--- title: "Construction of the Literature Graph in — Ammar 2018" description: "The paper describes the production pipeline behind Semantic Scholar." authors: ["Waleed Ammar", "Dirk Groeneveld", "Chandra Bhagavatula", "Iz Beltagy", "Miles Crawford", "Doug Downey", "Jason Dunkelberger", "Ahmed Elgohary", "Sergey Feldman", "Vu Ha", "Rodney Kinney", "Sebastian Kohlmeier", "Kyle Lo", "Tyler Murray", "Hsu-Han Ooi", "Matthew Peters", "Joanna Power", "Sam Skjonsberg", "Lucy Lu Wang", "Chris Wilhelm", "Zheng Yuan", "Madeleine van Zuylen", "Oren Etzioni"] year: 2018 venue: "Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)" source: "https://aclanthology.org/N18-3011/" doi: "10.18653/v1/n18-3011" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/ammar-2018-construction-literature-graph-semantic-scholar/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ammar-2018-construction-literature-graph-semantic-scholar/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/) / Construction of the Literature Graph in Semantic Scholar # Construction of the Literature Graph in Semantic Scholar **Authors:** [Waleed Ammar](https://md.research.elamur.ai/free/en/authors/waleed-ammar/), [Dirk Groeneveld](https://md.research.elamur.ai/free/en/authors/dirk-groeneveld/), [Chandra Bhagavatula](https://md.research.elamur.ai/free/en/authors/chandra-bhagavatula/), [Iz Beltagy](https://md.research.elamur.ai/free/en/authors/iz-beltagy/), Miles Crawford, [Doug Downey](https://md.research.elamur.ai/free/en/authors/doug-downey/), Jason Dunkelberger, [Ahmed Elgohary](https://md.research.elamur.ai/free/en/authors/ahmed-elgohary/), [Sergey Feldman](https://md.research.elamur.ai/free/en/authors/sergey-feldman/), Vu Ha, [Rodney Kinney](https://md.research.elamur.ai/free/en/authors/rodney-kinney/), [Sebastian Kohlmeier](https://md.research.elamur.ai/free/en/authors/sebastian-kohlmeier/) et al. (23 authors) · **Year:** 2018 · **Venue:** Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/N18-3011/) · [PDF](https://aclanthology.org/N18-3011.pdf) · [DOI 10.18653/v1/n18-3011](https://doi.org/10.18653/v1/n18-3011) · [OpenAlex](https://openalex.org/W2801930304) **Citations:** 317 citations (openalex-snapshot · 2026-10-14) · [80](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary The paper describes the production pipeline behind Semantic Scholar. It turns a large, heterogeneous collection of scientific publications into a single directed property graph that machines can query. The graph has over 280M nodes covering papers, authors, entities and entity mentions. Its edges encode citations, authorship, entity linking and relations between mentions or entities. The authors break graph construction into standard NLP problems: sequence labeling for metadata, entity extraction and linking, author disambiguation, and relation extraction. They also point out where real-world conditions break the usual benchmark assumptions, for example the lack of large labeled sets and mismatched entity types. Metadata comes from ScienceParse, a two-layer BiLSTM with a CRF-style output layer that reads layout-aware token features from PDFs. It was trained on PubMed Central data that was labeled automatically. Entity extraction and linking approaches were evaluated with crowd annotations in computer science and biomedicine. The work shows that mature NLP components can be assembled into a deployed, large-scale scholarly knowledge graph. The authors also released several resources, including the ScienceParse models and metadata for more than 20M papers. ## Key points - **Graph size:** 37M unique papers (deduplicated by metadata string similarity), 12M authors, 0.4M entities and 237M entity mentions, for more than 280M nodes in total. - **ScienceParse training:** the model was trained on a PubMed Central snapshot of 1.4M PDFs. Gold labels were produced by matching known metadata strings inside the tokenized PDFs, which worked for 76% of documents. - **ScienceParse results:** on roughly 54K held-out documents, with strict exact-match scoring, F1 was: - 85.5 for titles - 92.1 for authors - 89.3 for bibliography titles - 97.0 for bibliography authors - 90.7 for bibliography venues - 98.0 for bibliography years - **Entity extraction evaluation:** three approaches (statistical, hybrid, off-the-shelf TagMe for CS) were compared on 500 papers. Labels came from CrowdFlower, keeping only items where at least three annotators agreed. The statistical method had the best precision but the lowest yield, while the hybrid method had the best yield at some cost in precision. - **Public resources:** metadata for over 20M papers, a meaningful citations dataset, figure/table extraction models (deepfigures), citation recommendation models (citeomatic) and science-parse. ## Interesting ideas - **Free training labels from existing metadata.** The authors projected known metadata strings onto PDF tokens to get labels at no annotation cost, and discarded documents where the matching failed. The same trick could bootstrap parsers for Ukrainian documents wherever structured records already exist alongside the files. - **Layout features normalized at several scales.** Font size and spacing were normalized relative to the page, the document and the whole corpus. Page number was encoded as a distance from both the start and the end of the file. Together these features help the model notice that titles sit near the beginning and references near the end, which suits any layout-sensitive extraction task. - **Reporting "yield" instead of recall.** When exhaustive gold annotation is impossible, the authors counted correct (paper, entity) pairs rather than claiming a recall figure. This is an honest, cheap way to compare systems on open-ended extraction. - **Conservative blocking rules for author disambiguation.** Two author records are considered for merging only if they share a last name and first initial, and full first names must match when both are spelled out. This keeps clustering scalable and limits false merges, and it would carry over to name matching in trade or geographic records. - **Distant supervision to work around limited KB coverage.** Known definitions and relations from a curated KB were used to auto-label text, so models could learn to find new definitions and relations that the KB lacks. This is useful for any domain where curation lags behind newly published material. