Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti

Fardin Ahsan Sakib, A H M Rezaul Karim, Saadat Hasan Khan, Md Mushfiqur Rahman
10/17/2023
cs.CLcs.LG

No official code found. Best implementation: mushfiqur11/bangla-sylheti-snips (0 stars, last commit 2024-08-29).

Abstract

As voice assistants cement their place in our technologically advanced society, there remains a need to cater to the diverse linguistic landscape, including colloquial forms of low-resource languages. Our study introduces the first-ever comprehensive dataset for intent detection and slot filling in formal Bangla, colloquial Bangla, and Sylheti languages, totaling 984 samples across 10 unique intents. Our analysis reveals the robustness of large language models for tackling downstream tasks with inadequate data. The GPT-3.5 model achieves an impressive F1 score of 0.94 in intent detection and 0.51 in slot filling for colloquial Bangla.

View on arXivView PDF

Code Implementations(1)

mushfiqur11/bangla-sylheti-snipsCommunity100%
00Python, Jupyter NotebookAug 27, 20232 years ago

Similar Papers

A Persian Benchmark for Joint Intent Detection and Slot Filling

89% match1 repo182023

Zero-Shot Slot and Intent Detection in Low-Resource Languages

88% match2023

ITALIC: An Italian Intent Classification Dataset

86% match1 repo142023

TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild

86% match2026

Creating Spoken Dialog Systems in Ultra-Low Resourced Settings

85% match2023

Generalized Multiple Intent Conditioned Slot Filling

85% match2023

Cite this paper

@article{sakib2023intent,
  title  = {Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti},
  author = {Fardin Ahsan Sakib and A H M Rezaul Karim and Saadat Hasan Khan and Md Mushfiqur Rahman},
  year   = {2023},
  eprint = {2310.10935},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.10935v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.10935.svg)](https://codeofpaper.com/paper/2310.10935)

Discussion