Long Duong | University of Melbourne (original) (raw)

Uploads

Papers by Long Duong

Research paper thumbnail of Two decades of ecohydraulics: trends of an emerging interdiscipline

We assessed how the emerging field of ecohydraulics research has changed over two decades by exam... more We assessed how the emerging field of ecohydraulics research has changed over two decades by examining the proceedings of the biennial International Symposium on Ecohydraulics. By using Natural Language Processing (NLP) in word usage, this paper provides a deep analysis of a longitudinal dataset and enables us to test more detailed questions than previous snapshots of the ecohydraulics literature. We formulated three main hypotheses related to the degree of multidisciplinarity, interdisciplinarity and transdisciplinarity within ecohydraulics. We investigated
temporal changes in author affiliation patterns and identified dominant topics of research. The total number of proceeding papers has increased over time and the field is becoming increasingly global. This and the identification of 10 distinctive macro-topics suggest well-developed multidisciplinarity in ecohydraulics. There has been reasonable stability in individual topics across time, except for 11 (out of 51) significant trends within the macro-topics of Fish responses, Hydraulic modelling, Water quality, Physical habitat modelling and Social responses, suggesting some increase in interdisciplinarity. The proportion of practitioners collaborating with researchers has surprisingly not changed greatly over time, indicating ecohydraulics has been transdisciplinary to some extent from its inception. Our results arguably provide an opportunity to better integrate fundamental understanding into practical applications in water management.

Research paper thumbnail of UniMelb at SemEval-2016 Task 3: Identifying Similar Questions by combining a CNN with String Similarity Measures

This paper describes the results of the participation of The University of Melbourne in the commu... more This paper describes the results of the participation of The University of Melbourne in the community question-answering (CQA) task of SemEval 2016 (Task 3-B). We obtained a MAP score of 70.2% on the test set, by combining three classifiers: a NaiveBayes classifier and a support vector machine (SVM) each trained over lexical similarity features, and a convolutional neural network (CNN). The CNN uses word embeddings and machine translation evaluation scores as features.

Research paper thumbnail of Cross-lingual Transfer for Unsupervised Dependency Parsing Without Parallel Data

Proceedings of the Nineteenth Conference on Computational Natural Language Learning, 2015

Research paper thumbnail of Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 2015

Research paper thumbnail of Exploring Methods and Resources for Discriminating Similar Languages

Proceedings of the First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects, 2014

Research paper thumbnail of What Can We Get From 1000 Tokens? A Case Study of Multilingual POS Tagging For Resource-Poor Languages

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014

Research paper thumbnail of Increasing the quality and quantity of source language data for unsupervised cross-lingual POS tagging

Research paper thumbnail of Automatic identification of expressions of locations in tweet messages using conditional random fields

Research paper thumbnail of Simpler unsupervised POS tagging with bilingual projections

Research paper thumbnail of A Neural Network Model for Low-Resource Universal Dependency Parsing

Accurate dependency parsing requires large treebanks, which are only available for a few language... more Accurate dependency parsing requires large treebanks, which are only available for a few languages. We propose a method that takes advantage of shared structure across languages to build a mature parser using less training data. We propose a model for learning a shared "universal" parser that operates over an interlingual continuous representation of language, along with language-specific mapping components. Compared with supervised learning, our methods give a consistent 8-10% improvement across several treebanks in low-resource simulations.

Research paper thumbnail of Two decades of ecohydraulics: trends of an emerging interdiscipline

We assessed how the emerging field of ecohydraulics research has changed over two decades by exam... more We assessed how the emerging field of ecohydraulics research has changed over two decades by examining the proceedings of the biennial International Symposium on Ecohydraulics. By using Natural Language Processing (NLP) in word usage, this paper provides a deep analysis of a longitudinal dataset and enables us to test more detailed questions than previous snapshots of the ecohydraulics literature. We formulated three main hypotheses related to the degree of multidisciplinarity, interdisciplinarity and transdisciplinarity within ecohydraulics. We investigated
temporal changes in author affiliation patterns and identified dominant topics of research. The total number of proceeding papers has increased over time and the field is becoming increasingly global. This and the identification of 10 distinctive macro-topics suggest well-developed multidisciplinarity in ecohydraulics. There has been reasonable stability in individual topics across time, except for 11 (out of 51) significant trends within the macro-topics of Fish responses, Hydraulic modelling, Water quality, Physical habitat modelling and Social responses, suggesting some increase in interdisciplinarity. The proportion of practitioners collaborating with researchers has surprisingly not changed greatly over time, indicating ecohydraulics has been transdisciplinary to some extent from its inception. Our results arguably provide an opportunity to better integrate fundamental understanding into practical applications in water management.

Research paper thumbnail of UniMelb at SemEval-2016 Task 3: Identifying Similar Questions by combining a CNN with String Similarity Measures

This paper describes the results of the participation of The University of Melbourne in the commu... more This paper describes the results of the participation of The University of Melbourne in the community question-answering (CQA) task of SemEval 2016 (Task 3-B). We obtained a MAP score of 70.2% on the test set, by combining three classifiers: a NaiveBayes classifier and a support vector machine (SVM) each trained over lexical similarity features, and a convolutional neural network (CNN). The CNN uses word embeddings and machine translation evaluation scores as features.

Research paper thumbnail of Cross-lingual Transfer for Unsupervised Dependency Parsing Without Parallel Data

Proceedings of the Nineteenth Conference on Computational Natural Language Learning, 2015

Research paper thumbnail of Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 2015

Research paper thumbnail of Exploring Methods and Resources for Discriminating Similar Languages

Proceedings of the First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects, 2014

Research paper thumbnail of What Can We Get From 1000 Tokens? A Case Study of Multilingual POS Tagging For Resource-Poor Languages

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014

Research paper thumbnail of Increasing the quality and quantity of source language data for unsupervised cross-lingual POS tagging

Research paper thumbnail of Automatic identification of expressions of locations in tweet messages using conditional random fields

Research paper thumbnail of Simpler unsupervised POS tagging with bilingual projections

Research paper thumbnail of A Neural Network Model for Low-Resource Universal Dependency Parsing

Accurate dependency parsing requires large treebanks, which are only available for a few language... more Accurate dependency parsing requires large treebanks, which are only available for a few languages. We propose a method that takes advantage of shared structure across languages to build a mature parser using less training data. We propose a model for learning a shared "universal" parser that operates over an interlingual continuous representation of language, along with language-specific mapping components. Compared with supervised learning, our methods give a consistent 8-10% improvement across several treebanks in low-resource simulations.

Log In