# Cross-Language Speaker Attribute Prediction Using MIL and RL

arXiv: https://arxiv.org/abs/2601.04257 · HTML: https://mlsanity.com/paper/2601.04257/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 47 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [Adversarial Dropout Regularization](https://mlsanity.com/paper/1711.01575/) (2017)
- [Learning how to Active Learn: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1708.02383/) (2017)
- [Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification](https://mlsanity.com/paper/1606.01614/) (2016)
- [Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition](https://mlsanity.com/paper/2002.10361/) (2020)
- [Evaluating and Modeling Attribution for Cross-Lingual Question Answering](https://mlsanity.com/paper/2305.14332/) (2023)
- [VoxCeleb Enrichment for Age and Gender Recognition](https://mlsanity.com/paper/2109.13510/) (2021)
- [Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification](https://mlsanity.com/paper/2007.15072/) (2020)
- [Cross-language Learning with Adversarial Neural Networks: Application to Community Question Answering](https://mlsanity.com/paper/1706.06749/) (2017)
- [Learning How to Self-Learn: Enhancing Self-Training Using Neural Reinforcement Learning](https://mlsanity.com/paper/1804.05734/) (2018)
- [Predicting gender and age categories in English conversations using lexical, non-lexical, and turn-taking features](https://mlsanity.com/paper/2102.13355/) (2021)
- [Language Barriers: Evaluating Cross-Lingual Performance of CNN and Transformer Architectures for Speech Quality Estimation](https://mlsanity.com/paper/2502.13004/) (2025)

## Built on by (most cited first, 1 of 1)

- [Integrating Fairness and Explainability in a Multiple Instance Reinforcement Learning System](https://mlsanity.com/paper/2610.00035/) (2026)

## Abstract (arXiv)

We study multilingual speaker attribute prediction under linguistic variation, domain mismatch, and data imbalance across languages. We propose RLMIL-DAT, a multilingual extension of the reinforced multiple instance learning framework that combines reinforcement learning based instance selection with domain adversarial training to encourage language invariant utterance representations. We evaluate the approach on a five language Twitter corpus in a few shot setting and on a VoxCeleb2 derived corpus covering forty languages in a zero shot setting for gender and age prediction. Across a wide range of model configurations and multiple random seeds, RLMIL-DAT consistently improves Macro F1 compared to standard multiple instance learning and the original reinforced multiple instance learning framework. The largest gains are observed for gender prediction, while age prediction remains more challenging and shows smaller but positive improvements. Ablation experiments indicate that domain adversarial training is the primary contributor to the performance gains, enabling effective transfer from high resource English to lower resource languages by discouraging language specific cues in the shared encoder. In the zero shot setting on the smaller VoxCeleb2 subset, improvements are generally positive but less consistent, reflecting limited statistical power and the difficulty of generalizing to many unseen languages. Overall, the results demonstrate that combining instance selection with adversarial domain adaptation is an effective and robust strategy for cross lingual speaker attribute prediction.