Related papers: Ranked Document Retrieval in (Almost) No Space
An indexed sequence of strings is a data structure for storing a string sequence that supports random access, searching, range counting and analytics operations, both for exact matches and prefix search. String sequences lie at the core of…
Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…
We engineer a self-index based retrieval system capable of rank-safe evaluation of top-k queries. The framework generalizes the GREEDY approach of Culpepper et al. (ESA 2010) to handle multi-term queries, including over phrases. We propose…
Most approaches for similar text retrieval and ranking with long natural language queries rely at some level on queries and responses having words in common with each other. Recent applications of transformer-based neural language models to…
Large-scale embedding-based retrieval (EBR) is the cornerstone of search-related industrial applications. Given a user query, the system of EBR aims to identify relevant information from a large corpus of documents that may be tens or…
Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organize sentence…
Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval. The reason may be the complexity of the…
This paper presents a robust and comprehensive graph-based rank aggregation approach, used to combine results of isolated ranker models in retrieval tasks. The method follows an unsupervised scheme, which is independent of how the isolated…
Text indexing is a classical algorithmic problem that has been studied for over four decades: given a text $T$, pre-process it off-line so that, later, we can quickly count and locate the occurrences of any string (the query pattern) in $T$…
In the real world, documents are organized in different formats and varied modalities. Traditional retrieval pipelines require tailored document parsing techniques and content extraction modules to prepare input for indexing. This process…
We give a practical random mapping that takes any set of documents represented as vectors in Euclidean space and then maps them to a sparse subset of the Hamming cube while retaining ordering of inter-vector inner products. Once represented…
We present a new universal source code for distributions of unlabeled binary and ordinal trees that achieves optimal compression to within lower order terms for all tree sources covered by existing universal codes. At the same time, it…
Rank fusion is a powerful technique that allows multiple sources of information to be combined into a single result set. However, to date fusion has not been regarded as being cost-effective in cases where strict per-query efficiency…
Document retrieval enables users to find their required documents accurately and quickly. To satisfy the requirement of retrieval efficiency, prevalent deep neural methods adopt a representation-based matching paradigm, which saves online…
Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity…
With the fast growth of the Internet, more and more information is available on the Web. The Semantic Web has many features which cannot be handled by using the traditional search engines. It extracts metadata for each discovered Web…
This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), "Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access". The goal of the task is to generate…
In web search, typically a candidate generation step selects a small set of documents---from collections containing as many as billions of web pages---that are subsequently ranked and pruned before being presented to the user. In Bing, the…
Bit vectors are fundamental building blocks of many succinct data structures. They can be used to represent graphs, are an important part of many text indices in the form of the wavelet tree, and can be used to encode ordered sequences of…
An essential task of most Question Answering (QA) systems is to re-rank the set of answer candidates, i.e., Answer Sentence Selection (A2S). These candidates are typically sentences either extracted from one or more documents preserving…