When Should Queries Be Decomposed? A Stage-Aware Study of Query Decomposition for Multi-Condition Retrieval
Eastern Institute of Technology, Ningbo（宁波东方理工学院）；Shanghai Jiao Tong University（上海交通大学）；Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin（浙江省工业智能与数字孪生重点实验室）
Multi-condition retrieval requires systems to identify documents that satisfy multiple distinct constraints, moving beyond mere topical relevance. While query decomposition is widely adopted as an intuitive remedy, its effectiveness across different retrieval pipeline stages remains underexplored. In this paper, we conduct a stage-aware empirical study and uncover a stark, stage-dependent effect: decomposition during initial retrieval frequently harms retrieval performance due to semantic dilution, yet substantially improves reranking by enabling more fine-grained constraint verification. Motivated by these insights, we propose a principled Stage-Aware Decomposition framework that retains the monolithic query during initial retrieval to preserve global semantic context, while employing sub-queries exclusively during reranking for fine-grained constraint matching. Extensive evaluations on the MultiConIR and SSRB benchmarks demonstrate that our framework consistently improves ranking performance for compositional queries across multiple retrieval and reranking models. We release our code at https://github.com/EIT-NLP/Query-Decompose.
Creating alternative queries, also known as query suggestion, has been proved to be helpful on improving users' search experience. Owing to the suggestions, users could retrieve their information need more quickly and accurately. In many scenarios, these suggestions could be generated from the click-through logs by establishing a bipartite graph of the clicked query-document pairs. Most of the existing methods focused on click-existing queries which possess clicked information in the search logs, to suggest related queries using the co-clicked documents. In this paper, we propose a simple yet …
Specific to Math Information Retrieval is combining text with mathematical formulae both in documents and in queries. Rigorous evaluation of query expansion and merging strategies combining math and standard textual keyword terms in a query are given. It is shown that techniques similar to those known from textual query processing may be applied in math information retrieval as well, and lead to a cutting edge performance. Striping and merging partial results from subqueries is one technique that improves results measured by information retrieval evaluation metrics like Bpref.
Query expansion is a functionality of search engines that suggests a set of related queries for a user-issued keyword query. Typical corpus-driven keyword query expansion approaches return popular words in the results as expanded queries. Using these approaches, the expanded queries may correspond to a subset of possible query semantics, and thus miss relevant results. To handle ambiguous queries and exploratory queries, whose result relevance is difficult to judge, we propose a new framework for keyword query expansion: we start with clustering the results according to user specified granular…
Effective information disclosure in the context of databases with a large conceptual schema is known to be a non-trivial problem. In particular the formulation of ad-hoc queries is a major problem in such contexts. Existing approaches for tackling this problem include graphical query interfaces, query by navigation, query by construction, and point to point queries. In this report we propose an adoption of the query by navigation mechanism that is especially geared towards the InfoAssistant product. Query by navigation is based on ideas from the information retrieval world, in particular on th…
Translating verbose information needs into crisp search queries is a phenomenon that is ubiquitous but hardly understood. Insights into this process could be valuable in several applications, including synthesizing large privacy-friendly query logs from public Web sources which are readily available to the academic research community. In this work, we take a step towards understanding query formulation by tapping into the rich potential of community question answering (CQA) forums. Specifically, we sample natural language (NL) questions spanning diverse themes from the Stack Exchange platform,…
Query autocompletions help users of search engines to speed up their searches by recommending completions of partially typed queries in a drop down box. These recommended query autocompletions are usually based on large logs of queries that were previously entered by the search engine's users. Therefore, misinformation entered -- either accidentally or purposely to manipulate the search engine -- might end up in the search engine's recommendations, potentially harming organizations, individuals, and groups of people. This paper proposes an alternative approach for generating query autocompleti…
Search engine retrieval effectiveness studies are usually small-scale, using only limited query samples. Furthermore, queries are selected by the researchers. We address these issues by taking a random representative sample of 1,000 informational and 1,000 navigational queries from a major German search engine and comparing Google's and Bing's results based on this sample. Jurors were found through crowdsourcing, data was collected using specialised software, the Relevance Assessment Tool (RAT). We found that while Google outperforms Bing in both query types, the difference in the performance …
Query suggestion refers to the task of suggesting relevant and related queries to a search engine user to help in query formulation process and to expedite information retrieval with minimum amount of effort. It is highly useful in situations where the search requirements are not well understood and hence it has been widely adopted by search engines to guide users' search activity. For news websites, user queries have a time sensitive nature inherent in them. When some new event happens, there is a sudden burst in queries related to that event and such queries are sustained over a period of ti…
Typically, search engines provide query suggestions to assist users in the search process. Query suggestions are very important for improving users search experience. However, most query suggestions are based on the user's search logs, and they can be influenced by infrequently searched queries. Depending on the user's query, query suggestions can be ineffective in global search engines but effective in a domestic search engine. Conversely, it can be effective in global engines and weak in domestic engines. In addition, log-based query suggestions require many search logs, which makes them dif…
The vocabulary mismatch problem is one of the important challenges facing traditional keyword-based Information Retrieval Systems. The aim of query expansion (QE) is to reduce this query-document mismatch by adding related or synonymous words or phrases to the query. Several existing query expansion algorithms have proved their merit, but they are not uniformly beneficial for all kinds of queries. Our long-term goal is to formulate methods for applying QE techniques tailored to individual queries, rather than applying the same general QE method to all queries. As an initial step, we have propo…
Inability of the naive users to formulate appropriate queries is a fundamental problem in web search engines. Therefore, assisting users to issue more effective queries is an important way to improve users' happiness. One effective approach is query reformulation, which generates new effective queries according to the current query issued by users. Previous researches typically generate words and phrases related to the original query. Since the definition of query reformulation is quite general, it is completely difficult to develop a uniform term-based approach for this problem. This paper us…
