A Densely Connected Criss-Cross Attention Network for Document-level Relation Extraction

• URL: http://arxiv.org/abs/2203.13953v1
• Date: Sat, 26 Mar 2022 01:01:34 GMT
• Title: A Densely Connected Criss-Cross Attention Network for Document-level Relation Extraction
• Authors: Liang Zhang, Yidong Cheng
• Abstract summary: Document-level relation extraction (RE) aims to identify relations between two entities in a given document. Previous research normally completed reasoning through information propagation on the mention-level or entity-level document-graph. We propose a novel model, called Densely Connected Criss-Cross Attention Network (Dense-CCNet), for document-level RE.
• Score: 3.276435438007766
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Document-level relation extraction (RE) aims to identify relations between two entities in a given document. Compared with its sentence-level counterpart, document-level RE requires complex reasoning. Previous research normally completed reasoning through information propagation on the mention-level or entity-level document-graph, but rarely considered reasoning at the entity-pair-level.In this paper, we propose a novel model, called Densely Connected Criss-Cross Attention Network (Dense-CCNet), for document-level RE, which can complete logical reasoning at the entity-pair-level. Specifically, the Dense-CCNet performs entity-pair-level logical reasoning through the Criss-Cross Attention (CCA), which can collect contextual information in horizontal and vertical directions on the entity-pair matrix to enhance the corresponding entity-pair representation. In addition, we densely connect multiple layers of the CCA to simultaneously capture the features of single-hop and multi-hop logical reasoning.We evaluate our Dense-CCNet model on three public document-level RE datasets, DocRED, CDR, and GDA. Experimental results demonstrate that our model achieves state-of-the-art performance on these three datasets.

Related papers

• Document-level Relation Extraction with Cross-sentence Reasoning Graph [14.106582119686635]
  Relation extraction (RE) has recently moved from the sentence-level to document-level. We propose a novel document-level RE model with a GRaph information Aggregation and Cross-sentence Reasoning network (GRACR) Experimental results show GRACR achieves excellent performance on two public datasets of document-level RE.
  arXiv  Detail & Related papers  (2023-03-07T14:14:12Z)
• ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select [53.071352033539526]
  We study the problem of extracting N-ary relations from scientific articles. Our proposed method ReSel decomposes this task into a two-stage procedure. Our experiments on three scientific information extraction datasets show that ReSel outperforms state-of-the-art baselines significantly.
  arXiv  Detail & Related papers  (2022-10-26T02:28:02Z)
• Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval [152.3504607706575]
  This research aims to conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product categories. We first contribute the Product1M datasets, and define two real practical instance-level retrieval tasks. We exploit to train a more effective cross-modal model which is adaptively capable of incorporating key concept information from the multi-modal data.
  arXiv  Detail & Related papers  (2022-06-17T15:40:45Z)
• A Masked Image Reconstruction Network for Document-level Relation Extraction [3.276435438007766]
  Document-level relation extraction requires inference over multiple sentences to extract complex relational triples. We propose a novel Document-level Relation Extraction model based on a Masked Image Reconstruction network (DRE-MIR) We evaluate our model on three public document-level relation extraction datasets.
  arXiv  Detail & Related papers  (2022-04-21T02:41:21Z)
• 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)
• Document-level Relation Extraction as Semantic Segmentation [38.614931876015625]
  Document-level relation extraction aims to extract relations among multiple entity pairs from a document. This paper approaches the problem by predicting an entity-level relation matrix to capture local and global information. We propose a Document U-shaped Network for document-level relation extraction.
  arXiv  Detail & Related papers  (2021-06-07T13:44:44Z)
• Coarse-to-Fine Entity Representations for Document-level Relation Extraction [28.39444850200523]
  Document-level Relation Extraction (RE) requires extracting relations expressed within and across sentences. Recent works show that graph-based methods, usually constructing a document-level graph that captures document-aware interactions, can obtain useful entity representations. We propose the textbfCoarse-to-textbfFine textbfEntity textbfRepresentation model (textbfCFER) that adopts a coarse-to-fine strategy.
  arXiv  Detail & Related papers  (2020-12-04T10:18:59Z)
• Bidirectional Graph Reasoning Network for Panoptic Segmentation [126.06251745669107]
  We introduce a Bidirectional Graph Reasoning Network (BGRNet) to mine the intra-modular and intermodular relations within and between foreground things and background stuff classes. BGRNet first constructs image-specific graphs in both instance and semantic segmentation branches that enable flexible reasoning at the proposal level and class level.
  arXiv  Detail & Related papers  (2020-04-14T02:32:10Z)
• An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis [73.7488524683061]
  We propose a novel Iterative Multi-Knowledge Transfer Network (IMKTN) for end-to-end ABSA. Our IMKTN transfers the task-specific knowledge from any two of the three subtasks to another one at the token level by utilizing a well-designed routing algorithm. Experimental results on three benchmark datasets demonstrate the effectiveness and superiority of our approach.
  arXiv  Detail & Related papers  (2020-04-04T13:49:54Z)
• HIN: Hierarchical Inference Network for Document-Level Relation Extraction [13.474450053582572]
  Document-level RE requires reading, inferring and aggregating over multiple sentences. How to obtain and aggregate the inference information with different granularity is challenging for document-level RE.
  arXiv  Detail & Related papers  (2020-03-28T09:32:31Z)
• Cascaded Human-Object Interaction Recognition [175.60439054047043]
  We introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding.
  arXiv  Detail & Related papers  (2020-03-09T17:05:04Z)

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.