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

[21] Weakly-supervised character-level convolutional neural networks for text classification
Liu, Yongsheng
Chen, Wenyu
Niyongabo, Rubungo Andre
Qu, Hong
Miao, Kebin
Wei, Feng
DEVELOPMENTS OF ARTIFICIAL INTELLIGENCE TECHNOLOGIES IN COMPUTATION AND ROBOTICS, 2020, 12 : 701 - 708
[22] Character-Level Attention Convolutional Neural Networks for Short-Text Classification
Yin, Feiyang
Yao, Zhilin
Liu, Jia
HUMAN CENTERED COMPUTING, 2019, 11956 : 560 - 567
[23] Character-level convolutional networks for arithmetic operator character recognition
Liang, Zhijie
Li, Qing
Liao, Shengbin
FIFTH INTERNATIONAL CONFERENCE ON EDUCATIONAL INNOVATION THROUGH TECHNOLOGY (EITT 2016), 2016, : 208 - 212
[24] Automatically Classifying Chinese Judgment Documents Using Character-Level Convolutional Neural Networks
Zhou, Xiaosong
Li, Chuanyi
Ge, Jidong
Li, Zhongjin
Zhou, Xiaoyu
Luo, Bin
PRICAI 2018: TRENDS IN ARTIFICIAL INTELLIGENCE, PT II, 2018, 11013 : 430 - 437
[25] MOJI: Character-level convolutional neural networks for Malicious Obfuscated Java']JavaScript Inspection
Ishida, Minato
Kaneko, Naoshi
Sumi, Kazuhiko
APPLIED SOFT COMPUTING, 2023, 137
[26] Text Classification and Transfer Learning Based on Character-Level Deep Convolutional Neural Networks
Sato, Minato
Orihara, Ryohei
Sei, Yuichi
Tahara, Yasuyuki
Ohsuga, Akihiko
AGENTS AND ARTIFICIAL INTELLIGENCE (ICAART 2017), 2018, 10839 : 62 - 81
[27] Neural Character-Level Syntactic Parsing for Chinese
Li, Zuchao
Zhou, Junru
Zhao, Hai
Zhang, Zhisong
Li, Haonan
Ju, Yuqi
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2022, 73 : 461 - 509
[28] Neural Character-Level Syntactic Parsing for Chinese
Li Z.
Zhou J.
Zhao H.
Zhang Z.
Li H.
Ju Y.
Journal of Artificial Intelligence Research, 2022, 73 : 461 - 509
[29] Neural Character-Level Dependency Parsing for Chinese
Li, Haonan
Zhang, Zhisong
Ju, Yuqi
Zhao, Hai
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 5205 - 5212
[30] Character-Aware Convolutional Neural Networks for Paraphrase Identification
Huang, Jiangping
Ji, Donghong
Yao, Shuxin
Huang, Wenzhi
NEURAL INFORMATION PROCESSING, ICONIP 2016, PT II, 2016, 9948 : 177 - 184

← 1 2 3 4 5 →