Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding

• URL: http://arxiv.org/abs/2305.10448v1
• Date: Tue, 16 May 2023 15:25:19 GMT
• Title: Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding
• Authors: Shuwei Feng, Tianyang Zhan, Zhanming Jie, Trung Quoc Luong, Xiaoran Jin
• Abstract summary: GenDoc is a sequence-to-sequence document understanding model pre-trained with unified masking across three modalities. The proposed model utilizes an encoder-decoder architecture, which allows for increased adaptability to a wide range of downstream tasks.
• Score: 3.185382039518151
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This paper presents GenDoc, a general sequence-to-sequence document understanding model pre-trained with unified masking across three modalities: text, image, and layout. The proposed model utilizes an encoder-decoder architecture, which allows for increased adaptability to a wide range of downstream tasks with diverse output formats, in contrast to the encoder-only models commonly employed in document understanding. In addition to the traditional text infilling task used in previous encoder-decoder models, our pre-training extends to include tasks of masked image token prediction and masked layout prediction. We also design modality-specific instruction and adopt both disentangled attention and the mixture-of-modality-experts strategy to effectively capture the information leveraged by each modality. Evaluation of the proposed model through extensive experiments on several downstream tasks in document understanding demonstrates its ability to achieve superior or competitive performance compared to state-of-the-art approaches. Our analysis further suggests that GenDoc is more robust than the encoder-only models in scenarios where the OCR quality is imperfect.

Related papers

• Few-shot Action Recognition with Captioning Foundation Models [61.40271046233581]
  CapFSAR is a framework to exploit knowledge of multimodal models without manually annotating text. Visual-text aggregation module based on Transformer is further designed to incorporate cross-modal-temporal complementary information. experiments on multiple standard few-shot benchmarks demonstrate that the proposed CapFSAR performs favorably against existing methods.
  arXiv  Detail & Related papers  (2023-10-16T07:08:39Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval [34.08763911138496]
  This study brings multi-view modeling to the contextual masked auto-encoder. We refer to this multi-view pretraining method as CoT-MAE v2.
  arXiv  Detail & Related papers  (2023-04-05T08:00:38Z)
• Exploring and Exploiting Multi-Granularity Representations for Machine Reading Comprehension [13.191437539419681]
  We propose a novel approach called Adaptive Bidirectional Attention-Capsule Network (ABA-Net) ABA-Net adaptively exploits the source representations of different levels to the predictor. We set the new state-of-the-art performance on the SQuAD 1.0 dataset.
  arXiv  Detail & Related papers  (2022-08-18T10:14:32Z)
• 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)
• Disentangled Sequence to Sequence Learning for Compositional Generalization [62.954842223732435]
  We propose an extension to sequence-to-sequence models which allows us to learn disentangled representations by adaptively re-encoding the source input. Experimental results on semantic parsing and machine translation empirically show that our proposal yields more disentangled representations and better generalization.
  arXiv  Detail & Related papers  (2021-10-09T22:27:19Z)
• HydraSum -- Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models [12.070474521259776]
  We introduce HydraSum, a new summarization architecture that extends the single decoder framework of current models. Our proposed model encourages each expert, i.e. decoder, to learn and generate stylistically-distinct summaries. A guided version of the training process can explicitly govern which summary style is partitioned between decoders.
  arXiv  Detail & Related papers  (2021-10-08T22:49:49Z)
• SelfDoc: Self-Supervised Document Representation Learning [46.22910270334824]
  SelfDoc is a task-agnostic pre-training framework for document image understanding. Our framework exploits the positional, textual, and visual information of every semantically meaningful component in a document. It achieves superior performance on multiple downstream tasks with significantly fewer document images used in the pre-training stage compared to previous works.
  arXiv  Detail & Related papers  (2021-06-07T04:19:49Z)
• Adaptive Bi-directional Attention: Exploring Multi-Granularity Representations for Machine Reading Comprehension [29.717816161964105]
  We propose a novel approach called Adaptive Bidirectional Attention, which adaptively exploits the source representations of different levels to the predictor. Results are better than the previous state-of-the-art model by 2.5$%$ EM and 2.3$%$ F1 scores.
  arXiv  Detail & Related papers  (2020-12-20T09:31:35Z)
• Cross-Thought for Sentence Encoder Pre-training [89.32270059777025]
  Cross-Thought is a novel approach to pre-training sequence encoder. We train a Transformer-based sequence encoder over a large set of short sequences. Experiments on question answering and textual entailment tasks demonstrate that our pre-trained encoder can outperform state-of-the-art encoders.
  arXiv  Detail & Related papers  (2020-10-07T21:02:41Z)
• Rethinking and Improving Natural Language Generation with Layer-Wise Multi-View Decoding [59.48857453699463]
  In sequence-to-sequence learning, the decoder relies on the attention mechanism to efficiently extract information from the encoder. Recent work has proposed to use representations from different encoder layers for diversified levels of information. We propose layer-wise multi-view decoding, where for each decoder layer, together with the representations from the last encoder layer, which serve as a global view, those from other encoder layers are supplemented for a stereoscopic view of the source sequences.
  arXiv  Detail & Related papers  (2020-05-16T20:00:39Z)

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.