This paper describes the basic philosophy and implementation of MPLUS (M+), a robust medical text analysis tool that uses a semantic model based on Bayesian Networks (BNs). BNs provide a concise and useful formalism for representing semantic patterns in medical text, and for recognizing and reasoning over those patterns. BNs are noise-tolerant, and facilitate the training of M+.
{"title":"MPLUS: a probabilistic medical language understanding system","authors":"Lee M. Christensen, P. Haug, M. Fiszman","doi":"10.3115/1118149.1118154","DOIUrl":"https://doi.org/10.3115/1118149.1118154","url":null,"abstract":"This paper describes the basic philosophy and implementation of MPLUS (M+), a robust medical text analysis tool that uses a semantic model based on Bayesian Networks (BNs). BNs provide a concise and useful formalism for representing semantic patterns in medical text, and for recognizing and reasoning over those patterns. BNs are noise-tolerant, and facilitate the training of M+.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115892753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Pustejovsky, J. Castaño, Jason Zhang, R. Saurí, W. Luo
The automatic extraction of information from Medline articles and abstracts (commonly referred to now as the biobibliome) promises to play an increasingly critical role in aiding research while speeding up the discovery process. We have been developing robust natural language tools for the automated extraction of structured information from biomedical texts as part of a project we call MEDSTRACT. Here we will describe an architecture for developing databases for domain specific information servers for research and support in the biomedical community. These are currently comprised of the following: a Bio-Relation Server, and the Bio-Acronym server, Acromed, which will include also aliases. Each information server is derived automatically from an integration of diverse components which employ robust natural language processing of Medline text and IE techniques. The front-end consists of conventional search and navigation capabilities, as well as visualization tools that help to navigate the databases and explore the results of a search. It is hoped that this set of applications will allow for quick, structured access to relevant information on individual genes by biologists over the web.
{"title":"Medstract: creating large-scale information servers from biomedical texts","authors":"J. Pustejovsky, J. Castaño, Jason Zhang, R. Saurí, W. Luo","doi":"10.3115/1118149.1118161","DOIUrl":"https://doi.org/10.3115/1118149.1118161","url":null,"abstract":"The automatic extraction of information from Medline articles and abstracts (commonly referred to now as the biobibliome) promises to play an increasingly critical role in aiding research while speeding up the discovery process. We have been developing robust natural language tools for the automated extraction of structured information from biomedical texts as part of a project we call MEDSTRACT. Here we will describe an architecture for developing databases for domain specific information servers for research and support in the biomedical community. These are currently comprised of the following: a Bio-Relation Server, and the Bio-Acronym server, Acromed, which will include also aliases. Each information server is derived automatically from an integration of diverse components which employ robust natural language processing of Medline text and IE techniques. The front-end consists of conventional search and navigation capabilities, as well as visualization tools that help to navigate the databases and explore the results of a search. It is hoped that this set of applications will allow for quick, structured access to relevant information on individual genes by biologists over the web.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134322581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. B. Cohen, A. Dolbey, G. Acquaah-Mensah, L. Hunter
We studied contrast and variability in a corpus of gene names to identify potential heuristics for use in performing entity identification in the molecular biology domain. Based on our findings, we developed heuristics for mapping weakly matching gene names to their official gene names. We then tested these heuristics against a large body of Medline abstracts, and found that using these heuristics can increase recall, with varying levels of precision. Our findings also underscored the importance of good information retrieval and of the ability to disambiguate between genes, proteins, RNA, and a variety of other referents for performing entity identification with high precision.
{"title":"Contrast and variability in gene names","authors":"K. B. Cohen, A. Dolbey, G. Acquaah-Mensah, L. Hunter","doi":"10.3115/1118149.1118152","DOIUrl":"https://doi.org/10.3115/1118149.1118152","url":null,"abstract":"We studied contrast and variability in a corpus of gene names to identify potential heuristics for use in performing entity identification in the molecular biology domain. Based on our findings, we developed heuristics for mapping weakly matching gene names to their official gene names. We then tested these heuristics against a large body of Medline abstracts, and found that using these heuristics can increase recall, with varying levels of precision. Our findings also underscored the importance of good information retrieval and of the ability to disambiguate between genes, proteins, RNA, and a variety of other referents for performing entity identification with high precision.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126167425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
NLP systems will be more portable among medical domains if acquisition of semantic lexicons can be facilitated. We are pursuing lexical acquisition through the syntactic relationships of words in medical corpora. Therefore we require a syntactic parser which is flexible, portable, captures head-modifier pairs and does not require a large training set. We have designed a dependency grammar parser that learns through a transformational-based algorithm. We propose a novel design for templates and transformations which capitalize on the dependency structure directly and produces human-readable rules. Our parser achieved a 77% accurate parse training on only 830 sentences. Further work will evaluate the usefulness of this parse for lexical acquisition.
