HIN: Hierarchical Inference Network for Document-Level Relation Extraction

Tang, Hengzhu; Cao, Yanan; Zhang, Zhenyu; Cao, Jiangxia; Fang, Fang; Wang, Shi; Yin, Peng-Fei

doi:10.1007/978-3-030-47426-3_16

Cited by 97 publications

(58 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We attribute it to the document graph on the entity level, which can better model the semantic information in a document. (3) From the results of ; Tang et al (2020), the BERT-based models showed stronger prediction power for document-level RE. They outperformed the other comparative models on both CDR and DocRED.…”

Section: Resultsmentioning

confidence: 94%

Global-to-Local Neural Networks for Document-Level Relation Extraction

Wang¹,

Hu²,

Cao³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Relation extraction (RE) aims to identify the semantic relations between named entities in text. Recent years have witnessed it raised to the document level, which requires complex reasoning with entities and mentions throughout an entire document. In this paper, we propose a novel model to document-level RE, by encoding the document information in terms of entity global and local representations as well as context relation representations. Entity global representations model the semantic information of all entities in the document, entity local representations aggregate the contextual information of multiple mentions of specific entities, and context relation representations encode the topic information of other relations. Experimental results demonstrate that our model achieves superior performance on two public datasets for document-level RE. It is particularly effective in extracting relations between entities of long distance and having multiple mentions.

show abstract

Section: Resultsmentioning

confidence: 94%

Global-to-Local Neural Networks for Document-Level Relation Extraction

Wang¹,

Hu²,

Cao³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…For many NLP tasks, contextual information from surrounding sentences can improve the quality of a generated sentence. We have seen this for coreference resolution (Joshi et al, 2019), relation extraction (Tang et al, 2020), and machine translation (Werlen et al, 2018;Macé and Servan, 2019). In this work, we show the effectiveness of including document-level context when rewriting recipes to fit a dietary constraint.…”

Section: Document-level Controlled Generationmentioning

confidence: 86%

Substance over Style: Document-Level Targeted Content Transfer

Hegel

Rao

Çelikyılmaz

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Existing language models excel at writing from scratch, but many real-world scenarios require rewriting an existing document to fit a set of constraints. Although sentence-level rewriting has been fairly well-studied, little work has addressed the challenge of rewriting an entire document coherently. In this work, we introduce the task of document-level targeted content transfer and address it in the recipe domain, with a recipe as the document and a dietary restriction (such as vegan or dairy-free) as the targeted constraint. We propose a novel model for this task based on the generative pretrained language model (GPT-2) and train on a large number of roughly-aligned recipe pairs. 1 Both automatic and human evaluations show that our model out-performs existing methods by generating coherent and diverse rewrites that obey the constraint while remaining close to the original document. Finally, we analyze our model's rewrites to assess progress toward the goal of making language generation more attuned to constraints that are substantive rather than stylistic.

show abstract

“…HIN-GloVe/HIN-BERT base , proposed by Tang et al (2020). Hierarchical Inference Network (HIN) aggregate information from entity-level, sentence-level, and document-level to predict target relations, and use GloVe (Pennington et al, 2014) or BERT base for word embedding.…”

Section: Baselines and Evaluation Metricsmentioning

confidence: 99%

Double Graph Based Reasoning for Document-level Relation Extraction

Zeng

Chang

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

160

121

View full text Add to dashboard Cite

Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across paragraphs. In this paper, we propose Graph Aggregation-and-Inference Network (GAIN), a method to recognize such relations for long paragraphs. GAIN constructs two graphs, a heterogeneous mentionlevel graph (MG) and an entity-level graph (EG). The former captures complex interaction among different mentions and the latter aggregates mentions underlying for the same entities. Based on the graphs we propose a novel path reasoning mechanism to infer relations between entities. Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art. Our code is available at https://github.com/ PKUnlp-icler/GAIN.

show abstract

HIN: Hierarchical Inference Network for Document-Level Relation Extraction

Cited by 97 publications

References 12 publications

Global-to-Local Neural Networks for Document-Level Relation Extraction

Global-to-Local Neural Networks for Document-Level Relation Extraction

Substance over Style: Document-Level Targeted Content Transfer

Double Graph Based Reasoning for Document-level Relation Extraction

Contact Info

Product

Resources

About