# CalibreNet: Calibration Networks for Multilingual Sequence Labeling

arXiv: https://arxiv.org/abs/2011.05723 · HTML: https://mlsanity.com/paper/2011.05723/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [From Good to Best: Two-Stage Training for Cross-lingual Machine Reading Comprehension](https://mlsanity.com/paper/2112.04735/) (2021)
- [Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling](https://mlsanity.com/paper/2204.05210/) (2022)
- [Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension](https://mlsanity.com/paper/2204.00996/) (2022)
- [Sharing, Teaching and Aligning: Knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension](https://mlsanity.com/paper/2311.06758/) (2023)
- [Uncertainty Quantification for Named Entity Recognition via Full-Sequence and Subsequence Conformal Prediction](https://mlsanity.com/paper/2601.16999/) (2026)

## Abstract (arXiv)

Lack of training data in low-resource languages presents huge challenges to sequence labeling tasks such as named entity recognition (NER) and machine reading comprehension (MRC). One major obstacle is the errors on the boundary of predicted answers. To tackle this problem, we propose CalibreNet, which predicts answers in two steps. In the first step, any existing sequence labeling method can be adopted as a base model to generate an initial answer. In the second step, CalibreNet refines the boundary of the initial answer. To tackle the challenge of lack of training data in low-resource languages, we dedicatedly develop a novel unsupervised phrase boundary recovery pre-training task to enhance the multilingual boundary detection capability of CalibreNet. Experiments on two cross-lingual benchmark datasets show that the proposed approach achieves SOTA results on zero-shot cross-lingual NER and MRC tasks.