Extracting Lexical Relations from Biomedical Text: Learning Parts and Wholes MPhil / PhD Upgrade Report
نویسنده
چکیده
Lexical relations organise and structure vocabulary. They reflect relations in the real world. Meronymy is the lexical relation between a word representing a part, and a word representing a whole, such as (finger partOf hand). Meronymy is of special importance in biomedicine: structure and process are organised along partitive axes. Anatomy, for example, is rich in part-whole relations. This importance is reflected in the modelling of meronymy in several biomedical knowledge resource. Much research has been carried out on the extraction of taxonomies (isA or kindOf relations) from text. Very little research has applied the same techniques to meronymy, and where it has been carried out, it has been limited in one way or another. This report examines meronymy and its place in biomedicine, reviews earlier work on part-whole extraction, and proposes extensions to it. Notational Conventions Relations between lexical items Lexical items will be shown in typewriter text, with their semantic types (where shown) in square brackets and [small caps], and lexical relations between them in italics. For example, bridge[body part] partOf nose[body part] Incorrect examples will be preceded by a ?. For example, ?bridge[artificial structure] partOf nose[body part] Co-referents will be underlined. For example, If there are co-referents in some text, they will be underlined. Hyponymy and Hyperonymy may be shown by the symbols ⊂ and ⊃ . For example, dog ⊂ animal ⊃ cat Meronymy and Holonymy may be shown by the symbols ≺ and . For example, wheel ≺ bicycle chain Not meronymy and Not Holonymy may be shown by the symbols 6≺ and 6 . For example, finger 6≺ knee 6 toe
منابع مشابه
L2 Learners’ Lexical Inferencing: Perceptual Learning Style Preferences, Strategy Use, Density of Text, and Parts of Speech as Possible Predictors
This study was intended first to categorize the L2 learners in terms of their learning style preferences and second to investigate if their learning preferences are related to lexical inferencing. Moreover, strategies used for lexical inferencing and text related issues of text density and parts of speech were studied to determine their moderating effects and the best predictors of lexical infe...
متن کاملRepresenting Natural Kinds by Spatial Inclusion and Containment
Biomedical terminologies lack a clear-cut understanding of the semantics of part-whole relations. In order to design a conceptually adequate ontology for the biomedical domain, we investigate different forms of ontological dependencies between parts and wholes. We then suggest, for natural kinds at least, a move away from modeling the relations between parts and wholes and advocate instead conc...
متن کاملرویکردی با ناظر در استخراج واژگان کلیدی اسناد فارسی با استفاده از زنجیرههای لغوی
Keywords are the main focal points of interest within a text, which intends to represent the principal concepts outlined in the document. Determining the keywords using traditional methods is a time consuming process and requires specialized knowledge of the subject. For the purposes of indexing the vast expanse of electronic documents, it is important to automate the keyword extraction task. S...
متن کاملSearching for High-Utility Text in the Biomedical Literature
Much current research is concerned with extracting biomedical facts from text, so far with relatively modest results. Our work is motivated by the idea that text mining can be improved, if the system could first identify text regions that are rich in scientific content, retrieve documents that have many such regions, and focus on fact extraction from these regions. We call these parts of the te...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2003