# XL-NBT: A Cross-lingual Neural Belief Tracking Framework

arXiv: https://arxiv.org/abs/1808.06244 · HTML: https://mlsanity.com/paper/1808.06244/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2018.

## Built on by (most cited first, 7 of 7)

- [Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.08570/) (2021)
- [Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking](https://mlsanity.com/paper/2109.13620/) (2021)
- [Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues](https://mlsanity.com/paper/2111.02574/) (2021)
- [Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks](https://mlsanity.com/paper/2111.01340/) (2021)
- [X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing](https://mlsanity.com/paper/2106.03777/) (2021)
- [Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation](https://mlsanity.com/paper/2302.09424/) (2023)
- [XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking](https://mlsanity.com/paper/2204.05895/) (2022)

## Abstract (arXiv)

Task-oriented dialog systems are becoming pervasive, and many companies heavily rely on them to complement human agents for customer service in call centers. With globalization, the need for providing cross-lingual customer support becomes more urgent than ever. However, cross-lingual support poses great challenges---it requires a large amount of additional annotated data from native speakers. In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework. Specifically, we assume that there exists a source language with dialog belief tracking annotations while the target languages have no annotated dialog data of any form. Then, we pre-train a state tracker for the source language as a teacher, which is able to exploit easy-to-access parallel data. We then distill and transfer its own knowledge to the student state tracker in target languages. We specifically discuss two types of common parallel resources: bilingual corpus and bilingual dictionary, and design different transfer learning strategies accordingly. Experimentally, we successfully use English state tracker as the teacher to transfer its knowledge to both Italian and German trackers and achieve promising results.