# A Benchmark for Bangla Task-Oriented Dialogue Understanding

arXiv: https://arxiv.org/abs/2610.18060 · HTML: https://mlsanity.com/paper/2610.18060/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [Are All Languages Created Equal in Multilingual BERT?](https://mlsanity.com/paper/2005.09093/) (2020)
- [BERT for Joint Intent Classification and Slot Filling](https://mlsanity.com/paper/1902.10909/) (2019)
- [MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark](https://mlsanity.com/paper/2008.09335/) (2020)
- [Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialog](https://mlsanity.com/paper/1810.13327/) (2018)
- [BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla](https://mlsanity.com/paper/2101.00204/) (2021)
- [End-to-End Slot Alignment and Recognition for Cross-Lingual NLU](https://mlsanity.com/paper/2004.14353/) (2020)
- [BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla](https://mlsanity.com/paper/2205.11081/) (2022)
- [GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2110.07679/) (2021)
- [BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis](https://mlsanity.com/paper/2408.08964/) (2024)
- [End-to-End Natural Language Understanding Pipeline for Bangla Conversational Agents](https://mlsanity.com/paper/2107.05541/) (2021)
- [Leveraging Code-Mixed Product Metadata and User Feedback for Personalized Recommendation on Daraz Bangladesh](https://mlsanity.com/paper/2606.16387/) (2026)
- [Constraint-Aware Conversational Job Recommendation in Code-Mixed Low-Resource Settings](https://mlsanity.com/paper/2610.05787/) (2026)

## Abstract (arXiv)

Task-oriented dialogue understanding remains underexplored for Bangla, particularly in multilingual settings involving English and romanized Bangla (Banglish). We introduce BanglaTOD, a parallel tri-lingual benchmark comprising 209 multi-turn dialogues across nine Bangladesh-specific service domains and 64 intents. Each conversational turn is aligned across Bangla, English, and Banglish, yielding 4,689 language-specific turn records annotated with intents, token-level slots, state updates, and accumulated dialogue states. We establish context-aware baselines for joint intent classification and slot filling using mBERT, BERT-base-uncased, and BanglaBERT. Cross-language analysis reveals substantial performance differences across models and linguistic representations, while removing dialogue history reduces intent accuracy by 19.0--25.7 percentage points. BanglaTOD provides a foundation for multilingual dialogue understanding and future dialogue state tracking research in Bangladesh-specific conversational applications. The dataset is publicly available at hrefhttps://huggingface.co/datasets/afri7here/BanglaTODHugging Face.