Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings

1 code implementation • COLING 2022 • Linlin Liu, Thien Hai Nguyen, Shafiq Joty, Lidong Bing, Luo Si

We operationalize our framework by first proposing a novel sense-aware cross entropy loss to model word senses explicitly.

Cross-Lingual NER Cross-Lingual Word Embeddings +5

DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks

no code implementations • EMNLP 2020 • Bosheng Ding, Linlin Liu, Lidong Bing, Canasai Kruengkrai, Thien Hai Nguyen, Shafiq Joty, Luo Si, Chunyan Miao

Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models.

Data Augmentation named-entity-recognition +6

Improving Low-Resource Named Entity Recognition using Joint Sentence and Token Labeling

no code implementations • ACL 2020 • Canasai Kruengkrai, Thien Hai Nguyen, Sharifah Mahani Aljunied, Lidong Bing

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.

Binary Classification Classification +7

PhraseRNN: Phrase Recursive Neural Network for Aspect-based Sentiment Analysis

no code implementations • EMNLP 2015 • Thien Hai Nguyen, Kiyoaki Shirai

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Topic Modeling based Sentiment Analysis on Social Media for Stock Market Prediction

no code implementations • IJCNLP 2015 • Thien Hai Nguyen, Kiyoaki Shirai

Sentiment Analysis Stock Prediction