Related papers: Improving Document Representations by Generating P…

Semi-structured query systems for document-oriented databases have many real applications. One particular application that we are interested in is matching each financial receipt image with its corresponding place of interest (POI, e.g.,…

Models such as latent semantic analysis and those based on neural embeddings learn distributed representations of text, and match the query against the document in the latent semantic space. In traditional information retrieval models, on…

Dense embedding models are commonly deployed in commercial search engines, wherein all the document vectors are pre-computed, and near-neighbor search (NNS) is performed with the query vector to find relevant documents. However, the…

Ranking has always been one of the top concerns in information retrieval research. For decades, lexical matching signal has dominated the ad-hoc retrieval process, but it also has inherent defects, such as the vocabulary mismatch problem.…

Developing increasingly efficient and accurate algorithms for approximate nearest neighbor search is a paramount goal in modern information retrieval. A primary approach to addressing this question is clustering, which involves partitioning…

Similar question retrieval is a core task in community-based question answering (CQA) services. To balance the effectiveness and efficiency, the question retrieval system is typically implemented as multi-stage rankers: The first-stage…

Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized…

Accurately retrieving relevant bid keywords for user queries is critical in Sponsored Search but remains challenging, particularly for short, ambiguous queries. Existing dense and generative retrieval models often fail to capture nuanced…

Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these systems, their robustness is critical to avoid downstream…

Learning a high-dimensional dense representation for vocabulary terms, also known as a word embedding, has recently attracted much attention in natural language processing and information retrieval tasks. The embedding vectors are typically…

Recent research demonstrates the effectiveness of using pre-trained language models for legal case retrieval. Most of the existing works focus on improving the representation ability for the contextualized embedding of the [CLS] token and…

For a product of interest, we propose a search method to surface a set of reference products. The reference products can be used as candidates to support downstream modeling tasks and business applications. The search method consists of…

Similarity query is the family of queries based on some similarity metrics. Unlike the traditional database queries which are mostly based on value equality, similarity queries aim to find targets "similar enough to" the given data objects,…

Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus and compare these…

Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously inefficient in terms of resources and latency. We propose Fast-Forward indexes -- vector…

As user content and queries become increasingly multi-modal, the need for effective multi-modal search systems has grown. Traditional search systems often rely on textual and metadata annotations for indexed images, while multi-modal…

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…

Retrieving relevant documents from a corpus is typically based on the semantic similarity between the document content and query text. The inclusion of structural relationship between documents can benefit the retrieval mechanism by…