Related papers: Ultron: An Ultimate Retriever on Corpus with a Mod…
To extract answers from a large corpus, open-domain question answering (QA) systems usually rely on information retrieval (IR) techniques to narrow the search space. Standard inverted index methods such as TF-IDF are commonly used as thanks…
Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…
Differentiable Search Indices (DSIs) encode a corpus of documents in model parameters and use the same model to answer user queries directly. Despite the strong performance of DSI models, deploying them in situations where the corpus…
Research and industry are rapidly advancing the innovation and adoption of foundation model-based systems, yet the tools for managing these models have not kept pace. Understanding the provenance and lineage of models is critical for…
Starting from an unsolved problem of information retrieval this paper presents an ontology-based model for indexing and retrieval. The model combines the methods and experiences of cognitive-to-interpret indexing languages with the…
Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual embedding models with supervised rerankers to achieve…
In this paper, we propose DEXTER, an end to end system to extract information from tables present in medical health documents, such as electronic health records (EHR) and explanation of benefits (EOB). DEXTER consists of four sub-system…
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…
Document retrieval has been an important research problem over many years in the information retrieval community. State-of-the-art techniques utilize various methods in matching documents to a given document including keywords, phrases, and…
Recent studies have proposed leveraging Large Language Models (LLMs) as information retrievers through query rewriting. However, for challenging corpora, we argue that enhancing queries alone is insufficient for robust semantic matching;…
The similarity between the question and indexed documents is a crucial factor in document retrieval for retrieval-augmented question answering. Although this is typically the only method for obtaining the relevant documents, it is not the…
Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of recently proposed DR…
A core interest in building Artificial Intelligence (AI) agents is to let them interact with and assist humans. One example is Dynamic Search (DS), which models the process that a human works with a search engine agent to accomplish a…
Information Extraction from visually rich documents is a challenging task that has gained a lot of attention in recent years due to its importance in several document-control based applications and its widespread commercial value. The…
We address the task of ranking objects (such as people, blogs, or verticals) that, unlike documents, do not have direct term-based representations. To be able to match them against keyword queries, evidence needs to be amassed from…
Generative retrieval (GR) directly predicts the identifiers of relevant documents (i.e., docids) based on a parametric model. It has achieved solid performance on many ad-hoc retrieval tasks. So far, these tasks have assumed a static…
Unsupervised domain adaptation generalizes neural retrievers to an unseen domain by generating pseudo queries on target domain documents. The quality and efficiency of this adaptation critically depend on which documents are selected for…
Dense retrieval has become a prominent method to obtain relevant context or world knowledge in open-domain NLP tasks. When we use a learned dense retriever on a retrieval corpus at inference time, an often-overlooked design choice is the…
Reading comprehension models are based on recurrent neural networks that sequentially process the document tokens. As interest turns to answering more complex questions over longer documents, sequential reading of large portions of text…
Code retrieval aims to provide users with desired code snippets based on users' natural language queries. With the development of deep learning technologies, adopting pre-trained models for this task has become mainstream. Considering the…