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/) ## Cited by Cited by 80 papers of our library cite it (of the 140884 whose bibliographies we read); 13 of them have a page here, 67 not yet. - [Large language models are few-shot clinical information extractors](https://md.research.elamur.ai/free/en/papers/agrawal-2022-large-language-models-are-few/) - [Masader: Metadata Sourcing for Arabic Text and Speech Data Resources](https://md.research.elamur.ai/free/en/papers/alyafeai-2022-masader-metadata-sourcing-arabic-text/) - [SciBERT: A Pretrained Language Model for Scientific Text](https://md.research.elamur.ai/free/en/papers/beltagy-2019-scibert-pretrained-language-model-scientific/) - [Systematic Inequalities in Language Technology Performance across the World's Languages](https://md.research.elamur.ai/free/en/papers/blasi-2022-systematic-inequalities-language-technology-performance/) - [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://md.research.elamur.ai/free/en/papers/cohan-2020-specter-document-level-representation-learning/) - [Paragraph-level Simplification of Medical Texts](https://md.research.elamur.ai/free/en/papers/devaraj-2021-paragraph-level-simplification-medical-texts/) - [Text Generation from Knowledge Graphs with Graph Transformers](https://md.research.elamur.ai/free/en/papers/kedziorski-2019-text-generation-knowledge-graphs-graph/) - [Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art](https://md.research.elamur.ai/free/en/papers/lewis-2020-pretrained-language-models-biomedical-clinical/) - [S2ORC: The Semantic Scholar Open Research Corpus](https://md.research.elamur.ai/free/en/papers/lo-2019-s2orc-semantic-scholar-open-research/) - [Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction](https://md.research.elamur.ai/free/en/papers/luan-2018-multi-task-identification-entities-relations/) - [ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing](https://md.research.elamur.ai/free/en/papers/neumann-2019-scispacy-fast-robust-models-biomedical/) - [Investigating Pretrained Language Models for Graph-to-Text Generation](https://md.research.elamur.ai/free/en/papers/ribeiro-2021-investigating-pretrained-language-models-graph/) - [Benchmarking Retrieval-Augmented Generation for Medicine](https://md.research.elamur.ai/free/en/papers/xiong-2024-benchmarking-retrieval-augmented-generation-medicine/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{ammar2018construction, title = {{Construction of the Literature Graph in Semantic Scholar}}, author = {Ammar, Waleed and Groeneveld, Dirk and Bhagavatula, Chandra and Beltagy, Iz and Crawford, Miles and Downey, Doug and Dunkelberger, Jason and Elgohary, Ahmed and Feldman, Sergey and Ha, Vu and Kinney, Rodney and Kohlmeier, Sebastian and Lo, Kyle and Murray, Tyler and Ooi, Hsu-Han and Peters, Matthew and Power, Joanna and Skjonsberg, Sam and Wang, Lucy Lu and Wilhelm, Chris and Yuan, Zheng and Zuylen, Madeleine van and Etzioni, Oren}, booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)}, year = {2018}, doi = {10.18653/v1/n18-3011}, url = {https://doi.org/10.18653/v1/n18-3011} } ``` - [← previous Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://md.research.elamur.ai/free/en/papers/welbl-2018-constructing-datasets-multi-hop-reading/) - [next → Context-Aware Neural Machine Translation Learns Anaphora Resolution](https://md.research.elamur.ai/free/en/papers/voita-2018-context-aware-neural-machine-translation/) - [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/) ## References 28 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Martin Krallinger, Florian Leitner, Obdulia Rabal, Miguel Vazquez, Julen Oyarzabal, and Alfonso Valencia. 2015. CHEMDNER: The drugs and chemical names extraction challenge. In J. Cheminformatics. [find](https://scholar.google.com/scholar?q=Martin+Krallinger%2C+Florian+Leitner%2C+Obdulia+Rabal%2C+Miguel+Vazquez%2C+Julen+Oyarzabal%2C+and+Alfonso+Valencia%2E+2015%2E+CHEMDNER%3A+The+drugs+and+chemical+names+extraction+challenge%2E+In+J%2E+Cheminformatics%2E) 2. Waleed Ammar, Matthew E. Peters, Chandra Bhagavatula, and Russell Power. 