Synonym extraction and abbreviation expansion with ensembles of semantic spaces
Journal of Biomedical SemanticsPublished 1 January 2014Open access
Aron Henriksson, Hans Moen, Maria Skeppstedt, Vidas Daudaravičius, Martin Duneld
Citations97
SJR quartileQ2
SJR score0.49
SNIP0.97
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is demonstrated that ensembles of semantic spaces can yield improved performance on the tasks of automatically extracting synonyms and abbreviation-expansion pairs, potentially allowing enhanced performance to be obtained on a wide range of natural language processing tasks.
Abstract
This study demonstrates that ensembles of semantic spaces can yield improved performance on the tasks of automatically extracting synonyms and abbreviation-expansion pairs. This notion, which merits further exploration, allows different distributional models - with different model parameters - and different types of corpora to be combined, potentially allowing enhanced performance to be obtained on a wide range of natural language processing tasks.
Keywords
Computer ScienceBiochemistry, Genetics and Molecular Biology
Journal of the American Society for Information ScienceIndexing by latent semantic analysis
12,677 Citations1990Scott Deerwester, Susan Dumais +3 more
Lecture notes in computer scienceEnsemble Methods in Machine Learning
7,862 Citations2000Thomas G. Dietterich
Communications of the ACMA vector space model for automatic indexing
7,434 Citations1975Gerard Salton, Anita M.-Y. Wong +1 more
An approach based on space density computations is used to choose an optimum indexing vocabulary for a collection of documents, demonstating the usefulness of the model.
Psychological ReviewA solution to Plato's problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge.
6,039 Citations1997Thomas K. Landauer, Susan Dumais
A new general theory of acquired similarity and knowledge representation, latent semantic analysis (LSA), is presented and used to successfully simulate such learning and several other psycholinguistic phenomena.
Automatic acquisition of hyponyms from large text corpora
3,283 Citations1992Marti A. Hearst
A set of lexico-syntactic patterns that are easily recognizable, that occur frequently and across text genre boundaries, and that indisputably indicate the lexical relation of interest are identified.
Behavior Research Methods, Instruments, & ComputersProducing high-dimensional semantic spaces from lexical co-occurrence
1,839 Citations1996Kevin Lund, Curt Burgess
A procedure that processes a corpus of text and produces numeric vectors containing information about its meanings for each word, which provide the basis for a representational model of semantic memory, hyperspace analogue to language (HAL).
Journal of the American Medical Informatics Association2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text
1,271 Citations2011Özlem Uzuner, Brett R. South +2 more
The 2010 i2b2/VA Workshop on Natural Language Processing Challenges for Clinical Records presented three tasks, which showed that machine learning approaches could be augmented with rule-based systems to determine concepts, assertions, and relations.
Yearbook of Medical InformaticsExtracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research
896 Citations2008Guergana Savova, Karin Kipper-Schuler +2 more
Performance of information extraction systems with clinical text has improved since the last systematic review in 1995, but they are still rarely applied outside of the laboratory they have been developed in.
Journal of the Royal Statistical Society Series C (Applied Statistics)Statistics for Business and Economics.
820 Citations1988R. P. Hope, Paul Newbold
Briefings in BioinformaticsA survey of current work in biomedical text mining
767 Citations2005Aaron Cohen
The major challenge of biomedical text mining over the next 5-10 years will require enhanced access to full text, better understanding of the feature space of biomedical literature, better methods for measuring the usefulness of systems to users, and continued cooperation with the biomedical research community to ensure that their needs are addressed.
Psychological ReviewRepresenting word meaning and order information in a composite holographic lexicon.
638 Citations2007Michael N. Jones, D. J. K. Mewhort
A computational model that builds a holographic lexicon representing both word meaning and word order from unsupervised experience with natural language demonstrates that a broad range of psychological data can be accounted for directly from the structure of lexical representations learned in this way, without the need for complexity to be built into either the processing mechanisms or the representations.
ACM Transactions on Information SystemsRank-biased precision for measurement of retrieval effectiveness
628 Citations2008Alistair Moffat, Justin Zobel
A new effectiveness metric, rank-biased precision, is introduced that is derived from a simple model of user behavior, is robust if answer rankings are extended to greater depths, and allows accurate quantification of experimental uncertainty, even when only partial relevance judgments are available.
