Intent Detection on Indonesian Text Using Convolutional Neural Network

Bilah, Chiva Olivia; Adji, Teguh Bharata; Setiawan, Noor Akhmad

doi:10.1109/cyberneticscom55287.2022.9865291

Cited by 3 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In later work the authors improved the accuracy to reach 0.9112 (Shams and Aslam, 2022). ATIS was also used for intent detection in the Indonesian language (Bilah et al, 2022) and the authors reported an accuracy of 0.9584 using a CNN-based model. (Basu et al, 2022) utilized Snips (Coucke et al, 2018) and ATIS to train a meta-learning approach with contrastive learning for intent detection and slot-filling.…”

Section: Related Workmentioning

confidence: 96%

ArBanking77: Intent Detection Neural Model and a New Dataset in Modern and Dialectical Arabic

Jarrar,

Birim,

Khalilia

et al. 2023

Proceedings of ArabicNLP 2023

View full text Add to dashboard Cite

This paper presents the ArBanking77, a large Arabic dataset for intent detection in the banking domain. Our dataset was arabized and localized from the original English Banking77 dataset, which consists of 13,083 queries to ArBanking77 dataset with 31,404 queries in both Modern Standard Arabic (MSA) and Palestinian dialect, with each query classified into one of the 77 classes (intents). Furthermore, we present a neural model, based on AraBERT, fine-tuned on ArBanking77, which achieved an F1-score of 0.9209 and 0.8995 on MSA and Palestinian dialect, respectively. We performed extensive experimentation in which we simulated low-resource settings, where the model is trained on a subset of the data and augmented with noisy queries to simulate colloquial terms, mistakes and misspellings found in real NLP systems, especially live chat queries. The data and the models are publicly available at https://sina.birzeit.edu/arbanking77.

show abstract

Section: Related Workmentioning

confidence: 96%

ArBanking77: Intent Detection Neural Model and a New Dataset in Modern and Dialectical Arabic

Jarrar,

Birim,

Khalilia

et al. 2023

Proceedings of ArabicNLP 2023

View full text Add to dashboard Cite

show abstract

“…Cluster 3 concentrated on technological aspects, including natural language processing, reinforcement learning, and the Seq2Seq model. The longest path was identified between Li et al (2016) and Bilah et al (2022) (Figure 6). Li et al (2016) initiated a neural conversational model allowing chatbots to achieve long-term success in dialogues but was criticized for being cheaply obtained and deterministic (Kandasamy et al, 2017).…”

Section: Literature Clusteringmentioning

confidence: 99%

“…Khin and Soe (2020) were inspired to develop a question-answering chatbot in Myanmar languages with the Seq2Seq model providing information about universities in response to user inquiries. However, opportunities to enhance the system's comprehension precision of human language were combined with challenges, for example, a concern about long-term dependence on technology (Bilah et al, 2022).…”

Section: Literature Clusteringmentioning

confidence: 99%

A Bibliometric Analysis of Artificial Intelligence Chatbots in Language Education

Liu,

Lin,

2024

SER

View full text Add to dashboard Cite

Chatbots in language education demonstrate promising potential. This study identifies their developmental paths, recent designs, and primary application contexts through a bibliometric and visualization analysis. We find that artificial intelligence chatbots in language education have gained avid interest in recent years due to technological advancements and growing social attention. Research demonstrates an interdisciplinary trend, and integrating various technologies has improved chatbot effectiveness in education. This study identifies popular research issues on chatbots in language education, such as students’ perceptions, effectiveness evaluation, and technological upgrades. Additionally, we find various roles and functions of chatbots in specific language education domains characterized by learning content, strategies, and contexts. This study establishes its significance by summarizing and discussing the effects of artificial intelligence chatbots from a language education perspective. We propose a model for chatbot applications and research in language education that connects technological and pedagogical aspects, which can be extended and validated to broaden future research empirically.