2017. The ai2 system at semeval-2017 task 10 (scienceie): semi-supervised end-to-end entity and relation extraction. In ACL workshop (SemEval). [find](https://scholar.google.com/scholar?q=Waleed+Ammar%2C+Matthew+E%2E+Peters%2C+Chandra+Bhagavatula%2C+and+Russell+Power%2E+2017%2E+The+ai2+system+at+semeval%2D2017+task+10+%28scienceie%29%3A+semi%2Dsupervised+end%2Dto%2Dend+entity+and+relation+extraction%2E+In+ACL+wor) 3. Guillaume Lample, Miguel Ballesteros, Sandeep K Subramanian, Kazuya Kawakami, and Chris Dyer. 2016. Neural architectures for named entity recognition. In HLT-NAACL. [find](https://scholar.google.com/scholar?q=Guillaume+Lample%2C+Miguel+Ballesteros%2C+Sandeep+K+Subramanian%2C+Kazuya+Kawakami%2C+and+Chris+Dyer%2E+2016%2E+Neural+architectures+for+named+entity+recognition%2E+In+HLT%2DNAACL%2E) 4. Isabelle Augenstein, Mrinal Das, Sebastian Riedel, Lakshmi Vikraman, and Andrew D. McCallum. 2017. [find](https://scholar.google.com/scholar?q=Isabelle+Augenstein%2C+Mrinal+Das%2C+Sebastian+Riedel%2C+Lakshmi+Vikraman%2C+and+Andrew+D%2E+McCallum%2E+2017%2E) 5. Semeval 2017 task 10 (scienceie): Extracting keyphrases and relations from scientific publications. In ACL workshop (SemEval). [find](https://scholar.google.com/scholar?q=Semeval+2017+task+10+%28scienceie%29%3A+Extracting+keyphrases+and+relations+from+scientific+publications%2E+In+ACL+workshop+%28SemEval%29%2E) [our card](https://md.research.elamur.ai/free/en/papers/augenstein-2017-semeval-2017-task-10-scienceie/) 6. Jiao Li, Yueping Sun, Robin J. Johnson, Daniela Sci-aky, Chih-Hsuan Wei, Robert Leaman, Allan Peter Davis, Carolyn J. Mattingly, Thomas C. Wiegers, and Zhiyong Lu. 2016. Biocreative v cdr task corpus: a resource for chemical disease relation extraction. Database : the journal of biological databases… [find](https://scholar.google.com/scholar?q=Jiao+Li%2C+Yueping+Sun%2C+Robin+J%2E+Johnson%2C+Daniela+Sci%2Daky%2C+Chih%2DHsuan+Wei%2C+Robert+Leaman%2C+Allan+Peter+Davis%2C+Carolyn+J%2E+Mattingly%2C+Thomas+C%2E+Wiegers%2C+and+Zhiyong+Lu%2E+2016%2E+Biocreative+v+cdr+task+corpus%3A) 7. Chandra Bhagavatula, Sergey Feldman, Russell Power, and Waleed Ammar. 2018. Content-based citation recommendation. In NAACL. [find](https://scholar.google.com/scholar?q=Chandra+Bhagavatula%2C+Sergey+Feldman%2C+Russell+Power%2C+and+Waleed+Ammar%2E+2018%2E+Content%2Dbased+citation+recommendation%2E+In+NAACL%2E) 8. Chandra Bhagavatula, Thanapon Noraset, and Doug Downey. 2015. TabEL: entity linking in web tables. In ISWC. [find](https://scholar.google.com/scholar?q=Chandra+Bhagavatula%2C+Thanapon+Noraset%2C+and+Doug+Downey%2E+2015%2E+TabEL%3A+entity+linking+in+web+tables%2E+In+ISWC%2E) 9. Xiao Ling, Sameer Singh, and Daniel S. Weld. 2015. Design challenges for entity linking. Transactions of the Association for Computational Linguistics 3:315–328. [find](https://scholar.google.com/scholar?q=Xiao+Ling%2C+Sameer+Singh%2C+and+Daniel+S%2E+Weld%2E+2015%2E+Design+challenges+for+entity+linking%2E+Transactions+of+the+Association+for+Computational+Linguistics+3%3A315%E2%80%93328%2E) 10. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel P. Kuksa. 