Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval最新文献_第3页

Quantum Language Model-based Query Expansion 基于量子语言模型的查询扩展

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3234970

Qiuchi Li, M. Melucci, P. Tiwari

引用次数: 9

Binary Classification Model Inspired from Quantum Detection Theory 基于量子探测理论的二元分类模型

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3234979

E. D. Buccio, Qiuchi Li, M. Melucci, P. Tiwari

{"title":"Binary Classification Model Inspired from Quantum Detection Theory","authors":"E. D. Buccio, Qiuchi Li, M. Melucci, P. Tiwari","doi":"10.1145/3234944.3234979","DOIUrl":"https://doi.org/10.1145/3234944.3234979","url":null,"abstract":"Despite its long history, classification is still a subject of extensive research because new application domains require more effective algorithms than the state-of-the-art classification algorithms, which rely on the logical theory of sets, the theory of probability and the algebra of vector spaces. The combination of distinct theoretical frameworks may be the key to making an important step forward toward a stable and significant improvement in classification effectiveness and, to the same extent improved Quantum Mechanics (QM) signal detection. QM may give rise to a new theoretical framework for classification, since it essentially moves the optimal bound of effectiveness beyond the levels made possible by the state-of-the-art classification algorithms. In this paper, we propose a binary classification model inspired by quantum detection theory in an effort to investigate how much benefit it brings as compared to classical models. Our experiments suggest that the improvement in classification effectiveness can be obtained, although the potential of quantum detection can only be partially exploited.","PeriodicalId":193631,"journal":{"name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130177313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 14

Entire Information Attentive GRU for Text Representation 文本表示的全信息关注GRU

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3234947

Guoxiu He, Wei Lu

引用次数: 7

Classifying Community QA Questions That Contain an Image 分类包含图像的社区QA问题

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3234948

Kenta Tamaki, Riku Togashi, Sosuke Kato, Sumio Fujita, Hideyuki Maeda, T. Sakai

引用次数: 4

A Vertical PRF Architecture for Microblog Search 微博搜索的垂直PRF架构

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3234960

Flávio Martins, João Magalhães, Jamie Callan

{"title":"A Vertical PRF Architecture for Microblog Search","authors":"Flávio Martins, João Magalhães, Jamie Callan","doi":"10.1145/3234944.3234960","DOIUrl":"https://doi.org/10.1145/3234944.3234960","url":null,"abstract":"In microblog retrieval, query expansion can be essential to obtain good search results due to the short size of queries and posts. Since information in microblogs is highly dynamic, an up-to-date index coupled with pseudo-relevance feedback (PRF) with an external corpus has a higher chance of retrieving more relevant documents and improving ranking. In this paper, we focus on the research question:how can we reduce the query expansion computational cost while maintaining the same retrieval precision as standard PRF? Therefore, we propose to accelerate the query expansion step of pseudo-relevance feedback. The hypothesis is that using an expansion corpus organized into verticals for expanding the query, will lead to a more efficient query expansion process and improved retrieval effectiveness. Thus, the proposed query expansion method uses a distributed search architecture and resource selection algorithms to provide an efficient query expansion process. Experiments on the TREC Microblog datasets show that the proposed approach can match or outperform standard PRF in MAP and NDCG@30, with a computational cost that is three orders of magnitude lower.","PeriodicalId":193631,"journal":{"name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131741725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Empirical Study of Multi-level Convolution Models for IR Based on Representations and Interactions 基于表征与交互的红外多尺度卷积模型实证研究

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3234954

Yifan Nie, Yanling Li, Jian-Yun Nie

引用次数: 23

An Extended Query Performance Prediction Framework Utilizing Passage-Level Information 利用通道级信息的扩展查询性能预测框架

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3234946

Haggai Roitman

引用次数: 14

Product Question Intent Detection using Indicative Clause Attention and Adversarial Learning 使用指示从句注意和对抗性学习的产品问题意图检测

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3234961

Qian Yu, Wai Lam

引用次数: 6

Understanding the Representational Power of Neural Retrieval Models Using NLP Tasks 利用NLP任务理解神经检索模型的表征能力

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3234959

Daniel Cohen, Brendan T. O'Connor, W. Bruce Croft

{"title":"Understanding the Representational Power of Neural Retrieval Models Using NLP Tasks","authors":"Daniel Cohen, Brendan T. O'Connor, W. Bruce Croft","doi":"10.1145/3234944.3234959","DOIUrl":"https://doi.org/10.1145/3234944.3234959","url":null,"abstract":"The ease of constructing effective neural networks has resulted in a large number of varying architectures iteratively improving performance on a task. Due to the nature of these models being black boxes, standard weight inspection is difficult. We propose a probe based methodology to evaluate what information is important or extraneous at each level of a network. We input natural language processing datasets into a trained answer passage neural network. Each layer of the neural network is used as input into a unique classifier, or probe, to correctly label that input with respect to a natural language processing task, probing the internal representations for information. Using this approach, we analyze the information relevant to retrieving answer passages from the perspective of information needed for part of speech tagging, named entity retrieval, sentiment classification, and textual entailment. We show a significant information need difference between two seemingly similar question answering collections, and demonstrate that passage retrieval and textual entailment share a common information space, while POS and NER information is used only at a compositional level in the lower layers of an information retrieval model. Lastly, we demonstrate that incorporating this information into a multitask environment is correlated to the information retained by these models during the probe inspection phase.","PeriodicalId":193631,"journal":{"name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129384086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

What Will Search Engines be Changed by NLP Advancements NLP的进步会改变搜索引擎吗

Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2018-09-10 DOI: 10.1145/3234944.3241521

M. Zhou

{"title":"What Will Search Engines be Changed by NLP Advancements","authors":"M. Zhou","doi":"10.1145/3234944.3241521","DOIUrl":"https://doi.org/10.1145/3234944.3241521","url":null,"abstract":"I think that the vision of a search engine is \"Natural Search\" with which users input his or her search intent in a natural way such as using natural language or an image and immediately obtains the desired accurate information which is concisely and comprehensibly expressed. During this process, NLP is undoubtedly one of the most crucial technologies. In the past, the search engine uses limited and shallow NLP technologies because NLP technology is not as mature as people have expected. In recent years, we have witnessed that NLP has made huge advances in various tasks such as semantic parser, question-answering, machine translation, machine reading comprehension and text generation. I think that now it is the time to consider applying these new technologies to a search engine to further improve the intelligence and naturalness of the search process. It is necessary to understand the new progress of NLP and their potential impact to a search engine. In this talk, I first provide an overview of advancements of methodology and technology in NLP filed in recent years. Then I will share my thoughts about the promising change of search engines brought by these new NLP technologies. I will further elaborate my thoughts on changing search engine with a set of intelligent question-answering techniques comprising semantic parser, question-answering and machine reading comprehension. Although these new promising NLP have rapidly brought meaningful change to a search engine, there are still many problems unsolved. As a conclusion, a list of the challenging topics will be proposed with my initial thoughts of solutions.","PeriodicalId":193631,"journal":{"name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131842254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1