检索结果-内蒙古大学图书馆

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

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

ICTNET at Trec 2019 Incident Streams Track 28

ICTNET at Trec 2019 Incident Streams Track

引用

28th Text REtrieval Conference, TREC 2019

作者： Guangsheng, Kuang Kun, Zhang Jiabao, Zhang Xin, Zheng University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology China

Social medial become our public ways to share our information in our lives. Crisis management via social medial is becoming indispensable for its tremendous information. While deep learning shows surprising outcome in many tasks. So in this paper, we cope this learning task with neural network in the view of classification problem. © 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

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 News Track 28

ICTNET at TREC 2019 News Track

引用

28th Text REtrieval Conference, TREC 2019

作者： Ding, Yuyang Lian, Xiaoying Zhou, Houquan Liu, Zhaoge Ding, Hanxing Hou, Zhongni University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology China

This paper describes our work in the background linking task and entity ranking task in TREC 2018 News Track. We explore four methods in background linking task and two methods in entity ranking task. All of our methods largely rely on off-the-shell open-source components(e.g., Solr for indexing the documents), and follow the basic thoughts-BM25 and relevance feedback. These methods differ in how they analyze the given input to obtain a query and to what extent the returned results are re-ranked taking meta data of the document(e.g., publish dates) into account. © 2019 28th Text REtrieval Conference, TREC 2019 - Proceedings. All Rights Reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ICTNET at TREC 2019 Complex Answer Retrieval Track 28

ICTNET at TREC 2019 Complex Answer Retrieval Track

引用

28th Text REtrieval Conference, TREC 2019

作者： Ren, Hongfei Xiong, Ruibin Zeng, Yutao 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 participate in the Complex Answer Retrieval(CAR) track at TREC 2019. We applied several useful models in this work. In the rough ranking, we applied doc2query model to predict queries and retrieve using BM25. In the re-ranking, we submitted 5 different runs which use 5 different models, include BM25, DRMMTKS, Bert-DRMMTKS, Bert-ConvKNRM and Bert-ConvKNRM-50, to try to get the best result. © 2019 28th Text REtrieval Conference, TREC 2019 - Proceedings. All Rights Reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Virtual node based adaptive routing in wireless ad hoc networks

引用

中国高等学校学术文摘·计算机科学 2009年第4期3卷 535-542页

作者： Gang LI Hongmei SUN Key Lab of Network Science and Technology Institute of Computing TechnologyChinese Academy of SciencesBeijing 100080China Communications Technology Lab Intel China Research CenterBeijing 100080China

It is a challenge to make the routes quickly adapt to the changed network topology when nodes fail in a wireless ad hoc *** this paper,we propose an adaptive routing protocol,which groups the network nodes into virtual nodes according to their data transfer capabilities and creates virtual-node-based *** protocol can accommodate the routes to node failures by adaptively updating the virtual nodes and just-in-time using available nodes during data *** simulations indicate that the proposed protocol can keep the routes failed-node-free when the available virtual node members cover the failed nodes scattering area.

关键词： wireless ad hoc networks mobile ad hoc networks route protocols adaptability route repair

来源：评论

学校读者我要写书评

暂无评论

Evaluating natural language generation via unbalanced optimal transport 29

Evaluating natural language generation via unbalanced optima...

引用

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

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense 38

CausalDiff: Causality-Inspired Disentanglement via Diffusion...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Mingkun Bi, Keping Chen, Wei Chen, Quanrun Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China Key Laboratory of Network Data Science and Technology Institute of Computing Technology CAS China School of Statistics University of International Business and Economics China

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://***/cas-AISafetyBasicResearchGroup/CausalDiff. © 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

Match-SRNN: Modeling the recursive matching structure with spatial RNN 25

Match-SRNN: Modeling the recursive matching structure with s...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Wan, Shengxian Lan, Yanyan Xu, Jun Guo, Jiafeng Pang, Liang Xueqi, Cheng 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

Semantic matching, which aims to determine the matching degree between two texts, is a fundamental problem for many NLP applications. Recently, deep learning approach has been applied to this problem and significant improvements have been achieved. In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i.e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position. Based on this idea, we propose a novel deep architecture, namely Match-SRNN, to model the recursive matching structure. Firstly, a tensor is constructed to capture the word level interactions. Then a spatial RNN is applied to integrate the local interactions recursively, with importance determined by four types of gates. Finally, the matching score is calculated based on the global interaction. We show that, after degenerated to the exact matching scenario, Match-SRNN can approximate the dynamic programming process of longest common subsequence. Thus, there exists a clear interpretation for Match-SRNN. Our experiments on two semantic matching tasks showed the effectiveness of Match-SRNN, and its ability of visualizing the learned matching structure.

关键词： Dynamic programming

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：