According to the probability ranking principle, the document set with the highest values of probability of relevance optimizes information retrieval effectiveness given the probabilities are estimated as accurately as possible. The key point of this principle is the separation of the document set into two subsets with a given level of fallout and with the highest recall. If subsets of set measures are replaced by subspaces and space measures, we obtain an alternative theory stemming from Quantum Theory. That theory is named after vector probability because vectors represent event like sets do in classical probability. The paper shows that the separation into vector subspaces is more effective than the separation into subsets with the same available evidence. The result is proved mathematically and verified experimentally. In general, the paper suggests that quantum theory is not only a source of rhetoric inspiration, but is a sufficient condition to improve retrieval effectiveness in a principled way.
Middle East Technical University（中东技术大学）；University of Amsterdam（阿姆斯特丹大学）
The vocabulary mismatch problem is a long-standing problem in information retrieval. Semantic matching holds the promise of solving the problem. Recent advances in language technology have given rise to unsupervised neural models for learning representations of words as well as bigger textual units. Such representations enable powerful semantic matching methods. This survey is meant as an introduction to the use of neural models for semantic matching. To remain focused we limit ourselves to web search. We detail the required background and terminology, a taxonomy grouping the rapidly growing b…
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；Université Pierre et Marie Curie（皮埃尔和玛丽·居里大学）；Image & Pervasive Access Lab, UMI CNRS 2955（法国国家科学研究中心2955联合研究单元图像与普适访问实验室）
This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval. We propose DeepHash: a hashing scheme based on deep networks. Key to making DeepHash work at extremely low bitrates are three important considerations -- regularization, depth and fine-tuning -- each requiring solutions specific to the hashing problem. In-depth evaluation shows that our scheme consistently outperforms state-of-the-art methods across all data sets for both Fisher Vectors and Deep Convolutional Neural Network features, by up to 20 …
The paper presents our design of a next generation information retrieval system based on tag co-occurrences and subsequent clustering. We help users getting access to digital data through information visualization in the form of tag clusters. Current problems like the absence of interactivity and semantics between tags or the difficulty of adding additional search arguments are solved. In the evaluation, based upon SERVQUAL and IT systems quality indicators, we found out that tag clusters are perceived as more useful than tag clouds, are much more trustworthy, and are more enjoyable to use.
Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）
Getting an overview over the legal domain has become challenging, especially in a broad, international context. Legal question answering systems have the potential to alleviate this task by automatically retrieving relevant legal texts for a specific statement and checking whether the meaning of the statement can be inferred from the found documents. We investigate a combination of the BM25 scoring method of Elasticsearch with word embeddings trained on English translations of the German and Japanese civil law. For this, we define criteria which select a dynamic number of relevant documents ac…
Getting relevant information from search engines has been the heart of research works in information retrieval. Query expansion is a retrieval technique that has been studied and proved to yield positive results in relevance. Users are required to express their queries as a shortlist of words, sentences, or questions. With this short format, a huge amount of information is lost in the process of translating the information need from the actual query size since the user cannot convey all his thoughts in a few words. This mostly leads to poor query representation which contributes to undesired r…
Search engine has become a fundamental component in various web and mobile applications. Retrieving relevant documents from the massive datasets is challenging for a search engine system, especially when faced with verbose or tail queries. In this paper, we explore a vector space search framework for document retrieval. Specifically, we trained a deep semantic matching model so that each query and document can be encoded as a low dimensional embedding. Our model was trained based on BERT architecture. We deployed a fast k-nearest-neighbor index service for online serving. Both offline and onli…
On most sponsored search platforms, advertisers bid on some keywords for their advertisements (ads). Given a search request, ad retrieval module rewrites the query into bidding keywords, and uses these keywords as keys to select Top N ads through inverted indexes. In this way, an ad will not be retrieved even if queries are related when the advertiser does not bid on corresponding keywords. Moreover, most ad retrieval approaches regard rewriting and ad-selecting as two separated tasks, and focus on boosting relevance between search queries and ads. Recently, in e-commerce sponsored search more…
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 inde…
The task of expert finding has been getting increasing attention in information retrieval literature. However, the current state-of-the-art is still lacking in principled approaches for combining different sources of evidence. This paper explores the usage of unsupervised rank aggregation methods as a principled approach for combining multiple estimators of expertise, derived from the textual contents, from the graph-structure of the citation patterns for the community of experts, and from profile information about the experts. We specifically experimented two unsupervised rank aggregation app…
Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces
Stanford University（斯坦福大学）；IBM Research AI（IBM研究院AI部门）
Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks. Unfortunately, some dimensions of this progress are illusory: the majority of the popular IR benchmarks today focus exclusively on downstream task accuracy and thus conceal the costs incurred by systems that trade away efficiency for quality. Latency, hardware cost, and other efficiency considerations are paramount to the deployment of IR systems in user-facing settings. We propose that IR benchmarks structure their evaluation methodology…
Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
National Engineering Research Center for Software Engineering, Peking University（软件工程国家工程研究中心，北京大学）；City University of Hong Kong（香港城市大学）；Tencent Technology（腾讯科技）；Peking University（北京大学）
Nanjing Tech University（南京工业大学）；Jinling Institute of Technology（金陵科技学院）；Beihang University（北京航空航天大学）
Given a natural language description, text-based person retrieval aims to identify images of a target person from a large-scale person image database. Existing methods generally face a \textbf{color over-reliance problem}, which means that the models rely heavily on color information when matching cross-modal data. Indeed, color information is an important decision-making accordance for retrieval, but the over-reliance on color would distract the model from other key clues (e.g. texture information, structural information, etc.), and thereby lead to a sub-optimal retrieval performance. To solv…
Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering
Institute of Computing and Intelligence, Harbin Institute of Technology (Shenzhen)（计算与智能研究院，哈尔滨工业大学（深圳））；Shenzhen Loop Area Institute (SLAI)（深圳环形区研究院（SLAI））
Beyond Global Similarity: Towards Fine-Grained, Multi-Condition Multimodal Retrieval
Shanghai Jiao Tong University（上海交通大学）；Institute of Digital Twin, Eastern Institute of Technology（数字孪生研究院，东部技术研究所）；Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative（宁波空间智能与数字衍生关键实验室）
