Method Mention Extraction from Scientific Research Papers
6183Authors
nan
Abstract
Scientific publications contain many references to method terminologies used during scientific experiments. New terms are constantly created within the research community, especially in the biomedical domain where thousands of papers are published each week. In this study we report our attempt to automatically extract such method terminologies from scientific research papers, using rule-based and machine learning techniques. We first used some linguistic features to extract fine-grained method sentences from a large biomedical corpus and then applied well established methodologies to extract the method terminologies. We focus the present study on the extraction of method phrases that contain an explicit mention of method keywords such as (algorithm, technique, analysis, approach and method) and other less explicit method terms such as Multiplex Ligation dependent Probe Amplification. Our initial results show an average F-score of 91.89 for the rule-based system and 78.26 for the Conditional Random Field-based machine learning system. KEYWORDS: terminology extraction, rule-based, machine learning, corpus, linguistic features. 1211 1
Keywords
Full Content
Proceedings of COLING 2012: Technical Papers, pages 1211–1222, COLING 2012, Mumbai, December 2012. Method mention extraction from scientific research papers Hospice Houngbo Robert E. Mercer Department of Computer Science The University of Western Ontario, London, ON, Canada hhoungbo@uwo.ca, mercer@csd.uwo.ca ABSTRACT Scientific publications contain many references to method terminologies used during scientific experiments. New terms are constantly created within the research community, especially in the biomedical domain where thousands of papers are published each week. In this study we report our attempt to automatically extract such method terminologies from scientific research papers, using rule-based and machine learning techniques. We first used some linguistic features to extract fine-grained method sentences from a large biomedical corpus and then applied well established methodologies to extract the method terminologies. We focus the present study on the extraction of method phrases that contain an explicit mention of method keywords such as (algorithm, technique, analysis, approach and method) and other less explicit method terms such as Multiplex Ligation dependent Probe Amplification. Our initial results show an average F-score of 91.89 for the rule-based system and 78.26 for the Conditional Random Field-based machine learning system. KEYWORDS: terminology extraction, rule-based, machine learning, corpus, linguistic features. 1211 1 Introduction The methods and techniques used during scientific experiments and reported in scientific papers are often expressed in different forms. They can be in the form of a semantic sequence (see (Hunston, 2008) containing the word method (“rank-based normalization method” in Sentence 1), the word technique (“Non-negative matrix factorization technique” in Sentence 2), the word analysis (“discriminant analysis” in Sentence 3), and so on. Sentence 1: In order to compare U133A and U133 Plus 2.0 data we further normalized the data with a rank-based normalization method. Sentence 2: In the Bioinformatics field a great deal of interest has been given to Non-negative matrix factorization technique NMF due to its capability of providing new insights and relevant information about the complex latent relationships in experimental data sets. Sentence 3: The relative performance of the four IBDQ dimensions in distinguishing best patients with minor symptoms from those with severe was studied by discriminant analysis. A method mention can be a terminology term such as the phrase Multiplex Ligation dependent Probe Amplification in Sentence 4. Sentence 4: Recently < Multiplex Ligation dependent Probe Amplification > < MLPA > has also been used to quantify copy number classes. A method expression can also be a verb phrase referring to an action performed during an experiment, such as the verb phrase to search for in sentence 5. Sentence 5: These sequences were used to search for the nearly invariant nucleotides of the inverse core AAC and core GTT sites separated by a distance typical of previously identified attC sites to bp . In some cases, the context in which the method terminologies are used in the text can contain valuable information about the method mention, such as synonyms, definition, and other relations with entities in the text. The automatic extraction of terminologies has been the focus of …
Content truncated to 500 words
Labeled Text
Scientific publications contain many references to method terminologies used during scientific experiments. New terms are constantly created within the research community, especially in the biomedical domain where thousands of papers are published each week. In this study we report our attempt to automatically extract such method terminologies from scientific research papers, using rule-based and machine learning techniques. We first used some linguistic features to extract fine-grained method sentences from a large biomedical corpus and then applied well established methodologies to extract the method terminologies. We focus the present study on the extraction of method phrases that contain an explicit mention of method keywords such as (algorithm, technique, analysis, approach and method) and other less explicit method terms such as Multiplex Ligation dependent Probe Amplification. Our initial results show an average F-score of 91.89 for the rule-based system and 78.26 for the Conditional Random Field-based machine learning system. KEYWORDS: terminology extraction, rule-based, machine learning, corpus, linguistic features. 1211 1
Publication Details
- Paper ID:
- 6183
- Year:
- 2012
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan