An Interactive Framework of Cross-Lingual NLU for In-Vehicle Dialogue
As globalization accelerates, the linguistic diversity and semantic complexity of in-vehicle communication is increasing. In order to meet the needs of different language speakers, this paper proposes an interactive attention-based contrastive learning framework (IABCL) for the field of in-vehicle d...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/20/8501 |
_version_ | 1797572353274675200 |
---|---|
author | Xinlu Li Liangkuan Fang Lexuan Zhang Pei Cao |
author_facet | Xinlu Li Liangkuan Fang Lexuan Zhang Pei Cao |
author_sort | Xinlu Li |
collection | DOAJ |
description | As globalization accelerates, the linguistic diversity and semantic complexity of in-vehicle communication is increasing. In order to meet the needs of different language speakers, this paper proposes an interactive attention-based contrastive learning framework (IABCL) for the field of in-vehicle dialogue, aiming to effectively enhance cross-lingual natural language understanding (NLU). The proposed framework aims to address the challenges of cross-lingual interaction in in-vehicle dialogue systems and provide an effective solution. IABCL is based on a contrastive learning and attention mechanism. First, contrastive learning is applied in the encoder stage. Positive and negative samples are used to allow the model to learn different linguistic expressions of similar meanings. Its main role is to improve the cross-lingual learning ability of the model. Second, the attention mechanism is applied in the decoder stage. By articulating slots and intents with each other, it allows the model to learn the relationship between the two, thus improving the ability of natural language understanding in languages of the same language family. In addition, this paper constructed a multilingual in-vehicle dialogue (MIvD) dataset for experimental evaluation to demonstrate the effectiveness and accuracy of the IABCL framework in cross-lingual dialogue. With the framework studied in this paper, IABCL improves by 2.42% in intent, 1.43% in slot, and 2.67% in overall when compared with the latest model. |
first_indexed | 2024-03-10T20:55:03Z |
format | Article |
id | doaj.art-cd0d160857b04cc2981aad0bb2e5fe3e |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T20:55:03Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-cd0d160857b04cc2981aad0bb2e5fe3e2023-11-19T18:03:53ZengMDPI AGSensors1424-82202023-10-012320850110.3390/s23208501An Interactive Framework of Cross-Lingual NLU for In-Vehicle DialogueXinlu Li0Liangkuan Fang1Lexuan Zhang2Pei Cao3School of Artificial Intelligence and Big Data, Hefei University, Hefei 230061, ChinaSchool of Artificial Intelligence and Big Data, Hefei University, Hefei 230061, ChinaSchool of Artificial Intelligence and Big Data, Hefei University, Hefei 230061, ChinaSchool of Artificial Intelligence and Big Data, Hefei University, Hefei 230061, ChinaAs globalization accelerates, the linguistic diversity and semantic complexity of in-vehicle communication is increasing. In order to meet the needs of different language speakers, this paper proposes an interactive attention-based contrastive learning framework (IABCL) for the field of in-vehicle dialogue, aiming to effectively enhance cross-lingual natural language understanding (NLU). The proposed framework aims to address the challenges of cross-lingual interaction in in-vehicle dialogue systems and provide an effective solution. IABCL is based on a contrastive learning and attention mechanism. First, contrastive learning is applied in the encoder stage. Positive and negative samples are used to allow the model to learn different linguistic expressions of similar meanings. Its main role is to improve the cross-lingual learning ability of the model. Second, the attention mechanism is applied in the decoder stage. By articulating slots and intents with each other, it allows the model to learn the relationship between the two, thus improving the ability of natural language understanding in languages of the same language family. In addition, this paper constructed a multilingual in-vehicle dialogue (MIvD) dataset for experimental evaluation to demonstrate the effectiveness and accuracy of the IABCL framework in cross-lingual dialogue. With the framework studied in this paper, IABCL improves by 2.42% in intent, 1.43% in slot, and 2.67% in overall when compared with the latest model.https://www.mdpi.com/1424-8220/23/20/8501interactive frameworkin-vehicle dialoguecontrastive learningattention mechanismcross-lingual |
spellingShingle | Xinlu Li Liangkuan Fang Lexuan Zhang Pei Cao An Interactive Framework of Cross-Lingual NLU for In-Vehicle Dialogue Sensors interactive framework in-vehicle dialogue contrastive learning attention mechanism cross-lingual |
title | An Interactive Framework of Cross-Lingual NLU for In-Vehicle Dialogue |
title_full | An Interactive Framework of Cross-Lingual NLU for In-Vehicle Dialogue |
title_fullStr | An Interactive Framework of Cross-Lingual NLU for In-Vehicle Dialogue |
title_full_unstemmed | An Interactive Framework of Cross-Lingual NLU for In-Vehicle Dialogue |
title_short | An Interactive Framework of Cross-Lingual NLU for In-Vehicle Dialogue |
title_sort | interactive framework of cross lingual nlu for in vehicle dialogue |
topic | interactive framework in-vehicle dialogue contrastive learning attention mechanism cross-lingual |
url | https://www.mdpi.com/1424-8220/23/20/8501 |
work_keys_str_mv | AT xinluli aninteractiveframeworkofcrosslingualnluforinvehicledialogue AT liangkuanfang aninteractiveframeworkofcrosslingualnluforinvehicledialogue AT lexuanzhang aninteractiveframeworkofcrosslingualnluforinvehicledialogue AT peicao aninteractiveframeworkofcrosslingualnluforinvehicledialogue AT xinluli interactiveframeworkofcrosslingualnluforinvehicledialogue AT liangkuanfang interactiveframeworkofcrosslingualnluforinvehicledialogue AT lexuanzhang interactiveframeworkofcrosslingualnluforinvehicledialogue AT peicao interactiveframeworkofcrosslingualnluforinvehicledialogue |