Talla at SemEval-2018 Task 7: Hybrid Loss Optimization for Relation
            Classification using Convolutional Neural Networks

Pratap, Bhanu; Shank, Daniel Burton; Ositelu, Oladipo; Galbraith, Byron

doi:10.18653/v1/s18-1139

Cited by 4 publications

(4 citation statements)

References 7 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Compared with the traditional single-scale convolution kernel relational classification model, the performance was significantly improved. Pratap et al [19] proposed a self-learning mod-ule that can combine the features extracted by the neural network with domain expert knowledge to improve the performance of relational classification networks.…”

Section: Relation Classification Model Based On Convolutional Neural ...mentioning

confidence: 99%

“Standard Text” Relational Classification Model Based on Concatenated Word Vector Attention and Feature Concatenation

et al. 2023

View full text Add to dashboard Cite

The task of relation classification is an important pre-task in natural language processing tasks. Relation classification can provide a high-quality corpus for tasks such as machine translation, human–computer dialogue, and structured text generation. In the process of the digitalization of standards, identifying the entity relationship in the standard text is an important prerequisite for the formation of subsequent standard knowledge. Only by accurately labeling the relationship between entities can there be higher efficiency and accuracy in the subsequent formation of knowledge bases and knowledge maps. This study proposes a standard text relational classification model based on cascaded word vector attention and feature splicing. The model was compared and ablated on our labeled standard text Chinese dataset. At the same time, in order to prove the performance of the model, the above experiments were carried out on two general English datasets, SemEval-2010 Task 8 and KBP37. On standard text datasets and general datasets, the model proposed in this study achieved excellent results.

show abstract

Section: Relation Classification Model Based On Convolutional Neural ...mentioning

confidence: 99%

“Standard Text” Relational Classification Model Based on Concatenated Word Vector Attention and Feature Concatenation

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Second, for the word level attention, the value of α h and α l are assigned according to a proportion of 2:1 on three SemEval-dataset and a proportion of 9:2 on KBP37 dataset. Finally, we introduce learning rate decay λ * as to reduce initial learning rate λ by (12).…”

Section: B Settingsmentioning

confidence: 99%

“…As for two subtask datasets from SemEval-2018 task 7, Nooralahzadeh et al [11] employed the shortest dependency path (SDP) information in CNN and obtained a relatively high performance. Nevertheless, by including additional features, such as part-of-speech (POS) features and WordNet-based features, Pratap et al [12] achieved even better performance. On KBP37 dataset, Supervised Ranking CNN [13] with an active learning extension gained the state-of-the-art performance.…”

Section: Introductionmentioning

confidence: 99%

A Single Attention-Based Combination of CNN and RNN for Relation Classification

et al. 2019

View full text Add to dashboard Cite

As a vital task in natural language processing, relation classification aims to identify relation types between entities from texts. In this paper, we propose a novel Att-RCNN model to extract text features and classify relations by combining recurrent neural network (RNN) and convolutional neural network (CNN). This network structure utilizes RNN to extract higher level contextual representations of words and CNN to obtain sentence features for the relation classification task. In addition to this network structure, both word-level and sentence-level attention mechanisms are employed in Att-RCNN to strengthen critical words and features to promote the model performance. Moreover, we conduct experiments on four distinct datasets: SemEval-2010 task 8, SemEval-2018 task 7 (two subtask datasets), and KBP37 dataset. Compared with the previous public models, Att-RCNN has the overall best performance and achieves the highest F 1 score, especially on the KBP37 dataset. INDEX TERMS Relation classification, neural network, attention mechanism.

show abstract

“…O modelo ETH-DS3Lab [100] utilizou um híbrido entre um modelo CNN e uma LSTM e o modelo UWNLP [101] foi baseado em um modelo LSTM. Os modelos SIRIUS-LTG-UiO [102] e Talla [103] utilizaram modelos baseados em CNN. Os resultados para ambas astarefas são apresentados na Tabela 4.12.…”

Section: Resultsunclassified

Redes Neurais De Memória Aumentada Para Extração De Relações Em Textos

VILLALOBOS¹

View full text Add to dashboard Cite

show abstract

Talla at SemEval-2018 Task 7: Hybrid Loss Optimization for Relation Classification using Convolutional Neural Networks

Cited by 4 publications

References 7 publications

“Standard Text” Relational Classification Model Based on Concatenated Word Vector Attention and Feature Concatenation

“Standard Text” Relational Classification Model Based on Concatenated Word Vector Attention and Feature Concatenation

A Single Attention-Based Combination of CNN and RNN for Relation Classification

Redes Neurais De Memória Aumentada Para Extração De Relações Em Textos

Contact Info

Product

Resources

About