MER: a Minimal Named-Entity Recognition Tagger and Annotation Server
1 like388 views
MER is a minimal named-entity recognition tool and annotation server developed by researchers at the University of Lisbon. It uses simple text files as input lexicons and requires only two components - lexicon processing and annotation generation - implemented as a GNU Bash shell script, allowing it to run on any Unix system. The annotation server uses MER to rapidly recognize entities in text, returning results in under 3 seconds on average by matching text to an inverted lexicon of over 1 million terms. The open-source system requires minimal computational resources and software dependencies.
MER: a Minimal Named-Entity Recognition Tagger and Annotation Server
- 1. MER: a Minimal Named‐Entity Recognition Tagger and Annotation Server Francisco M. Couto, Luis F. Campos, and Andre Lamurias LaSIGE, Faculdade de Ciências, Universidade de Lisboa, Portugal BioCreative V.5 Workshop , April 26‐27, 2017
- 2. Why Minimal? • TIPS (Technical interoperability and performance of annotation servers) – it’s cool, we have to participate somehow • But we have limited computational resources • Idea: Go Minimal – Minimize the number of tools and steps to perform Named‐Entity Recognition (NER)
- 3. What is Minimal? • Flexibility – Simple input • Autonomy – minimal set of components and software dependencies • Efficiency – Low execution time
- 4. How Minimal? • Only requires a lexicon as input – a text file • Only two components: 1. process the lexicon (offline) 2. produce the annotations (on‐the‐fly) • GNU Bash shell script – Using high performance grep and awk tools – Portability: any Unix‐like operating system
- 7. Recognition • Common Solution – Apply grep directly to the input text – execution time is proportional to the size of the lexicon • Inverted Solution – input text as patterns matched against the lexicon – more than 100 times faster • TIPS chemical lexicon
- 11. Input: Lexicons • Cell line and cell type – Cellosaurus • Chemical – HMDB, ChEBI and ChEMBL • Disease: – Human Disease Ontology • miRNA: – miRBase • Protein: – Protein Ontology • Subcellular structure: – cellular component aspect of Gene Ontology • Tissue and organ: – tissue and organ subsets of UBERON https://github.com/lasigeBioTM/MER/raw/biocreative2017/data/TIPS_MER_lexicons_Jan2017.zip
- 13. Input: text • jq – a command‐line JSON processor – to parse the requests • cURL – to download each document • Parsers – PubMed, Patents, PMC https://github.com/lasigeBioTM/MER/tree/biocreative2017/external_services • NO CACHE
- 14. Output • Added some more columns to MER output – BeCalm TSV format • The score – 1‐1/ln(nc), – nc = # characters of the recognized term
- 15. Infrastructure • Three Virtual Machines (VM). – Each ad 8GB of RAM and 4 CPUs @ 1.7 GHz – CentOS Linux release 7.3.1611 (Core) • VM (primary) to process the requests, distribute the jobs, and execute MER. • The other two VMs (secondary) just execute MER. • NGINX as HTTP server running CGI scripts – high performance • Task Spooler to manage and distribute jobs
- 19. Conclusions • MER a minimal NER tagger – Flexible: extensible to any lexicon – Autonomous: only requires a GNU Bash shell – Efficient: high‐performance capacity of grep • Annotation Server – developed in‐house – minimal software dependencies – and is open‐source • Future: entity linking functionality in MER
- 20. Acknowledgments • Portuguese National Distributed Computing Infrastructure (http://www.incd.pt) • Links – https://github.com/lasigeBioTM/MER – http://labs.fc.ul.pt/mer/