Related papers: Ultron: An Ultimate Retriever on Corpus with a Mod…
This paper introduces a deep learning model tailored for document information analysis, emphasizing document classification, entity relation extraction, and document visual question answering. The proposed model leverages transformer-based…
Deep Research systems have revolutionized how LLMs solve complex questions through iterative reasoning and evidence gathering. However, current systems remain fundamentally constrained to textual web data, overlooking the vast knowledge…
Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents. Most recent…
Question answering is one of the most important and difficult applications at the border of information retrieval and natural language processing, especially when we talk about complex science questions which require some form of inference…
Over the past few decades, the amount of scientific articles and technical literature has increased exponentially in size. Consequently, there is a great need for systems that can ingest these documents at scale and make their content…
Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…
Because of the increasing number of electronic data, designing efficient tools to retrieve and exploit documents is a major challenge. Current search engines suffer from two main drawbacks: there is limited interaction with the list of…
Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ an array of document…
Understanding documents with rich layouts is an essential step towards information extraction. Business intelligence processes often require the extraction of useful semantic content from documents at a large scale for subsequent…
Generative retrieval constitutes an innovative approach in information retrieval, leveraging generative language models (LM) to generate a ranked list of document identifiers (docid) for a given query. It simplifies the retrieval pipeline…
Document parsing is essential for analyzing complex document structures and extracting fine-grained information, supporting numerous downstream applications. However, existing methods often require integrating multiple independent models to…
Generative retrieval shed light on a new paradigm of document retrieval, aiming to directly generate the identifier of a relevant document for a query. While it takes advantage of bypassing the construction of auxiliary index structures,…
Existing summarization systems mostly generate summaries purely relying on the content of the source document. However, even for humans, we usually need some references or exemplars to help us fully understand the source document and write…
Information retrieval involves selecting artifacts from a corpus that are most relevant to a given search query. The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and…
The extraction of relevant information carried out by named entities in handwriting documents is still a challenging task. Unlike traditional information extraction approaches that usually face text transcription and named entity…
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…
Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended to…
We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved items is a combinatorial optimization problem, generally…
Universal Information Extraction~(Universal IE) aims to solve different extraction tasks in a uniform text-to-structure generation manner. Such a generation procedure tends to struggle when there exist complex information structures to be…
Retrieving relevant contexts from a large corpus is a crucial step for tasks such as open-domain question answering and fact checking. Although neural retrieval outperforms traditional methods like tf-idf and BM25, its performance degrades…