I’m a Postdoctoral Associate in the Westlake NLP group, working with Yue Zhang. Previously, I graduated with a PhD from the Insight Centre, University College Dublin, where I worked with Barry Smyth and Ruihai Dong.
I am broadly interested in the problem of Data-centric AI and Trustworthy AI, improving the transparency and generalization of neural networks for natural language understanding. To achieve this goal, I am now working on causality guided methods for NLP and its applications in high-stake domains. Feel free to contact me via email if you have any questions about our research work.
PhD in Artificial Intelligence, 2017-2021
University College Dublin
MSc in Artificial Intelligence, 2017
University College Dublin
BSc in Computer Science, 2016
Harbin Engineering University
This paper describes a numeric-oriented hierarchical transformer model (NumHTML) to predict stock returns, and financial risk using multi-modal aligned earnings calls data by taking advantage of the different categories of numbers (monetary, temporal, percentages etc.) and their magnitude.
We demonstrate the success of deep learning methods in modeling unstructured data for financial applications, including explainable deep learning models, multi-modal multi- task learning frameworks, and counterfactual generation systems for explanations and data augmentations.
While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that may exist in their training and test data.
This paper proposes a novel methodology for producing plausible counterfactual explanations, whilst exploring the regularization benefits of adversarial training on language models in the domain of FinTech. Exhaustive quantitative experiments demonstrate that not only does this approach improve the model accuracy when compared to the current state-of-the-art and human performance, but it also generates counterfactual explanations which are significantly more plausible based on human trials.
We present the approach used in this work as providing a suitable framework for processing similar forms of data in the future. The resulting dataset is more than six times larger than those currently available to the research community and we discuss its potential in terms of current and future research challenges and opportunities.
This paper proposes a novel hierarchical, transformer, multi-task architecture designed to harness the text and audio data from quarterly earnings conference calls to predict future price volatility in the short and long term. This includes a comprehensive comparison to a variety of baselines, which demonstrates very significant improvements in prediction accuracy, in the range 17% - 49% compared to the current state-of-the-art.
In this paper, we take into account the semantics of the FEARS search terms by leveraging the Bidirectional Encoder Representations from Transformers (BERT), and further apply a self-attention deep learning model to our refined FEARS seamlessly for stock return prediction.
We use an output attention mechanism to allocate different weights to different days in terms of their contribution to stock price movement. Thorough empirical studies based upon historical prices of several individual stocks demonstrate the superiority of our proposed method in stock price prediction compared to state-of-the-art methods
We propose a dual-level attention mechanism for the relation extraction problem
We propose a dual-level attention mechanism for the relation extraction problem