Contextual Document Embeddings

• URL: http://arxiv.org/abs/2410.02525v3
• Date: Fri, 18 Oct 2024 17:18:24 GMT
• Title: Contextual Document Embeddings
• Authors: John X. Morris, Alexander M. Rush,
• Abstract summary: We propose two complementary methods for contextualized document embeddings. First, an alternative contrastive learning objective that explicitly incorporates the document neighbors into the intra-batch contextual loss. Second, a new contextual architecture that explicitly encodes neighbor document information into the encoded representation.
• Score: 77.22328616983417
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dense document embeddings are central to neural retrieval. The dominant paradigm is to train and construct embeddings by running encoders directly on individual documents. In this work, we argue that these embeddings, while effective, are implicitly out-of-context for targeted use cases of retrieval, and that a contextualized document embedding should take into account both the document and neighboring documents in context - analogous to contextualized word embeddings. We propose two complementary methods for contextualized document embeddings: first, an alternative contrastive learning objective that explicitly incorporates the document neighbors into the intra-batch contextual loss; second, a new contextual architecture that explicitly encodes neighbor document information into the encoded representation. Results show that both methods achieve better performance than biencoders in several settings, with differences especially pronounced out-of-domain. We achieve state-of-the-art results on the MTEB benchmark with no hard negative mining, score distillation, dataset-specific instructions, intra-GPU example-sharing, or extremely large batch sizes. Our method can be applied to improve performance on any contrastive learning dataset and any biencoder.

Related papers

• Unified Multi-Modal Interleaved Document Representation for Information Retrieval [57.65409208879344]
  We produce more comprehensive and nuanced document representations by holistically embedding documents interleaved with different modalities. Specifically, we achieve this by leveraging the capability of recent vision-language models that enable the processing and integration of text, images, and tables into a unified format and representation.
  arXiv  Detail & Related papers  (2024-10-03T17:49:09Z)
• Cross-Modal Entity Matching for Visually Rich Documents [4.8119678510491815]
  Visually rich documents utilize visual cues to augment their semantics. Existing works that enable structured querying on these documents do not take this into account. We propose Juno -- a cross-modal entity matching framework to address this limitation.
  arXiv  Detail & Related papers  (2023-03-01T18:26:14Z)
• Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval [79.37614949970013]
  We propose a new dense retrieval model which learns diverse document representations with deep query interactions. Our model encodes each document with a set of generated pseudo-queries to get query-informed, multi-view document representations.
  arXiv  Detail & Related papers  (2022-08-08T16:00:55Z)
• TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents [51.744527199305445]
  This paper proposes a unified end-to-end information extraction framework from visually rich documents. Text reading and information extraction can reinforce each other via a well-designed multi-modal context block. The framework can be trained in an end-to-end trainable manner, achieving global optimization.
  arXiv  Detail & Related papers  (2022-07-14T08:52:07Z)
• Contextualization for the Organization of Text Documents Streams [0.0]
  We present several experiments with some stream analysis methods to explore streams of text documents. We use only dynamic algorithms to explore, analyze, and organize the flux of text documents.
  arXiv  Detail & Related papers  (2022-05-30T22:25:40Z)
• Unified Pretraining Framework for Document Understanding [52.224359498792836]
  We present UDoc, a new unified pretraining framework for document understanding. UDoc is designed to support most document understanding tasks, extending the Transformer to take multimodal embeddings as input. An important feature of UDoc is that it learns a generic representation by making use of three self-supervised losses.
  arXiv  Detail & Related papers  (2022-04-22T21:47:04Z)
• Combining Deep Learning and Reasoning for Address Detection in Unstructured Text Documents [0.0]
  We propose a hybrid approach that combines deep learning with reasoning for finding and extracting addresses from unstructured text documents. We use a visual deep learning model to detect the boundaries of possible address regions on the scanned document images.
  arXiv  Detail & Related papers  (2022-02-07T12:32:00Z)
• Coherence-Based Distributed Document Representation Learning for Scientific Documents [9.646001537050925]
  We propose a coupled text pair embedding (CTPE) model to learn the representation of scientific documents. We use negative sampling to construct uncoupled text pairs whose two parts are from different documents. We train the model to judge whether the text pair is coupled or uncoupled and use the obtained embedding of coupled text pairs as the embedding of documents.
  arXiv  Detail & Related papers  (2022-01-08T15:29:21Z)
• Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation [50.01708049531156]
  We focus on a new practical task, document-scale text content manipulation, which is the opposite of text style transfer. In detail, the input is a set of structured records and a reference text for describing another recordset. The output is a summary that accurately describes the partial content in the source recordset with the same writing style of the reference.
  arXiv  Detail & Related papers  (2020-02-24T12:52:10Z)
• Document Network Projection in Pretrained Word Embedding Space [7.455546102930911]
  We present Regularized Linear Embedding (RLE), a novel method that projects a collection of linked documents into a pretrained word embedding space. We leverage a matrix of pairwise similarities providing complementary information (e.g., the network proximity of two documents in a citation graph) The document representations can help to solve many information retrieval tasks, such as recommendation, classification and clustering.
  arXiv  Detail & Related papers  (2020-01-16T10:16:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.