Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

By Guoshun Nan, Zhijiang Guo, Ivan Sekulic, Wei Dang Lu. Annual Meeting of the Association for Computational Linguistics, 2020

323 citations recorded by the source corpus.

Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant information in the document remains a challenging research question. Existing approaches construct static document-level graphs based on syntactic trees, co-references or heuristics from the unstructured text to model the dependencies. Unlike previous methods that may not be able to capture rich non-local interactions for inference, we propose a novel model that empowers the relational reasoning across sentences by automatically inducing the latent document-level graph. We further develop a refinement strategy, which enables the model to incrementally aggregate relevant information for multi-hop reasoning. Specifically, our model achieves an F1 score of 59.05 on a large-scale document-level dataset (DocRED), significantly improving over the previous results, and also yields new state-of-the-art results on the CDR and GDA dataset. Furthermore, extensive analyses show that the model is able to discover more accurate inter-sentence relations.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/013faec0400d315935e71a2bdfeb22cc83752b3e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Shirui Pan
3. Linhao Luo
4. Fei Huang
5. Fukun Ma
6. Kevin Huang
7. Shumin Deng
8. Xindong Wu

Citations in the corpus

• Unifying Large Language Models and Knowledge Graphs: A Roadmap (2023, methodology): “Then, the student LLM is utilized to generate commonsense KGs.”
• Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling (2020, methodology): “2019) or adding more types of edges (Christopoulou, Miwa, and Ananiadou 2019; Nan et al. 2020).”
• AdaPrompt: Adaptive Prompt-based Finetuning for Relation Extraction (2021, background): “RE appeals to many researchers (Zhang et al., 2017, 2018a, 2019; Nan et al., 2020; Wu et al., 2021) due to the capability to extract textual information and benefit many NLP applications (e.g., information retrieval, dialog generation, and question answering).”
• KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction (2021, background): “Relation extraction (RE) is a critical task in knowledge base population, attracting considerable research attention (Zhang et al. 2017, 2018; Baumgartner et al. 2018; Zhang et al. 2019, 2020; Nan et al. 2020; Wu et al. 2021).”
• Semi-supervised Relation Extraction via Incremental Meta Self-Training (2020, methodology): “Relation extraction methods are often formulated in a supervised setting (Zeng et al., 2015; Guo et al., 2020; Nan et al., 2020) and require manual annotations on large amounts of corpora, which is labor-intensive to obtain.”