Journal of Biomedical InformaticsMeasures of semantic similarity and relatedness in the biomedical domain
584 Citations2006Ted Pedersen, Serguei Pakhomov +2 more
There is a role both for more flexible measures of relatedness based on information derived from corpora, as well as for measures that rely on existing ontological structures.
Publications (Konstfack University of Arts, Crafts, and Design)The Word-Space Model : Using distributional analysis to represent syntagmatic and paradigmatic relations between words in high-dimensional vector spaces
535 Citations2006Magnus Sahlgren
The word-space model is a computational model of word meaning that utilizes the distributional patterns of words collected over large text data to represent semantic similarity between words in terabytes of data.
A SIMPLE ALGORITHM FOR IDENTIFYING ABBREVIATION DEFINITIONS IN BIOMEDICAL TEXT
520 Citations2002Ariel Schwartz, Marti A. Hearst
This paper shows that the problem of identifying abbreviations' definitions can be solved with a much simpler algorithm than that proposed by other research efforts, and achieves 96% precision and 82% recall on a standard test collection, which is at least as good as existing approaches.
SIAM ReviewA Measure of Similarity between Graph Vertices: Applications to Synonym Extraction and Web Searching
424 Citations2004Vincent D. Blondel, Anahí Gajardo +3 more
Random indexing of text samples for latent semantic analysis
384 Citations2000Pentti Kanerva, Jan Kristoferson +1 more
Random Indexing of Text Samples for Latent Semantic Analysis Pentti Kanerva Jan Kristoferson Anders Holst [email protected], [email protected] RWCP Theoretical Foundation SICS Laboratory Swedish Institute of Computer Science, Box 1263, SE-16429 Kista, Sweden LatentSemantic Analysis is a method of computing vectors that captures ent corpus and the vectors capture words-by-contexts matrix meaning.
Journal of the American Medical Informatics AssociationCreating an Online Dictionary of Abbreviations from MEDLINE
217 Citations2002Joseph Tung‐Chieh Chang
An algorithm to identify abbreviations from text using a statistical learning algorithm, logistic regression, to score abbreviation expansions based on their resemblance to a training set of human-annotated abbreviations is developed.
Journal of Biomedical InformaticsEmpirical distributional semantics: Methods and biomedical applications
214 Citations2009Trevor Cohen, Dominic Widdows
The available methodologies for derivation of semantic relatedness from free text are reviewed, as well as their evaluation in a variety of biomedical and other applications.
Improving the estimation of relevance models using large external corpora
202 Citations2006Fernando Díaz, Donald Metzler
The results show that using a high quality corpus that is comparable to the evaluation corpus can be as, if not more, effective than using the web.
Journal of the American Medical Informatics AssociationMapping Abbreviations to Full Forms in Biomedical Articles
148 Citations2002Hong Yu
The authors found that an average of 25 percent of abbreviations were defined in biomedical articles and that of a randomly selected subset of undefined abbreviations, 68 percent could be mapped to any of four abbreviation databases.
Permutations as a means to encode order in word space
145 Citations2008Magnus Sahlgren, Anders Holst +1 more
It is shown that sequence information can be encoded into high-dimensional fixed-width vectors using permutations of coordinates, thus providing a general and computationally light alternative to convolution.
Finding synonyms using automatic word alignment and measures of distributional similarity
124 Citations2006Lonneke van der Plas, Jörg Tiedemann
This work presents a method based on automatic word alignment of parallel corpora consisting of documents translated into multiple languages and compares it with a monolingual syntax-based method, which shows much higher precision and recall scores for the task of synonym extraction.
BioinformaticsExtracting synonymous gene and protein terms from biological literature
103 Citations2003Hong Yu, Eugene Agichtein
Four complementary approaches for extracting gene and protein synonyms from text are explored, namely the unsupervised, partially supervised, and supervised machine-learning techniques, as well as the manual knowledge-based approach.
BioinformaticsResolving abbreviations to their senses in Medline
103 Citations2005Sylvain Gaudan, Harald Kirsch +1 more
An automatic analysis of Medline abstracts and linguistic methods are combined to build a dictionary of abbreviation/sense pairs and the system disambiguates abbreviations with a precision of 98.9% for a recall of 99.2% (98.5% accuracy).
