Computing and Information Systems - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 16
-
ItemCross-linguistic comparison of linguistic feature encoding in BERT models for typologically different languages(Association for Computational Linguistics, 2022-01-01)Though recently there have been an increased interest in how pre-trained language models encode different linguistic features, there is still a lack of systematic comparison between languages with different morphology and syntax. In this paper, using BERT as an example of a pre-trained model, we compare how three typologically different languages (English, Korean, and Russian) encode morphology and syntax features across different layers. In particular, we contrast languages which differ in a particular aspect, such as flexibility of word order, head directionality, morphological type, presence of grammatical gender, and morphological richness, across four different tasks.
-
ItemThe patient is more dead than alive: exploring the current state of the multi-document summarization of the biomedical literature(ASSOC COMPUTATIONAL LINGUISTICS-ACL, 2022)
-
ItemWhat does it take to bake a cake? The RecipeRef corpus and anaphora resolution in procedural text(ASSOC COMPUTATIONAL LINGUISTICS-ACL, 2022)
-
ItemMemorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation(ASSOC COMPUTATIONAL LINGUISTICS-ACL, 2021)
-
ItemChEMU-Ref: A corpus for modeling anaphora resolution in the chemical domain(Association for Computational Linguistics, 2021-01-01)Chemical patents contain rich coreference and bridging links, which are the target of this research. Specially, we introduce a novel annotation scheme, based on which we create the ChEMU-Ref dataset from reaction description snippets in English-language chemical patents. We propose a neural approach to anaphora resolution, which we show to achieve strong results, especially when jointly trained over coreference and bridging links.
-
ItemBetter Health Explorer: Designing for Health Information Seekers(Association for Computing Machinery, 2015)A vast amount of health information has been published online, yet users often report difficulties in locating information in this particular domain. Based on our prior research, we consider four categories of online health information seekers who demonstrate mixed information needs. Although their searching needs are often well satisfied by entering keywords into search engines, their need to explore information is not so well supported, thus affecting their user experience and satisfaction. In this paper, we propose design principles for supporting the exploration of online health information. We present the rationale and the design process of a web app - Better Health Explorer - which is a proof-of-concept app tailored to health information exploration. This work contributes to the design of online health information systems as well as exploratory systems in general.
-
ItemImproved Topic Representations of Medical Documents to Assist COVID-19 Literature Exploration(Association for Computational Linguistics, 2020)
-
ItemBetter health information exploration(ACM, 2015-12-07)The provision of health information has to be clear and appealing to users. Research has shown that health information seekers do not all have the same attributes, skills or needs. In any given health-related app or website, there is a need to provide tools for accessing information in ways that appeal to users. This is not always supported by current web technologies. As such, based on prior research on health information seeking behaviour and needs, we designed and created a proofof- concept website named Better Health Explorer to experiment on health information seekers. The pilot results show a positive effect on supporting and improving the experience of seekers with exploratory search behaviour.
-
ItemTowards a semantic lexicon for biological language processing(HINDAWI LTD, 2005)This paper explores the use of the resources in the National Library of Medicine's Unified Medical Language System (UMLS) for the construction of a lexicon useful for processing texts in the field of molecular biology. A lexicon is constructed from overlapping terms in the UMLS SPECIALIST lexicon and the UMLS Metathesaurus to obtain both morphosyntactic and semantic information for terms, and the coverage of a domain corpus is assessed. Over 77% of tokens in the domain corpus are found in the constructed lexicon, validating the lexicon's coverage of the most frequent terms in the domain and indicating that the constructed lexicon is potentially an important resource for biological text processing.
-
ItemUsing natural language processing and VetCompass to understand antimicrobial usage patterns in Australia(Wiley, 2019-08-01)Background Currently there is an incomplete understanding of antimicrobial usage patterns in veterinary clinics in Australia, but such knowledge is critical for the successful implementation and monitoring of antimicrobial stewardship programs. Methods VetCompass Australia collects medical records from 181 clinics in Australia (as of May 2018). These records contain detailed information from individual consultations regarding the medications dispensed. One unique aspect of VetCompass Australia is its focus on applying natural language processing (NLP) and machine learning techniques to analyse the records, similar to efforts conducted in other medical studies. Results The free text fields of 4,394,493 veterinary consultation records of dogs and cats between 2013 and 2018 were collated by VetCompass Australia and NLP techniques applied to enable the querying of the antimicrobial usage within these consultations. Conclusion The NLP algorithms developed matched antimicrobial in clinical records with 96.7% accuracy and an F1 Score of 0.85, as evaluated relative to expert annotations. This dataset can be readily queried to demonstrate the antimicrobial usage patterns of companion animal practices throughout Australia.