Hybrid neural tagging model for open relation extraction

Jia, Shengbin; Shijia, E; Ding, Ling; Chen, Xiaojun; Xiang, Yang

doi:10.1016/j.eswa.2022.116951

Cited by 11 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In sequence labeling open IE systems, when extracting arguments for a specific predicate, predicate-related features are used as input variables (Stanovsky et al, 2018;Zhan and Zhao, 2019;Jia and Xiang, 2019). We analyzed this extraction process from the perspective of multimodal 1 The code for our model and related resources can be found in https://github.com/youngbin-ro/ Multi2OIE learning (Mangai et al, 2010;Ngiam et al, 2011;Baltrušaitis et al, 2019), which defines an entire sequence and the corresponding predicate information as a modality.…”

Section: Multi-head Attention For Open Iementioning

confidence: 99%

“…(Fader et al, 2011;Mausam et al, 2012;Del Corro and Gemulla, 2013), most recent open IE research has focused on deep-neural-network-based supervised learning models. Such systems are typically based on bidirectional long short-term memory (BiLSTM) and are formulated for two categories: sequence labeling (Stanovsky et al, 2018;Sarhan and Spruit, 2019;Jia and Xiang, 2019) and sequence generation (Cui et al, 2018;Sun et al, 2018;Bhutani et al, 2019). The latter enables flexible extraction; however, it is more computationally expensive than the former.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiˆ2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT

Ro¹,

Lee²,

Kang³

2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

In this paper, we propose Multi 2 OIE, which performs open information extraction (open IE) by combining BERT (Devlin et al., 2019) with multi-head attention blocks (Vaswani et al., 2017). Our model is a sequence-labeling system with an efficient and effective argument extraction method. We use a query, key, and value setting inspired by the Multimodal Transformer (Tsai et al., 2019) to replace the previously used bidirectional long short-term memory architecture with multihead attention. Multi 2 OIE outperforms existing sequence-labeling systems with high computational efficiency on two benchmark evaluation datasets, Re-OIE2016 and CaRB. Additionally, we apply the proposed method to multilingual open IE using multilingual BERT. Experimental results on new benchmark datasets introduced for two languages (Spanish and Portuguese) demonstrate that our model outperforms other multilingual systems without training data for the target languages.

show abstract

Section: Multi-head Attention For Open Iementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multiˆ2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT

Ro¹,

Lee²,

Kang³

2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

show abstract

“…Jia et al [25] proposed a hybrid neural network model for labeling open relations, employing the LSTM model of ordered neurons to encode syntactic information and capture associations between arguments. To do so, they built a large-scale, high-quality, fully automated training corpus.…”

Section: Related Workmentioning

confidence: 99%

Text prediction recurrent neural networks using long short-term memory-dropout

Iparraguirre-Villanueva¹,

Guevara-Ponce²,

Ruiz-Alvarado³

et al. 2023

IJEECS

View full text Add to dashboard Cite

Unit short-term memory (LSTM) is a type of recurrent neural network (RNN) whose sequence-based models are being used in text generation and/or prediction tasks, question answering, and classification systems due to their ability to learn long-term dependencies. The present research integrates the LSTM network and dropout technique to generate a text from a corpus as input, a model is developed to find the best way to extract the words from the context. For training the model, the poem "La Ciudad y los perros" which is composed of 128,600 words is used as input data. The poem was divided into two data sets, 38.88% for training and the remaining 61.12% for testing the model. The proposed model was tested in two variants: word importance and context. The results were evaluated in terms of the semantic proximity of the generated text to the given context.

show abstract

“…It concatenates and encodes the query together with the context to generate sequence embedding, with which this framework dynamically determines a sub-module (Single-span Extraction or Query-based Sequence Labeling) to label the potential relation(s) in the context. Jia et al (2022) propose a hybrid neural network model ( HNN4ORT) for open relation tagging. The (h, t, s), where h and t denote head entity and tail entity respectively, and s denotes the sentence corresponding to two entities.…”

Section: Open Relation Span Extractionmentioning

confidence: 99%

Open Information Extraction from 2007 to 2022 -- A Survey

Liu¹,

Gao²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Open information extraction is an important NLP task that targets extracting structured information from unstructured text without limitations on the relation type or the domain of the text. This survey paper covers open information extraction technologies from 2007 to 2022 with a focus on new models not covered by previous surveys. We propose a new categorization method from the source of information perspective to accommodate the development of recent OIE technologies. In addition, we summarize three major approaches based on task settings as well as current popular datasets and model evaluation metrics. Given the comprehensive review, several future directions are shown from datasets, source of information, output form, method, and evaluation metric aspects.

show abstract

Hybrid neural tagging model for open relation extraction

Cited by 11 publications

References 12 publications

Multiˆ2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT

Multiˆ2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT

Text prediction recurrent neural networks using long short-term memory-dropout

Open Information Extraction from 2007 to 2022 -- A Survey

Contact Info

Product

Resources

About