Lecture notes in computer scienceWikipedia Mining for an Association Web Thesaurus Construction
101 Citations2007Kotaro Nakayama, Takahiro Hara +1 more
An efficient link mining method pfibf (Path Frequency - Inversed Backward link Frequency) and the extension method "forward / backward link weighting (FB weighting)" are proposed in order to construct a huge scale association thesaurus of Wikipedia.
Journal of the American Medical Informatics AssociationDictionary construction and identification of possible adverse drug events in Danish clinical narrative text
89 Citations2013Robert Eriksson, Peter Bjødstrup Jensen +3 more
A dictionary-building method that allows synonyms to be identified and anatomical location descriptions can be merged to allow appropriate grouping of effects in the same location and could be used to identify possible ADEs in Danish clinical narratives.
Journal of the American Medical Informatics AssociationALICE: An Algorithm to Extract Abbreviations from MEDLINE
85 Citations2005Ao Huang
ALICE does not only facilitate recognition of an undefined abbreviation in a paper by constructing an abbreviation database or dictionary, but also makes biomedical literature retrieval more accurate.
IEEE Transactions on Information Technology in BiomedicineMeeting medical terminology needs-the ontology-enhanced Medical Concept Mapper
84 Citations2001Gondy Leroy, Hsinchun Chen
The Medical Concept Mapper is described, a tool designed to facilitate access to online medical information sources by providing users with appropriate medical search terms for their personal queries, and its unique contribution results from combining the UMLS Semantic Net with Concept Space in the deep semantic parsing (DSP) algorithm.
PubMedA study of abbreviations in MEDLINE abstracts.
82 Citations2002Hongfang Liu, Alan R. Aronson +1 more
This paper studied the UMLS coverage, textual variants of senses, and the ambiguity of abbreviations in MEDLINE abstracts to define three-letter abbreviations which were defined using parenthetical expressions.
PubMedTowards consumer-friendly PHRs: patients' experience with reviewing their health records.
81 Citations2007Alla Keselman, Laura Slaughter +6 more
A survey of patients' experience with reviewing their health records, in order to identify barriers to optimal record use points to providers' notes, laboratory test results and radiology reports as the most difficult records sections for lay reviewers.
Ensemble methods for automatic thesaurus extraction
71 Citations2002James Curran
This work explores ensemble efficacy for the more complex task of automatic thesaurus extraction on up to 300 million words, and examines the constraints on, and complexity of, different contextual representations which contribute to the sparseness-and noise-induced bias behaviour of NLP systems on very large corpora.
The Stockholm EPR Corpus – Characteristics and Some Initial Findings
69 Citations2009Hercules Dalianis, Martin Hassel +1 more
The characteristics of the Stockholm Electronic Patient Record Corpus (the SEPR Corpus), an important resource for performing research on clinical data, are described, which contains characteristics that are very interesting from a linguistic point of view, such as domain specific compounds and abbreviations, and various narratives.
BMC BioinformaticsUsing co-occurrence network structure to extract synonymous gene and protein names from MEDLINE abstracts
66 Citations2005AM Arjeh Cohen, William Hersh +2 more
Optimizing synonym extraction using monolingual and bilingual resources
65 Citations2003Hua Wu, Ming Zhou
Experimental results prove that the three resources are complementary to each other on synonym extraction, and that the ensemble method used is very effective to improve both precisions and recalls of extracted synonyms.
PubMedSynonym, topic model and predicate-based query expansion for retrieving clinical documents.
46 Citations2012Qing Zeng, Doug Redd +2 more
Amongst the three expansion methods, the topic model-based method performed the best in terms of recall and F-measure, and was developed and tested for the retrieval of clinical documents.
BMC BioinformaticsSynonym set extraction from the biomedical literature by lexical pattern discovery
44 Citations2008John P. McCrae, Nigel Collier
It is concluded that automatic methods can play a practical role in developing new thesauri or expanding on existing ones, and this can be done with only a small amount of training data and no need for resources such as parsers.
PubMedImproving perceived and actual text difficulty for health information consumers using semi-automated methods.
