science China(Information sciences) 2019年第3期62卷 196-198页

作者： Yusong DU Baodian WEI Huang ZHANG School of Data and Computer Science Sun Yat-sen University Guangdong Key Laboratory of Information Security Technology Chongqing Key Lab of Computer Network and Communication Technology

Dear editor,Discrete Gaussian sampling, that is, sampling from a discrete Gaussian distribution DΛ,σ,cwith parameter σ> 0 and center c∈R~n over an ndimensional lattice Λ, has been considered by the cryptography research community as one of the fundamental building blocks of lattice-based cryptography [1, 2]. The simplest lattice is the one-

关键词： A rejection sampling algorithm for off-centered discrete Gaussian distributions over the integers

来源：评论

学校读者我要写书评

暂无评论

Sparse Word Embeddings Using 1 Regularized Online Learning

Sparse Word Embeddings Using 1 Regularized Online Learning

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Sun, Fei Guo, Jiafeng Lan, Yanyan Xu, Jun Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

Recently, Word2Vec tool has attracted a lot of interest for its promising performances in a variety of natural language processing (NLP) tasks. However, a critical issue is that the dense word representations learned in Word2Vec are lacking of interpretability. It is natural to ask if one could improve their interpretability while keeping their performances. Inspired by the success of sparse models in enhancing interpretability, we propose to introduce sparse constraint into Word2Vec. Specifically, we take the Continuous Bag of Words (CBOW) model as an example in our study and add the l regularizer into its learning objective. One challenge of optimization lies in that stochastic gradient descent (SGD) cannot directly produce sparse solutions with 1 regularizer in online training. To solve this problem, we employ the Regularized Dual Averaging (RDA) method, an online optimization algorithm for regularized stochastic learning. In this way, the learning process is very efficient and our model can scale up to very large corpus to derive sparse word representations. The proposed model is evaluated on both expressive power and interpretability. The results show that, compared with the original CBOW model, the proposed model can obtain state-of-the-art results with better interpretability using less than 10% non-zero elements. © 2016 International Joint Conferences on Artificial Intelligence. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

ICTNET at TREC 2019 Deep Learning Track 28

ICTNET at TREC 2019 Deep Learning Track

引用

28th Text REtrieval Conference, TREC 2019

作者： Chen, Jiangui Cai, Yinqiong Jiang, Haoquan University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology China

We participated in the Deep Learning Track at TREC 2019. We built a ranking system which combines a search component based on BM25 and a semantic matching component using pretraining knowledge. Our best run achieves NDCG@10 of 0.6650, MAP of 0.2035. © 2019 28th Text REtrieval Conference, TREC 2019 - Proceedings. All Rights Reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：