{"title":"A transformational-based learner for dependency grammars in discharge summaries","authors":"D. A. Campbell, Stephen B. Johnson","doi":"10.3115/1118149.1118155","DOIUrl":"https://doi.org/10.3115/1118149.1118155","url":null,"abstract":"NLP systems will be more portable among medical domains if acquisition of semantic lexicons can be facilitated. We are pursuing lexical acquisition through the syntactic relationships of words in medical corpora. Therefore we require a syntactic parser which is flexible, portable, captures head-modifier pairs and does not require a large training set. We have designed a dependency grammar parser that learns through a transformational-based algorithm. We propose a novel design for templates and transformations which capitalize on the dependency structure directly and produces human-readable rules. Our parser achieved a 77% accurate parse training on only 830 sentences. Further work will evaluate the usefulness of this parse for lexical acquisition.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"230 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128601169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We describe our use of an existing resource, the Mouse Anatomical Nomenclature, to improve a symbolic interface to anatomically-indexed gene expression data. The goal is to reduce user effort in specifying anatomical structures of interest and increase precision and recall.
{"title":"Enhanced natural language access to anatomically-indexed data","authors":"Gail Sinclair, B. Webber, D. Davidson","doi":"10.3115/1118149.1118156","DOIUrl":"https://doi.org/10.3115/1118149.1118156","url":null,"abstract":"We describe our use of an existing resource, the Mouse Anatomical Nomenclature, to improve a symbolic interface to anatomically-indexed gene expression data. The goal is to reduce user effort in specifying anatomical structures of interest and increase precision and recall.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127300673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose two internal methods for accenting unknown words, which both learn on a reference set of accented words the contexts of occurrence of the various accented forms of a given letter. One method is adapted from POS tagging, the other is based on finite state transducers.We show experimental results for letter e on the French version of the Medical Subject Headings thesaurus. With the best training set, the tagging method obtains a precision-recall breakeven point of 84.2±4.4% and the transducer method 83.8±4.5% (with a baseline at 64%) for the unknown words that contain this letter. A consensus combination of both increases precision to 92.0±3.7% with a recall of 75%. We perform an error analysis and discuss further steps that might help improve over the current performance.
{"title":"Accenting unknown words in a specialized language","authors":"Pierre Zweigenbaum, N. Grabar","doi":"10.3115/1118149.1118153","DOIUrl":"https://doi.org/10.3115/1118149.1118153","url":null,"abstract":"We propose two internal methods for accenting unknown words, which both learn on a reference set of accented words the contexts of occurrence of the various accented forms of a given letter. One method is adapted from POS tagging, the other is based on finite state transducers.We show experimental results for letter e on the French version of the Medical Subject Headings thesaurus. With the best training set, the tagging method obtains a precision-recall breakeven point of 84.2±4.4% and the transducer method 83.8±4.5% (with a baseline at 64%) for the unknown words that contain this letter. A consensus combination of both increases precision to 92.0±3.7% with a recall of 75%. We perform an error analysis and discuss further steps that might help improve over the current performance.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129451789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Document retrieval in languages with a rich and complex morphology - particularly in terms of derivation and (single-word) composition - suffers from serious performance degradation with the stemming-only query-term-to-text-word matching paradigm. We propose an alternative approach in which morphologically complex word forms are segmented into relevant subwords (such as stems, named entities, acronyms), and subwords constitute the basic unit for indexing and retrieval. We evaluate our approach on a large biomedical document collection.