2011. Natural language processing (almost) from scratch. In JMLR. [find](https://scholar.google.com/scholar?q=Ronan+Collobert%2C+Jason+Weston%2C+L%C3%A9on+Bottou%2C+Michael+Karlen%2C+Koray+Kavukcuoglu%2C+and+Pavel+P%2E+Kuksa%2E+2011%2E+Natural+language+processing+%28almost%29+from+scratch%2E+In+JMLR%2E) [our card](https://md.research.elamur.ai/free/en/papers/collobert-2011-natural-language-processing-almost-scratch/) 11. Mike Mintz, Steven Bills, Rion Snow, and Daniel Jurafsky. 2009. Distant supervision for relation extraction without labeled data. In ACL. [find](https://scholar.google.com/scholar?q=Mike+Mintz%2C+Steven+Bills%2C+Rion+Snow%2C+and+Daniel+Jurafsky%2E+2009%2E+Distant+supervision+for+relation+extraction+without+labeled+data%2E+In+ACL%2E) 12. Aron Culotta, Pallika Kanani, Robert Hall, Michael Wick, and Andrew D. McCallum. 2007. Author disambiguation using error-driven machine learning with a ranking loss function. In IIWeb Workshop. [find](https://scholar.google.com/scholar?q=Aron+Culotta%2C+Pallika+Kanani%2C+Robert+Hall%2C+Michael+Wick%2C+and+Andrew+D%2E+McCallum%2E+2007%2E+Author+disambiguation+using+error%2Ddriven+machine+learning+with+a+ranking+loss+function%2E+In+IIWeb+Workshop%2E) 13. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. GloVe: Global vectors for word representation. In EMNLP. [find](https://scholar.google.com/scholar?q=Jeffrey+Pennington%2C+Richard+Socher%2C+and+Christopher+D%2E+Manning%2E+2014%2E+GloVe%3A+Global+vectors+for+word+representation%2E+In+EMNLP%2E) 14. Hal Daumé. 2007. Frustratingly easy domain adaptation. In ACL. [find](https://scholar.google.com/scholar?q=Hal+Daum%C3%A9%2E+2007%2E+Frustratingly+easy+domain+adaptation%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/iii-2007-frustratingly-easy-domain-adaptation/) 15. Matthew E. Peters, Waleed Ammar, Chandra Bhagavatula, and Russell Power. 2017. Semi-supervised sequence tagging with bidirectional language models. In ACL. [find](https://scholar.google.com/scholar?q=Matthew+E%2E+Peters%2C+Waleed+Ammar%2C+Chandra+Bhagavatula%2C+and+Russell+Power%2E+2017%2E+Semi%2Dsupervised+sequence+tagging+with+bidirectional+language+models%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/peters-2017-semi-supervised-sequence-tagging-bidirectional/) 16. Dina Demner-Fushman, Willie J. Rogers, and Alan R. Aronson. 2017. MetaMap Lite: an evaluation of a new Java implementation of MetaMap. In JAMIA. [find](https://scholar.google.com/scholar?q=Dina+Demner%2DFushman%2C+Willie+J%2E+Rogers%2C+and+Alan+R%2E+Aronson%2E+2017%2E+MetaMap+Lite%3A+an+evaluation+of+a+new+Java+implementation+of+MetaMap%2E+In+JAMIA%2E) 17. Noah Siegel, Nicholas Lourie, Russell Power, and Waleed Ammar. 2018. Extracting scientific figures with distantly supervised neural networks. In JCDL. [find](https://scholar.google.com/scholar?q=Noah+Siegel%2C+Nicholas+Lourie%2C+Russell+Power%2C+and+Waleed+Ammar%2E+2018%2E+Extracting+scientific+figures+with+distantly+supervised+neural+networks%2E+In+JCDL%2E) 18. Oren Etzioni. 2011. Search needs a shake-up. Nature 476 7358:25–6. [find](https://scholar.google.com/scholar?q=Oren+Etzioni%2E+2011%2E+Search+needs+a+shake%2Dup%2E+Nature+476+7358%3A25%E2%80%936%2E) 19. Marco Valenzuela, Vu Ha, and Oren Etzioni. 2015. Identifying meaningful citations. In AAAI Workshop (Scholarly Big Data). [find](https://scholar.google.com/scholar?q=Marco+Valenzuela%2C+Vu+Ha%2C+and+Oren+Etzioni%2E+2015%2E+Identifying+meaningful+citations%2E+In+AAAI+Workshop+%28Scholarly+Big+Data%29%2E) 20. Paolo Ferragina and Ugo Scaiella. 