We propose a method to protect the privacy of search engine users by decomposing the queries using semantically \emph{related} and unrelated \emph{distractor} terms. Instead of a single query, the search engine receives multiple decomposed query terms. Next, we reconstruct the search results relevant to the original query term by aggregating the search results retrieved for the decomposed query terms. We show that the word embeddings learnt using a distributed representation learning method can be used to find semantically related and distractor query terms. We derive the relationship between …
Keyword search against structured databases has become a popular topic of investigation, since many users find structured queries too hard to express, and enjoy the freedom of a ``Google-like'' query box into which search terms can be entered. Attempts to address this problem face a fundamental dilemma. Database querying is based on the logic of predicate evaluation, with a precisely defined answer set for a given query. On the other hand, in an information retrieval approach, ranked query results have long been accepted as far superior to results based on boolean query evaluation. As a conseq…
Query recommendations in search engines is a double edged sword, with undeniable benefits but potential of harm. Identifying unsafe queries is necessary to protect users from inappropriate query suggestions. However, identifying these is non-trivial because of the linguistic diversity resulting from large vocabularies, social-group-specific slang and typos, and because the inappropriateness of a term depends on the context. Here we formulate the problem as query-set expansion, where we are given a small and potentially biased seed set and the aim is to identify a diverse set of semantically re…
We propose a domain-independent framework for searching and retrieving facts and relationships within natural language text sources. In this framework, an extraction task over a text collection is expressed as a query that combines text fragments with wild cards, and the query result is a set of facts in the form of unary, binary and general $n$-ary tuples. A significance of our querying mechanism is that, despite being both simple and declarative, it can be applied to a wide range of extraction tasks. A problem in querying natural language text though is that a user-specified query may not re…
This short paper deals with the combination and comparison of two data sources: Search engine results and query suggestions for 16 terms related to political candidates and parties. The data was collected before the federal election in Germany in September 2017 for a period of two months. The rank biased overlap (RBO) statistic is used to measure the similarity of the top-weighted rankings. For each search term and for both the search results and query auto-completions we study the stability of the rankings over time.
ConvGQR: Generative Query Reformulation for Conversational Search
University of Montreal（蒙特利尔大学）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）
Query categorization is an essential part of query intent understanding in e-commerce search. A common query categorization task is to select the relevant fine-grained product categories in a product taxonomy. For frequent queries, rich customer behavior (e.g., click-through data) can be used to infer the relevant product categories. However, for more rare queries, which cover a large volume of search traffic, relying solely on customer behavior may not suffice due to the lack of this signal. To improve categorization of rare queries, we adapt the Pseudo-Relevance Feedback (PRF) approach to ut…
Computing similarity between a query and a document is fundamental in any information retrieval system. In search engines, computing query-document similarity is an essential step in both retrieval and ranking stages. In eBay search, document is an item and the query-item similarity can be computed by comparing different facets of the query-item pair. Query text can be compared with the text of the item title. Likewise, a category constraint applied on the query can be compared with the listing category of the item. However, images are one signal that are usually present in the items but are n…
For complex data types such as multimedia, traditional data management methods are not suitable. Instead of attribute matching approaches, access methods based on object similarity are becoming popular. Recently, this resulted in an intensive research of indexing and searching methods for the similarity-based retrieval. Nowadays, many efficient methods are already available, but using them to build an actual search system still requires specialists that tune the methods and build the system manually. Several attempts have already been made to provide a more convenient high-level interface in a…
We focus on the problem of query rewriting for sponsored search. We base rewrites on a historical click graph that records the ads that have been clicked on in response to past user queries. Given a query q, we first consider Simrank as a way to identify queries similar to q, i.e., queries whose ads a user may be interested in. We argue that Simrank fails to properly identify query similarities in our application, and we present two enhanced version of Simrank: one that exploits weights on click graph edges and another that exploits ``evidence.'' We experimentally evaluate our new schemes agai…
As research interest surges, vector similarity search is applied in multiple fields, including data mining, computer vision, and information retrieval. {Given a set of objects (e.g., a set of images) and a query object, we can easily transform each object into a feature vector and apply the vector similarity search to retrieve the most similar objects. However, the original vector similarity search cannot well support \textit{hybrid queries}, where users not only input unstructured query constraint (i.e., the feature vector of query object) but also structured query constraint (i.e., the desir…
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
The availability of large-scale datasets has driven the development of neural models that create generic summaries from single or multiple documents. In this work we consider query focused summarization (QFS), a task for which training data in the form of queries, documents, and summaries is not readily available. We propose to decompose QFS into (1) query modeling (i.e., finding supportive evidence within a set of documents for a query) and (2) conditional language modeling (i.e., summary generation). We introduce MaRGE, a Masked ROUGE Regression framework for evidence estimation and ranking …
Multi-hop logical reasoning is an established problem in the field of representation learning on knowledge graphs (KGs). It subsumes both one-hop link prediction as well as other more complex types of logical queries. Existing algorithms operate only on classical, triple-based graphs, whereas modern KGs often employ a hyper-relational modeling paradigm. In this paradigm, typed edges may have several key-value pairs known as qualifiers that provide fine-grained context for facts. In queries, this context modifies the meaning of relations, and usually reduces the answer set. Hyper-relational que…
Most of the existing information retrieval systems are based on bag of words model and are not equipped with common world knowledge. Work has been done towards improving the efficiency of such systems by using intelligent algorithms to generate search queries, however, not much research has been done in the direction of incorporating human-and-society level knowledge in the queries. This paper is one of the first attempts where such information is incorporated into the search queries using Wikipedia semantics. The paper presents an essential shift from conventional token based queries to conce…
