Search Results for author: Xian Li

Found 27 papers, 9 papers with code

Lifting the Curse of Multilinguality by Pre-training Modular Transformers

no code implementations12 May 2022 Jonas Pfeiffer, Naman Goyal, Xi Victoria Lin, Xian Li, James Cross, Sebastian Riedel, Mikel Artetxe

Multilingual pre-trained models are known to suffer from the curse of multilinguality, which causes per-language performance to drop as they cover more languages.

Named Entity Recognition Natural Language Inference +1

OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision

1 code implementation29 Apr 2022 Xinyang Zhang, Chenwei Zhang, Xian Li, Xin Luna Dong, Jingbo Shang, Christos Faloutsos, Jiawei Han

Most prior works on this matter mine new values for a set of known attributes but cannot handle new attributes that arose from constantly changing data.

Language Modelling

ATST: Audio Representation Learning with Teacher-Student Transformer

2 code implementations26 Apr 2022 Xian Li, Xiaofei Li

Self-supervised learning (SSL) learns knowledge from a large amount of unlabeled data, and then transfers the knowledge to a specific problem with a limited number of labeled data.

 Ranked #1 on Speaker Identification on VoxCeleb1 (Accuracy metric)

Audio Classification Instrument Recognition +5

Few-shot Learning with Multilingual Language Models

1 code implementation20 Dec 2021 Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O'Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyanov, Xian Li

In this work, we train multilingual autoregressive language models on a balanced corpus covering a diverse set of languages, and study their few- and zero-shot learning capabilities in a wide range of tasks.

Few-Shot Learning Hate Speech Detection +4

Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs

1 code implementation26 Nov 2021 Peter Hase, Mona Diab, Asli Celikyilmaz, Xian Li, Zornitsa Kozareva, Veselin Stoyanov, Mohit Bansal, Srinivasan Iyer

In this paper, we discuss approaches to detecting when models have beliefs about the world, and we improve on methods for updating model beliefs to be more truthful, with a focus on methods based on learned optimizers or hypernetworks.

Distributionally Robust Multilingual Machine Translation

1 code implementation EMNLP 2021 Chunting Zhou, Daniel Levy, Xian Li, Marjan Ghazvininejad, Graham Neubig

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models.

Machine Translation Translation

Multilingual Speech Translation from Efficient Finetuning of Pretrained Models

no code implementations ACL 2021 Xian Li, Changhan Wang, Yun Tang, Chau Tran, Yuqing Tang, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation through efficient transfer learning from a pretrained speech encoder and text decoder.

Text Generation Transfer Learning +1

FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task

no code implementations ACL (IWSLT) 2021 Yun Tang, Hongyu Gong, Xian Li, Changhan Wang, Juan Pino, Holger Schwenk, Naman Goyal

In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task.

Transfer Learning Translation

Unaware Fairness: Hierarchical Random Forest for Protected Classes

no code implementations30 Jun 2021 Xian Li

Procedural fairness has been a public concern, which leads to controversy when making decisions with respect to protected classes, such as race, social status, and disability.

Fairness

Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling

no code implementations NeurIPS 2021 Hongyu Gong, Yun Tang, Juan Pino, Xian Li

We further propose attention sharing strategies to facilitate parameter sharing and specialization in multilingual and multi-domain sequence modeling.

Speech Recognition Speech-to-Text Translation +1

Adaptive Sparse Transformer for Multilingual Translation

no code implementations15 Apr 2021 Hongyu Gong, Xian Li, Dmitriy Genzel

Based on these insights, we propose an adaptive and sparse architecture for multilingual modeling, and train the model to learn shared and language-specific parameters to improve the positive transfer and mitigate the interference.

Machine Translation Transfer Learning +1

Robust Optimization for Multilingual Translation with Imbalanced Data

no code implementations NeurIPS 2021 Xian Li, Hongyu Gong

We show that common training method which upsamples low resources can not robustly optimize population loss with risks of either underfitting high resource languages or overfitting low resource ones.

Machine Translation Translation

Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders

no code implementations EACL 2021 Xiang Kong, Adithya Renduchintala, James Cross, Yuqing Tang, Jiatao Gu, Xian Li

Recent work in multilingual translation advances translation quality surpassing bilingual baselines using deep transformer models with increased capacity.

Machine Translation Translation

Improving Zero-Shot Translation by Disentangling Positional Information

1 code implementation ACL 2021 Danni Liu, Jan Niehues, James Cross, Francisco Guzmán, Xian Li

The difficulty of generalizing to new translation directions suggests the model representations are highly specific to those language pairs seen in training.

Machine Translation Translation

Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms

1 code implementation29 Dec 2020 Yilun Zhou, Adithya Renduchintala, Xian Li, Sida Wang, Yashar Mehdad, Asish Ghoshal

Active learning (AL) algorithms may achieve better performance with fewer data because the model guides the data selection process.

Active Learning

Multilingual Speech Translation with Efficient Finetuning of Pretrained Models

no code implementations24 Oct 2020 Xian Li, Changhan Wang, Yun Tang, Chau Tran, Yuqing Tang, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder.

Cross-Lingual Transfer Text Generation +2

DeFuzz: Deep Learning Guided Directed Fuzzing

no code implementations23 Oct 2020 Xiaogang Zhu, Shigang Liu, Xian Li, Sheng Wen, Jun Zhang, Camtepe Seyit, Yang Xiang

Fuzzing is one of the most effective technique to identify potential software vulnerabilities.

Vulnerability Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.