43 Citations2012Gondy Leroy, James E. Endicott +3 more
An algorithm is developed that uses term familiarity to identify difficult text and select easier alternatives from lexical resources such as WordNet, UMLS and Wiktionary to help estimate text difficulty.
An evaluation of corpus-driven measures of medical concept similarity for information retrieval
42 Citations2012Bevan Koopman, Guido Zuccon +3 more
This paper evaluates the effectiveness of eight common corpus-driven measures in capturing semantic relatedness and compares these against human judged concept pairs assessed by medical professionals, showing that certain corpus- driven measures correlate strongly with human judgements.
Predicting strong associations on the basis of corpus data
35 Citations2009Yves Peirsman, Dirk Geeraerts
It is shown that the best single predictor is the log-likelihood ratio, followed closely by the document-based word space model, and an ensemble method that combines these two best approaches with the compounding algorithm achieves an increase in performance of almost 30% over the current state of the art.
A Robust Shallow Parser for Swedish
35 Citations2003Ola Knutsson, Johnny Bigert +1 more
A robust parser for Swedish that identifies the internal structure of phrases, but does not build full trees; in addition to phrase identification, clause boundaries are detected.
PubMedIdentifying synonymy between SNOMED clinical terms of varying length using distributional analysis of electronic health records.
32 Citations2013Aron Henriksson, Mike Conway +2 more
This paper demonstrates how distributional analysis of a large corpus of electronic health records - the MIMIC-II database - can be employed to extract synonyms of SNOMED CT preferred terms, demonstrating its ability to identify synonymous relations between terms of varying length.
Automatic acronym recognition
30 Citations2006Dana Dannélls
An analysis of the errors produced indicates that further improvement of the rule-based method requires the use of syntactic information and textual pre-processing, and performance could further improve by increasing the training set and modifying the input settings for the machine learning algorithms.
A summarization tool for time-sensitive social media
26 Citations2012Walid Magdy, Ahmed Ali +1 more
A new multidimensional microblog search tool that generates a comprehensive report from microblogs instead of a flat list of recent/relevant microblogs for a given query and can be configured for monitoring time-sensitive topics using a set of predefined queries.
Alignment-HMM-based Extraction of Abbreviations from Biomedical Text
18 Citations2012Dana Movshovitz‐Attias, William W. Cohen
Using the abbreviation alignment model, the algorithm was able to extract over 1.4 million abbreviations from a corpus of 200K full-text PubMed papers, including 455,844 unique definitions.
Corpus-Driven Terminology Development: Populating Swedish SNOMED CT with Synonyms Extracted from Electronic Health Records
18 Citations2013Aron Henriksson, Maria Skeppstedt +3 more
The potential of the proposed distributional methods for extracting synonym candidates for clinical terms using the Swedish version of SNOMED CT, which currently lacks synonyms is exemplified.
Communications of the ACMComputational Linguistics: Graphical input/output of nonstandard characters
17 Citations1968Hayashi Hideyuki, Sheila L. B. Duncan +1 more
A system developed at Harvard for graphically inputting and outputting nonstandard characters on a computer is printed and can deal with any orthography, although at present it is limited to 4000 Chinese characters and some mathematical symbols.
Initial Results in the Development of SCAN A Swedish Clinical Abbreviation Normalizer
16 Citations2012Niklas Isenius, Sumithra Velupillai +1 more
Optimizing the Dimensionality of Clinical Term Spaces for Improved Diagnosis Coding Support
13 Citations2013Aron Henriksson, Martin Hassel
The importance of dimensionality optimization is demonstrated and correlations between dimensionality and the size of the vocabulary are discussed, which may mitigate the effect of exploding vocabulary sizes when modeling multiword terms as single tokens.
QUT ePrints (Queensland University of Technology)Modelling Word Meaning using Efficient Tensor Representations
11 Citations2011Michael Symonds, Peter Bruza +2 more
This paper presents an efficient tensor based approach to modelling word meaning that builds on recent attempts to encode word order information, while providing flexible methods for extracting task specific semantic information.
Semantic Judgement of Medical Concepts: Combining Syntagmatic and Paradigmatic Information with the Tensor Encoding Model
8 Citations2012Michael Symonds, Guido Zuccon +3 more