Character-Level Convolutional Neural Network for Paraphrase Detection and Other Experiments

被引：2

作者：

Maraev, Vladislav ^{[1
]}

Saedi, Chakaveh ^{[1
]}

Rodrigues, Joao ^{[1
]}

Branco, Antonio ^{[1
]}

Silva, Joao ^{[1
]}

机构：

[1] Univ Lisbon, Fac Sci, Dept Informat, Lisbon, Portugal

来源：

ARTIFICIAL INTELLIGENCE AND NATURAL LANGUAGE | 2018年 / 789卷

关键词：

Paraphrase detection; Word embeddings; Character embeddings; Convolutional neural networks; Distributional semantics;

D O I：

10.1007/978-3-319-71746-3_23

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The central goal of this paper is to report on the results of an experimental study on the application of character-level embeddings and basic convolutional neural network to the shared task of sentence paraphrase detection in Russian. This approach was tested in the standard run of Task 2 of that shared task and revealed competitive results, namely 73.9% accuracy against the test set. It is compared against a word-level convolutional neural network for the same task, and varied other approaches, such as rule-based and classical machine learning.

引用

页码：293 / 304

页数：12

共 50 条

[11] Character-level text classification via convolutional neural network and gated recurrent unit
Liu, Bing
Zhou, Yong
Sun, Wei
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2020, 11 (08) : 1939 - 1949
[12] Keyword Extraction with Character-Level Convolutional Neural Tensor Networks
Lin, Zhe-Li
Wang, Chuan-Ju
ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2019, PT I, 2019, 11439 : 400 - 413
[13] Character-Level Convolutional Neural Network for Predicting Severity of Software Vulnerability from Vulnerability Description
Nakagawa, Shunta .
Nagai, Tatsuya
Kanehara, Hideaki
Furumoto, Keisuke
Takita, Makoto
Shiraishi, Yoshiaki
Takahashi, Takeshi
Mohri, Masami
Takano, Yasuhiro
Morii, Masakatu
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2019, E102D (09) : 1679 - 1682
[14] SanskritWord Segmentation Using Character-level Recurrent and Convolutional Neural Networks
Helwig, Oliver
Nehrdich, Sebastian
2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 2754 - 2763
[15] CECoR-Net: A Character-Level Neural Network Model for Web Attack Detection
Gong, Xinyu
Lu, Jialiang
Wang, Yuchen
Qiu, Han
He, Ruan
Qiu, Meikang
4TH IEEE INTERNATIONAL CONFERENCE ON SMART CLOUD (SMARTCLOUD 2019) / 3RD INTERNATIONAL SYMPOSIUM ON REINFORCEMENT LEARNING (ISRL 2019), 2019, : 98 - 103
[16] A Complaint Text Classification Model Based on Character-level Convolutional Network
Tong, Xuesong
Wu, Bin
Wang, Shuyang
Lv, Jinna
PROCEEDINGS OF 2018 IEEE 9TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND SERVICE SCIENCE (ICSESS), 2018, : 507 - 511
[17] Character-level neural network for biomedical named entity recognition
Gridach, Mourad
JOURNAL OF BIOMEDICAL INFORMATICS, 2017, 70 : 85 - 91
[18] Character-level Convolutional Networks for Text Classification
Zhang, Xiang
Zhao, Junbo
Yann Lecun
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 28 (NIPS 2015), 2015, 28
[19] Enhanced character-level deep convolutional neural networks for cardiovascular disease prediction
Zhang, Zhichang
Qiu, Yanlong
Yang, Xiaoli
Zhang, Minyu
BMC MEDICAL INFORMATICS AND DECISION MAKING, 2020, 20 (Suppl 3)
[20] Enhanced character-level deep convolutional neural networks for cardiovascular disease prediction
Zhichang Zhang
Yanlong Qiu
Xiaoli Yang
Minyu Zhang
BMC Medical Informatics and Decision Making, 20

← 1 2 3 4 5 →