Billy Chiu


2020

pdf bib
Autoencoding Keyword Correlation Graph for Document Clustering
Billy Chiu | Sunil Kumar Sahu | Derek Thomas | Neha Sengupta | Mohammady Mahdy
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Document clustering requires a deep understanding of the complex structure of long-text; in particular, the intra-sentential (local) and inter-sentential features (global). Existing representation learning models do not fully capture these features. To address this, we present a novel graph-based representation for document clustering that builds a graph autoencoder (GAE) on a Keyword Correlation Graph. The graph is constructed with topical keywords as nodes and multiple local and global features as edges. A GAE is employed to aggregate the two sets of features by learning a latent representation which can jointly reconstruct them. Clustering is then performed on the learned representations, using vector dimensions as features for inducing document classes. Extensive experiments on two datasets show that the features learned by our approach can achieve better clustering performance than other existing features, including term frequency-inverse document frequency and average embedding.

2019

pdf bib
Enhancing biomedical word embeddings by retrofitting to verb clusters
Billy Chiu | Simon Baker | Martha Palmer | Anna Korhonen
Proceedings of the 18th BioNLP Workshop and Shared Task

Verbs play a fundamental role in many biomed-ical tasks and applications such as relation and event extraction. We hypothesize that performance on many downstream tasks can be improved by aligning the input pretrained embeddings according to semantic verb classes. In this work, we show that by using semantic clusters for verbs, a large lexicon of verbclasses derived from biomedical literature, weare able to improve the performance of common pretrained embeddings in downstream tasks by retrofitting them to verb classes. We present a simple and computationally efficient approach using a widely-available “off-the-shelf” retrofitting algorithm to align pretrained embeddings according to semantic verb clusters. We achieve state-of-the-art results on text classification and relation extraction tasks.

2016

pdf bib
Intrinsic Evaluation of Word Vectors Fails to Predict Extrinsic Performance
Billy Chiu | Anna Korhonen | Sampo Pyysalo
Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP

pdf bib
How to Train good Word Embeddings for Biomedical NLP
Billy Chiu | Gamal Crichton | Anna Korhonen | Sampo Pyysalo
Proceedings of the 15th Workshop on Biomedical Natural Language Processing

pdf bib
Syllable based DNN-HMM Cantonese Speech to Text System
Timothy Wong | Claire Li | Sam Lam | Billy Chiu | Qin Lu | Minglei Li | Dan Xiong | Roy Shing Yu | Vincent T.Y. Ng
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

This paper reports our work on building up a Cantonese Speech-to-Text (STT) system with a syllable based acoustic model. This is a part of an effort in building a STT system to aid dyslexic students who have cognitive deficiency in writing skills but have no problem expressing their ideas through speech. For Cantonese speech recognition, the basic unit of acoustic models can either be the conventional Initial-Final (IF) syllables, or the Onset-Nucleus-Coda (ONC) syllables where finals are further split into nucleus and coda to reflect the intra-syllable variations in Cantonese. By using the Kaldi toolkit, our system is trained using the stochastic gradient descent optimization model with the aid of GPUs for the hybrid Deep Neural Network and Hidden Markov Model (DNN-HMM) with and without I-vector based speaker adaptive training technique. The input features of the same Gaussian Mixture Model with speaker adaptive training (GMM-SAT) to DNN are used in all cases. Experiments show that the ONC-based syllable acoustic modeling with I-vector based DNN-HMM achieves the best performance with the word error rate (WER) of 9.66% and the real time factor (RTF) of 1.38812.