show abstract

“…Klasifikasi intensi merupakan salah satu task yang ada dalam komponen utama dari chatbot, yaitu pemahaman bahasa alami atau natural language understanding (NLU) (Galitsky, 2019). Klasifikasi intensi berperan dalam memahami topik diskusi ketika chatbot berkomunikasi dengan manusia, sehingga secara tidak langsung juga berpengaruh pada penentuan jawaban yang benar dalam percakapan (Bilah et al, 2022).…”

Section: Klasifikasi Intensiunclassified

“…Kedua penelitian di atas telah menerapkan algoritma LSTM seperti yang digunakan pada penelitian kali ini. Perbedaannya, selain pada dataset yang digunakan, pada penelitian yang dilakukan oleh Bilah et al (2022) menggunakan embedding GloVe, sedangkan pada penelitian kali ini menggunakan BERT. Kemudian, pada penelitian yang dilakukan oleh Denny Prabowo et al (2018), chatbot dibangun secara end-to-end, sehingga klasifikasi intensi tidak dilakukan secara eksplisit.…”

unclassified

Klasifikasi Intensi dengan Metode Ling Short-Term Memory pada Chatbot Bahasa Indonesia

Al Farisi,

Perdana,

Adikara

2023

JTIIK

View full text Add to dashboard Cite

E-government merupakan sebuah konsep pemerintahan yang menyelenggarakan layanan publik secara digital yang didukung oleh teknologi informasi, sehingga menjadi lebih prima. Salah satu bentuk layanan publik digital yang umum ada di berbagai sektor adalah helpdesk. Helpdesk memungkinkan pengguna dapat bertanya atau melaporkan sesuatu untuk kemudian dijawab oleh staf. Permasalahan yang ada adalah ketersediaan staf yang hanya dapat menjawab pada jam kerja, sedangkan pengguna bisa jadi menemukan permasalahan yang urgent di luar jam kerja. Oleh karena itu, solusi yang ditawarkan adalah penerapan chatbot, sehingga dapat melayani kapan pun, sekaligus meringankan kerja dari staf. Penelitian ini mencoba untuk merancang salah satu komponen pada chatbot, yaitu model klasifikasi intensi, dengan metode Long Short-Term Memory. Data yang digunakan merupakan 501 teks riwayat pertanyaan dari database Helpdesk TIK UB yang termasuk ke dalam 7 kelas intensi yang ditentukan. Data akan melalui beberapa tahap prapemrosesan sebelum kemudian dilakukan pemodelan dan beberapa pengujian. Tahap pengujian meliputi pemilihan embedding yang digunakan, pemilihan teknik augmentasi data, dan penyetelan hyperparameter. Hasil dari keseluruhan pengujian, didapatkan model terbaik yang mampu menghasilkan akurasi sempurna untuk data latih dan data uji, serta loss 0,004 untuk data latih dan 0,044 untuk data uji. Abstract E-government is a government concept that organizes digital public services supported by information technology, so that they become more excellent. One form of digital public service that is common in various sectors is the helpdesk. Helpdesk allows users to ask questions or report something to be answered by staff. The problem that exists is the availability of staff who can only answer during working hours, while users may find urgent problems outside of working hours. Therefore, the solution offered is the implementation of a chatbot, so that it can serve at any time, while easing the work of staff. This study attempts to design one of the components of the chatbot, namely the intention classification model, using the Long Short-Term Memory method. The data used are 501 question history texts from the Helpdesk TIK UB database which fall into the 7 specified intensity classes. The data will go through several pre-processing stages before then being modeled and tested. The testing phase includes selecting the embedding used, data augmentation techniques selection, and hyperparameter tuning. The best model is obtained which can produce perfect accuracy for training data and test data, as well as a loss of 0.004 for training data and 0.044 for test data.

show abstract

Intent Detection on Indonesian Text Using Convolutional Neural Network

Cited by 3 publications

References 15 publications

ArBanking77: Intent Detection Neural Model and a New Dataset in Modern and Dialectical Arabic

ArBanking77: Intent Detection Neural Model and a New Dataset in Modern and Dialectical Arabic

A Bibliometric Analysis of Artificial Intelligence Chatbots in Language Education

Klasifikasi Intensi dengan Metode Ling Short-Term Memory pada Chatbot Bahasa Indonesia

Contact Info

Product

Resources

About