{"title":"Biomedical text retrieval in languages with a complex morphology","authors":"S. Schulz, Martin Honeck, U. Hahn","doi":"10.3115/1118149.1118158","DOIUrl":"https://doi.org/10.3115/1118149.1118158","url":null,"abstract":"Document retrieval in languages with a rich and complex morphology - particularly in terms of derivation and (single-word) composition - suffers from serious performance degradation with the stemming-only query-term-to-text-word matching paradigm. We propose an alternative approach in which morphologically complex word forms are segmented into relevant subwords (such as stems, named entities, acronyms), and subwords constitute the basic unit for indexing and retrieval. We evaluate our approach on a large biomedical document collection.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122411968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Information Extraction (IE), defined as the activity to extract structured knowledge from unstructured text sources, offers new opportunities for the exploitation of biological information contained in the vast amounts of scientific literature. But while IE technology has received increasing attention in the area of molecular biology, there have not been many examples of IE systems successfully deployed in end-user applications. We describe the development of PASTAWeb, a WWW-based interface to the extraction output of PASTA, an IE system that extracts protein structure information from MEDLINE abstracts. Key characteristics of PASTAWeb are the seamless integration of the PASTA extraction results (templates) with WWW-based technology, the dynamic generation of WWW content from 'static' data and the fusion of information extracted from multiple documents.
{"title":"Utilizing text mining results: The Pasta Web System","authors":"G. Demetriou, R. Gaizauskas","doi":"10.3115/1118149.1118160","DOIUrl":"https://doi.org/10.3115/1118149.1118160","url":null,"abstract":"Information Extraction (IE), defined as the activity to extract structured knowledge from unstructured text sources, offers new opportunities for the exploitation of biological information contained in the vast amounts of scientific literature. But while IE technology has received increasing attention in the area of molecular biology, there have not been many examples of IE systems successfully deployed in end-user applications. We describe the development of PASTAWeb, a WWW-based interface to the extraction output of PASTA, an IE system that extracts protein structure information from MEDLINE abstracts. Key characteristics of PASTAWeb are the seamless integration of the PASTA extraction results (templates) with WWW-based technology, the dynamic generation of WWW content from 'static' data and the fusion of information extracted from multiple documents.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122651578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Current information extraction efforts in the biomedical domain tend to focus on finding entities and facts in structured databases or MEDLINE® abstracts. We apply a gene and protein name tagger trained on Medline abstracts (ABGene) to a randomly selected set of full text journal articles in the biomedical domain. We show the effect of adaptations made in response to the greater heterogeneity of full text.
{"title":"Tagging gene and protein names in full text articles","authors":"L. Tanabe, W. Wilbur","doi":"10.3115/1118149.1118151","DOIUrl":"https://doi.org/10.3115/1118149.1118151","url":null,"abstract":"Current information extraction efforts in the biomedical domain tend to focus on finding entities and facts in structured databases or MEDLINE® abstracts. We apply a gene and protein name tagger trained on Medline abstracts (ABGene) to a randomly selected set of full text journal articles in the biomedical domain. We show the effect of adaptations made in response to the greater heterogeneity of full text.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129694041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We explore the use of Support Vector Machines (SVMs) for biomedical named entity recognition. To make the SVM training with the available largest corpus - the GENIA corpus - tractable, we propose to split the non-entity class into sub-classes, using part-of-speech information. In addition, we explore new features such as word cache and the states of an HMM trained by unsupervised learning. Experiments on the GENIA corpus show that our class splitting technique not only enables the training with the GENIA corpus but also improves the accuracy. The proposed new features also contribute to improve the accuracy. We compare our SVM-based recognition system with a system using Maximum Entropy tagging method.
{"title":"Tuning support vector machines for biomedical named entity recognition","authors":"Jun'ichi Kazama, Takaki Makino, Yoshihiro Ohta, Junichi Tsujii","doi":"10.3115/1118149.1118150","DOIUrl":"https://doi.org/10.3115/1118149.1118150","url":null,"abstract":"We explore the use of Support Vector Machines (SVMs) for biomedical named entity recognition. To make the SVM training with the available largest corpus - the GENIA corpus - tractable, we propose to split the non-entity class into sub-classes, using part-of-speech information. In addition, we explore new features such as word cache and the states of an HMM trained by unsupervised learning. Experiments on the GENIA corpus show that our class splitting technique not only enables the training with the GENIA corpus but also improves the accuracy. The proposed new features also contribute to improve the accuracy. We compare our SVM-based recognition system with a system using Maximum Entropy tagging method.","PeriodicalId":339993,"journal":{"name":"ACL Workshop on Natural Language Processing in the Biomedical Domain","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121888525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：