LSTM-based Deep Learning Models for non-factoid answer selection
- M. Tan, Bing Xiang, Bowen Zhou
- Computer ScienceArXiv
- 12 November 2015
A general deep learning framework is applied for the answer selection task, which does not depend on manually defined features or linguistic tools, and is extended in two directions to define a more composite representation for questions and answers.
Attentive Pooling Networks
- C. D. Santos, M. Tan, Bing Xiang, Bowen Zhou
- Computer ScienceArXiv
- 11 February 2016
The empirical results, from three very different benchmark tasks of question answering/answer selection, demonstrate that the proposed models outperform a variety of strong baselines and achieve state-of-the-art performance in all the benchmarks.
Improved Representation Learning for Question Answer Matching
- M. Tan, C. D. Santos, Bing Xiang, Bowen Zhou
- Computer ScienceAnnual Meeting of the Association for…
- 1 August 2016
This work develops hybrid models that process the text using both convolutional and recurrent neural networks, combining the merits on extracting linguistic information from both structures to address passage answer selection.
Multi-Agent Reinforcement Learning: Independent versus Cooperative Agents
- M. Tan
- Computer ScienceInternational Conference on Machine Learning
- 1 October 1997
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers
- Haoyu Wang, M. Tan, Saloni Potdar
- Computer ScienceAnnual Meeting of the Association for…
- 4 February 2019
This work focuses on the task of multiple relation extractions by encoding the paragraph only once, and builds the solution upon the pre-trained self-attentive models (Transformer), where it is shown that the approach is not only scalable but can also perform state-of-the-art on the standard benchmark ACE 2005.
Cost-sensitive learning of classification knowledge and its applications in robotics
- M. Tan
- Computer ScienceMachine-mediated learning
- 2004
A unified framework for learning-from-examples methods that trade off accuracy for efficiency during learning is proposed, and two methods (CS-ID3 and CS-IBL) are analyzed in detail.
Out-of-Domain Detection for Low-Resource Text Classification Tasks
Evaluations on real-world datasets show that the proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task, while maintaining a competitive performance on ID classification task.
MOLE: A Tenacious Knowledge-Acquisition Tool
- L. Eshelman, D. Ehret, J. McDermott, M. Tan
- Computer ScienceInt. J. Man Mach. Stud.
- 1987
Using Weighted Networks to Represent Classification Knowledge in Noisy Domains
- M. Tan, L. Eshelman
- Computer ScienceML Workshop
- 1988
Cost-Sensitive Concept Learning of Sensor Use in Approach ad Recognition
- M. Tan, J. C. Schlimmer
- Computer ScienceML Workshop
- 1 December 1989
...
...