Let’s Stop Incorrect Comparisons in End-to-end Relation Extraction!

Taillé, Bruno; Guigue, Vincent; Scoutheeten, Geoffrey; Gallinari, Patrick

doi:10.18653/v1/2020.emnlp-main.301

Cited by 21 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evaluation Following suggestions in (Taillé et al, 2020), we evaluate Precision (P), Recall (R), and F1 scores with micro-averaging and adopt the Strict Evaluation criterion. Specifically, a predicted entity is correct if its type and boundaries are correct, and a predicted relation is correct if its relation type is correct, as well as the boundaries and types of two argument entities are correct.…”

Section: Methodsmentioning

confidence: 99%

UniRE: A Unified Label Space for Entity Relation Extraction

Wang¹,

Sun²,

Wu³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks' label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell's label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster.

show abstract

Section: Methodsmentioning

confidence: 99%

UniRE: A Unified Label Space for Entity Relation Extraction

Wang¹,

Sun²,

Wu³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

show abstract

“…(2) strict evaluation (Rel+): in addition to what is required in the boundaries evaluation, predicted entity types also must be correct. More discussion of the evaluation settings can be found in Bekoulis et al (2018); Taillé et al (2020).…”

Section: Evaluation Metricsmentioning

confidence: 99%

A Frustratingly Easy Approach for Entity and Relation Extraction

Zhong¹,

Chen²

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

261

118

View full text Add to dashboard Cite

End-to-end relation extraction aims to identify named entities and extract relations between them. Most recent work models these two subtasks jointly, either by casting them in one structured prediction framework, or performing multi-task learning through shared representations. In this work, we present a simple pipelined approach for entity and relation extraction, and establish the new state-of-the-art on standard benchmarks (ACE04, ACE05 and SciERC), obtaining a 1.7%-2.8% absolute improvement in relation F1 over previous joint models with the same pre-trained encoders. Our approach essentially builds on two independent encoders and merely uses the entity model to construct the input for the relation model. Through a series of careful examinations, we validate the importance of learning distinct contextual representations for entities and relations, fusing entity information early in the relation model, and incorporating global context. Finally, we also present an efficient approximation to our approach which requires only one pass of both entity and relation encoders at inference time, achieving an 8-16× speedup with a slight reduction in accuracy. 1

show abstract

“…The term Relation Extraction is often used in the literature for different tasks and setups in the literature (Taillé et al, 2020). For clarity, we refer to Relation Extraction (RE) as the task of extracting triplets of relations between entities from raw text, with no given entity spans, usually also called endto-end Relation Extraction.…”

Section: Relation Extractionmentioning

confidence: 99%

“…While the aforementioned work highlights the relevance of Relation Extraction as a task, the lack of consistent baselines or a cohesive task definition has led to discrepancies in the use of datasets and the way models have been evaluated. Taillé et al (2020) explain the different issues in-so-far, and also make an attempt to unify RE evaluation and perform a fair comparison between systems.…”

Section: Relation Extractionmentioning

confidence: 99%

REBEL: Relation Extraction By End-to-end Language generation

Cabot¹,

Navigli

2021

Findings of the Association for Computational Linguistics: EMNLP 2021

View full text Add to dashboard Cite

Extracting relation triplets from raw text is a crucial task in Information Extraction, enabling multiple applications such as populating or validating knowledge bases, factchecking, and other downstream tasks. However, it usually involves multiple-step pipelines that propagate errors or are limited to a small number of relation types. To overcome these issues, we propose the use of autoregressive seq2seq models. Such models have previously been shown to perform well not only in language generation, but also in NLU tasks such as Entity Linking, thanks to their framing as seq2seq tasks. In this paper, we show how Relation Extraction can be simplified by expressing triplets as a sequence of text and we present REBEL, a seq2seq model based on BART that performs end-to-end relation extraction for more than 200 different relation types. We show our model's flexibility by finetuning it on an array of Relation Extraction and Relation Classification benchmarks, with it attaining state-of-the-art performance in most of them.

show abstract

Let’s Stop Incorrect Comparisons in End-to-end Relation Extraction!

Cited by 21 publications

References 35 publications

UniRE: A Unified Label Space for Entity Relation Extraction

UniRE: A Unified Label Space for Entity Relation Extraction

A Frustratingly Easy Approach for Entity and Relation Extraction

REBEL: Relation Extraction By End-to-end Language generation

Contact Info

Product

Resources

About