Diego Mollá Aliod
Curriculum Vitae
|
||||||||||||||||||||||
Research Topics | ||||||||||||||||||||||
Natural Language Processing. Text-based Question Answering. Information Extraction. Text Summarisation. Medical Texts. |
Most Significant Research Contributions
My research contribution is centered on the application of theoretical linguistics to specific real-world problems, in particular to automated text-based question answering and summarisation. Since 2009 I have focused on medical text processing.
I joined the University of Zurich and became the principal researcher in the ExtrAns and WebExtrAns projects (from 1996 to 2001). Both projects were based on the development of answer extraction systems. Answer extraction systems locate those sentences in the source text that contain the answer posed by the user. The outcome of the project was a working system that handles questions about 500 Linux/Unix documentation documents ("manpages"). I was the principal designer of the overall system and the integration of all modules. I was also the principal contributor to the design of the logical forms and the question-answering method that used the logical forms. The success of ExtrAns and WebExtrAns is evident from the fact that the system is cited as a pioneering question-answering system, an example of a question answering system of technical domains, and an example of the use of logical forms for question answering.
In Macquarie University I established the AnswerFinder project. AnswerFinder is a question answering system that combines the use of logical information (inspired from ExtrAns and WebExtrAns), state-of-the-art approaches in question answering, and innovative graph-based machine learning methods to find the exact answer to the user question. AnswerFinder has participated in the question answering track of the Text REtrieval conference (TREC), the main international forum for the evaluation of question-answering systems, between 2003 and 2006. AnswerFinder is in fact the only Australian-based question answering system that has participated in the question answering track of TREC.
Since 2009 I have led various projects related to the development and application of text-processing technologies that help the medical doctor find and appraise clinical evidence found in the vast resources of medical publications. I have gathered a summarisation corpus sourced from the Journal of Family Practice, and used the corpus to develop and evaluate techniques for text summarisation, clustering, keyword exraction, and appraisal of the medical evidence.
Publications
See https://researchers.mq.edu.au/en/persons/diego-molla-aliod/publications/
Teaching
Years | Organization | Level | Topic |
2001-pres | Macquarie University | Undergraduate and postgraduate lectures | Computing and Language Technology |
1995-96 | The University of Edinburgh | Postgraduate lectures | Logic |
1990-91 | Universitat Politècnica de València | Undergraduate lectures | Theory of Programming |
Doctoral Supervision and Review
I have supervised the following PhD students:
- Abeed Sarker (2013). Automatic Medical Summarisation to Support Evidence-based Medicine. [local copy]. Currently an Assistant Professor at Emory University School of Medicine, Atlanta, Georgia.
- Luiz Pizzato (2009). Using Linguistically Motivated Features in Document Retrieval for Question Answering. [local copy]. Co-founder of Octosocial, currently Head of Data Science, Liquid Studio ANZ at Accenture.
- Jean-Philippe Prost (2008). Modelling Syntactic Gradience with Loose Constraint-based Parsing. [local copy]. Currently a lecturer at Université Montpellier.
I have supervised the following Master of Research students:
- Urvashi Kanna (2021). Gradual Unfreezing Transformer-based Language Models for Biomedical Question Answering.
- Dima Galat (2020). Sequential Transfer Learning for Text Summarisation.
- Christopher Jones (2020). Reinforcement Learning for Query-based Multi-document Extractive Summarisation.
- Mandeep Kaur (2018). Supervised Machine Learning for Extractive Query Based Summarisation of Biomedical Data.
- Jiwei Wang (2016). Keyword and Keyphrase Extraction Techniques for Answering Biomedical Questions.
