ChuLo: Chunk-Level Key Information Representation for Long Document Processing

• URL: http://arxiv.org/abs/2410.11119v3
• Date: Mon, 11 Nov 2024 23:36:36 GMT
• Title: ChuLo: Chunk-Level Key Information Representation for Long Document Processing
• Authors: Yan Li, Soyeon Caren Han, Yue Dai, Feiqi Cao,
• Abstract summary: ChuLo is a novel chunk representation method for long document classification. Our approach minimizes information loss and improves the efficiency of Transformer-based models.
• Score: 11.29459225491404
• License:
• Abstract: Transformer-based models have achieved remarkable success in various Natural Language Processing (NLP) tasks, yet their ability to handle long documents is constrained by computational limitations. Traditional approaches, such as truncating inputs, sparse self-attention, and chunking, attempt to mitigate these issues, but they often lead to information loss and hinder the model's ability to capture long-range dependencies. In this paper, we introduce ChuLo, a novel chunk representation method for long document classification that addresses these limitations. Our ChuLo groups input tokens using unsupervised keyphrase extraction, emphasizing semantically important keyphrase based chunk to retain core document content while reducing input length. This approach minimizes information loss and improves the efficiency of Transformer-based models. Preserving all tokens in long document understanding, especially token classification tasks, is especially important to ensure that fine-grained annotations, which depend on the entire sequence context, are not lost. We evaluate our method on multiple long document classification tasks and long document token classification tasks, demonstrating its effectiveness through comprehensive qualitative and quantitative analyses.

Related papers

• KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches [52.02764371205856]
  Long context capability is a crucial competency for large language models (LLMs) This work provides a taxonomy of current methods and evaluating 10+ state-of-the-art approaches across seven categories of long context tasks.
  arXiv  Detail & Related papers  (2024-07-01T17:59:47Z)
• CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling [52.404072802235234]
  We introduce Chunked Instruction-aware State Eviction (CItruS), a novel modeling technique that integrates the attention preferences useful for a downstream task into the eviction process of hidden states. Our training-free method exhibits superior performance on long sequence comprehension and retrieval tasks over several strong baselines under the same memory budget.
  arXiv  Detail & Related papers  (2024-06-17T18:34:58Z)
• Equipping Transformer with Random-Access Reading for Long-Context Understanding [9.433800833564279]
  Long-context modeling presents a significant challenge for transformer-based large language models. We propose a novel reading strategy that enables transformers to efficiently process long documents without examining every token.
  arXiv  Detail & Related papers  (2024-05-21T21:41:07Z)
• Summarization-based Data Augmentation for Document Classification [16.49709049899731]
  We propose a simple yet effective summarization-based data augmentation, SUMMaug, for document classification. We first obtain easy-to-learn examples for the target document classification task. We then use the generated pseudo examples to perform curriculum learning.
  arXiv  Detail & Related papers  (2023-12-01T11:34:37Z)
• Attention Sorting Combats Recency Bias In Long Context Language Models [69.06809365227504]
  Current language models often fail to incorporate long contexts efficiently during generation. We show that a major contributor to this issue are attention priors that are likely learned during pre-training. We leverage this fact to introduce attention sorting'': perform one step of decoding, sort documents by the attention they receive, repeat the process, generate the answer with the newly sorted context.
  arXiv  Detail & Related papers  (2023-09-28T05:19:06Z)
• Information Extraction from Documents: Question Answering vs Token Classification in real-world setups [0.0]
  We compare the Question Answering approach with the classical token classification approach for document key information extraction. Our research showed that when dealing with clean and relatively short entities, it is still best to use token classification-based approach.
  arXiv  Detail & Related papers  (2023-04-21T14:43:42Z)
• Fine-Grained Distillation for Long Document Retrieval [86.39802110609062]
  Long document retrieval aims to fetch query-relevant documents from a large-scale collection. Knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder. We propose a new learning framework, fine-grained distillation (FGD), for long-document retrievers.
  arXiv  Detail & Related papers  (2022-12-20T17:00:36Z)
• Query-Based Keyphrase Extraction from Long Documents [4.823229052465654]
  This paper overcomes issue for keyphrase extraction by chunking the long documents. System employs a pre-trained BERT model and adapts it to estimate the probability that a given text span forms a keyphrase.
  arXiv  Detail & Related papers  (2022-05-11T10:29:30Z)
• 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)
• Long Document Summarization with Top-down and Bottom-up Inference [113.29319668246407]
  We propose a principled inference framework to improve summarization models on two aspects. Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency. We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets.
  arXiv  Detail & Related papers  (2022-03-15T01:24:51Z)
• Robust Document Representations using Latent Topics and Metadata [17.306088038339336]
  We propose a novel approach to fine-tuning a pre-trained neural language model for document classification problems. We generate document representations that capture both text and metadata artifacts in a task manner. Our solution also incorporates metadata explicitly rather than just augmenting them with text.
  arXiv  Detail & Related papers  (2020-10-23T21:52:38Z)

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.