2010. TAGME: on-the-fly annotation of short text fragments (by wikipedia entities). In CIKM. [find](https://scholar.google.com/scholar?q=Paolo+Ferragina+and+Ugo+Scaiella%2E+2010%2E+TAGME%3A+on%2Dthe%2Dfly+annotation+of+short+text+fragments+%28by+wikipedia+entities%29%2E+In+CIKM%2E) [our card](https://md.research.elamur.ai/free/en/papers/ferragina-2010-tagme-fly-annotation-short/) 21. Xiang Wang, Yan Dong, Xiang qian Qi, Yi-Ming Li, Cheng-Guang Huang, and Lijun Hou. 2013. Clinical review: Efficacy of antimicrobial-impregnated catheters in external ventricular drainage - a systematic review and meta-analysis. In Critical care. [find](https://scholar.google.com/scholar?q=Xiang+Wang%2C+Yan+Dong%2C+Xiang+qian+Qi%2C+Yi%2DMing+Li%2C+Cheng%2DGuang+Huang%2C+and+Lijun+Hou%2E+2013%2E+Clinical+review%3A+Efficacy+of+antimicrobial%2Dimpregnated+catheters+in+external+ventricular+drainage+%2D+a+systemati) 22. Gus Hahn-Powell, Marco Antonio Valenzuela-Escarcega, and Mihai Surdeanu. 2017. Swanson linking revisited: Accelerating literature-based discovery across domains using a conceptual influence graph. In ACL. [find](https://scholar.google.com/scholar?q=Gus+Hahn%2DPowell%2C+Marco+Antonio+Valenzuela%2DEscarcega%2C+and+Mihai+Surdeanu%2E+2017%2E+Swanson+linking+revisited%3A+Accelerating+literature%2Dbased+discovery+across+domains+using+a+conceptual+influence+graph%2E+In+) 23. Luca Weihs and Oren Etzioni. 2017. Learning to predict citation-based impact measures. In JCDL. [find](https://scholar.google.com/scholar?q=Luca+Weihs+and+Oren+Etzioni%2E+2017%2E+Learning+to+predict+citation%2Dbased+impact+measures%2E+In+JCDL%2E) 24. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation . [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+J%C3%BCrgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+computation+%2E) 25. Jian Wu, Kyle Williams, Hung-Hsuan Chen, Madian Khabsa, Cornelia Caragea, Alexander Ororbia, Douglas Jordan, and C. Lee Giles. 2014. CiteSeerX: AI in a digital library search engine. In AAAI. [find](https://scholar.google.com/scholar?q=Jian+Wu%2C+Kyle+Williams%2C+Hung%2DHsuan+Chen%2C+Madian+Khabsa%2C+Cornelia+Caragea%2C+Alexander+Ororbia%2C+Douglas+Jordan%2C+and+C%2E+Lee+Giles%2E+2014%2E+CiteSeerX%3A+AI+in+a+digital+library+search+engine%2E+In+AAAI%2E) 26. Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Jayant Krishnamurthy, and Luke S. Zettlemoyer. 2017. Learning a neural semantic parser from user feedback. In ACL. [find](https://scholar.google.com/scholar?q=Srinivasan+Iyer%2C+Ioannis+Konstas%2C+Alvin+Cheung%2C+Jayant+Krishnamurthy%2C+and+Luke+S%2E+Zettlemoyer%2E+2017%2E+Learning+a+neural+semantic+parser+from+user+feedback%2E+In+ACL%2E) 27. Chenyan Xiong, Russell Power, and Jamie Callan. 2017. Explicit semantic ranking for academic search via knowledge graph embedding. In WWW. [find](https://scholar.google.com/scholar?q=Chenyan+Xiong%2C+Russell+Power%2C+and+Jamie+Callan%2E+2017%2E+Explicit+semantic+ranking+for+academic+search+via+knowledge+graph+embedding%2E+In+WWW%2E) 28. Antonio J. Jimeno-Yepes, Bridget T. McInnes, and Alan R. Aronson. 2011. Exploiting mesh indexing in medline to generate a data set for word sense disambiguation. BMC bioinformatics 12(1):223. [find](https://scholar.google.com/scholar?q=Antonio+J%2E+Jimeno%2DYepes%2C+Bridget+T%2E+McInnes%2C+and+Alan+R%2E+Aronson%2E+2011%2E+Exploiting+mesh+indexing+in+medline+to+generate+a+data+set+for+word+sense+disambiguation%2E+BMC+bioinformatics+12%281%29%3A223%2E)