Postdoctoral Research Positions |
|||
Years | Organization & Department | Location | Job Title |
2005-pres | Macquarie University, Computing | Sydney, Australia | Senior Lecturer |
Continuing member of the Centre for Language Technology (CLT); continuing research on question answering; research on text processing for medical applications. | |||
2001-2004 | Macquarie University, Computing | Sydney, Australia | Lecturer |
Founding member of the Centre for Language Technology (CLT) in the Division of Information and Communication Sciences (currently, CLT is a research group of the Department of Computing at the Faculty of Science and Engineering) ; research in the extension of ExtrAns (see below) to perform more general question answering over larger volumes of data. | |||
2000-01 | University of Zurich, Computational Linguistics | Zurich, Switzerland | Senior Research Assistant |
Extension of ExtrAns (see below) to WebExtrAns, a help-system over text documents formatted in XML. The test text was the maintenance manual of an Airbus commercial aircraft. | |||
1996-99 | University of Zurich, Computational Linguistics | Zurich, Switzerland | Senior Research Assistant |
Design and implementation of ExtrAns. The goal of ExtrAns is to parse and build the logical form of the query given by users (in plain English), and then extract those sentences whose logical forms can prove that of the query, from the manual pages. The project is funded by the Swiss National Fund. | |||
Postgraduate Studies |
|||
Years | Organization & Department | Location | Course |
1992-96 | University of Edinburgh, Linguistics | Edinburgh, UK | PhD in Aspect Composition |
Dissertation on Aspectual Composition and Sentence Interpretation: A formal approach. | |||
1994-95 | Took leave and completed 1 year compulsory social service in Spain. | ||
1991-92 | University of Edinburgh, Linguistics | Edinburgh, UK | MSc in Speech and Language Processing |
Dissertation on Integrating time into Discourse Representation Theory: A computational approach. | |||
Graduated with Distinction. | |||
1990-91 | Universitat Politècnica de València, Computer Science | Valencia, Spain | Research in Pattern Recognition and Artificial Intelligence |
Automatic pattern recognition and its application to Speech Recognition and Computer Vision. | |||
Undergraduate Studies |
|||
Years | Organization | Location | Course |
1985-90 | Universitat Politècnica de València | Valencia, Spain | 5-yr degree in Computer Science |
Dissertation on Inference of k-testable languages | |||
Graduated with Distinction. | |||
Awarded with the Third National Prize to the best degree in Computer Science (Tercer Premio Nacional de Terminación de Estudios de Lienciatura en Informática) by the Spanish Ministry of Education and Science (Ministerio de Educación y Ciencia). |
Grants
Note that, unless otherwise specified, all figures are in Australian Dollars, rounded to the nearest $1,000.
Years | Source of Funding | Amount | Chief Investigators |
2022-2024 | ARC Discovery | $480,000 | John Yearwood, Vicky Mak, Bahadorreza Ofoghi, William Moran, D. Mollá |
An intelligent machine modelling assistant for combinatorial optimisation | |||
2017 | Macquarie University Outside Studies Program | $7,000 | D. Mollá |
Exploration of Deep Learning Techniques for Text Mining | |||
2013 | Macquarie University Research Infrastructure Block Grant | $77,000 | M. Dras, M. Johnson, B. Mans, D. Mollá, M. Honnibal |
A GPU-based Cluster for Computing | |||
2013 | Macquarie University Outside Studies Program | $4,000 | D. Mollá |
Application of Bayesian inference techniques to natural language processing of medical text | |||
2011-12 | Australia-India Strategic Research Fund, workshop | $23,000 | D. Mollá |
2010 | Macquarie University Research Development Grant (MQRDG) | $35,000 | D. Mollá |
Generation and Evaluation of Clinical Evidence-based Summaries on Demand | |||
2009 | ORISE - National Library of Medicine | USD3,000 + air ticket | D. Mollá |
Visit to the National Library of Medicine | |||
2005 | Macquarie University Safety Net | $19,898 | S. Cassidy, D. Mollá |
Information Access in Meeting Room Speech Archives | |||
2004 | Macquarie University MURDG | $5,200 | D. Mollá, M. Dras | Visit of Dr. Philippe Blache to enhance the development of new techniques for robust parsing and language understanding |
2004-06 | ARC Discovery | $290,000 | D. Mollá, R. Dale | A scalable and portable question-answering system |
2003-05 | ARC Linkage | $56,000 | D. Richards, D. Mollá, R. Schwitter | Achieving higher availability of storage subsystems through application of a self learning expert system. |
2001 | Macquarie University MUNS | $18,000 | D. Mollá | A fast and robust logical form generator using a third-party shallow parser. |
References
Available on request.