Thien Hai Nguyen


pdf bib
Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings
Linlin Liu | Thien Hai Nguyen | Shafiq Joty | Lidong Bing | Luo Si
Proceedings of the 29th International Conference on Computational Linguistics

Cross-lingual word embeddings (CLWE) have been proven useful in many cross-lingual tasks. However, most existing approaches to learn CLWE including the ones with contextual embeddings are sense agnostic. In this work, we propose a novel framework to align contextual embeddings at the sense level by leveraging cross-lingual signal from bilingual dictionaries only. We operationalize our framework by first proposing a novel sense-aware cross entropy loss to model word senses explicitly. The monolingual ELMo and BERT models pretrained with our sense-aware cross entropy loss demonstrate significant performance improvement for word sense disambiguation tasks. We then propose a sense alignment objective on top of the sense-aware cross entropy loss for cross-lingual model pretraining, and pretrain cross-lingual models for several language pairs (English to German/Spanish/Japanese/Chinese). Compared with the best baseline results, our cross-lingual models achieve 0.52%, 2.09% and 1.29% average performance improvements on zero-shot cross-lingual NER, sentiment classification and XNLI tasks, respectively.


pdf bib
Improving Low-Resource Named Entity Recognition using Joint Sentence and Token Labeling
Canasai Kruengkrai | Thien Hai Nguyen | Sharifah Mahani Aljunied | Lidong Bing
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Exploiting sentence-level labels, which are easy to obtain, is one of the plausible methods to improve low-resource named entity recognition (NER), where token-level labels are costly to annotate. Current models for jointly learning sentence and token labeling are limited to binary classification. We present a joint model that supports multi-class classification and introduce a simple variant of self-attention that allows the model to learn scaling factors. Our model produces 3.78%, 4.20%, 2.08% improvements in F1 over the BiLSTM-CRF baseline on e-commerce product titles in three different low-resource languages: Vietnamese, Thai, and Indonesian, respectively.

pdf bib
DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks
Bosheng Ding | Linlin Liu | Lidong Bing | Canasai Kruengkrai | Thien Hai Nguyen | Shafiq Joty | Luo Si | Chunyan Miao
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Data augmentation techniques have been widely used to improve machine learning performance as they facilitate generalization. In this work, we propose a novel augmentation method to generate high quality synthetic data for low-resource tagging tasks with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings. For the supervised settings, we conduct extensive experiments on named entity recognition (NER), part of speech (POS) tagging and end-to-end target based sentiment analysis (E2E-TBSA) tasks. For the semi-supervised settings, we evaluate our method on the NER task under the conditions of given unlabeled data only and unlabeled data plus a knowledge base. The results show that our method can consistently outperform the baselines, particularly when the given gold training data are less.


pdf bib
PhraseRNN: Phrase Recursive Neural Network for Aspect-based Sentiment Analysis
Thien Hai Nguyen | Kiyoaki Shirai
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Topic Modeling based Sentiment Analysis on Social Media for Stock Market Prediction
Thien Hai Nguyen | Kiyoaki Shirai
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)