SOLICITATION NOTICE
B -- Ontology and Natural Language Processing White Paper
- Notice Date
- 9/15/2006
- Notice Type
- Solicitation Notice
- NAICS
- 511210
— Software Publishers
- Contracting Office
- US Army Medical Research Acquisition Activity, ATTN: MCMR-AAA, 820 Chandler Street, Frederick, MD 21702-5014
- ZIP Code
- 21702-5014
- Solicitation Number
- W81XWH-06-P-0983A
- Response Due
- 9/22/2006
- Archive Date
- 11/21/2006
- Small Business Set-Aside
- N/A
- Description
- This is a combined synopsis/solicitation for commercial items prepared in accordance with the format in Subpart 12.6, as supplemented with additional information included in this notice. This announcement constitutes the only solicitation; proposals are being requested and a written solicitation will not be issued. Objectives: A. General: The Clinical Information Technology Program Office (CITPO) established a Terminology Service Bureau (TSB) to meet the terminology requirements of the Armed Forces Health Longitudinal Technology Application (AHLTA). The TSB is based on a central domain-onto logy called the Military Health System Core Ontology (MHSCO). With the deployment of AHLTA, there is a need to deal with the unstructured free text format of typed and dictated/transcribed notes in AHLTA. Natural Language Processing (NLP), in combination with an ontology, is a technology proposed to extract meaningful data from the free text documents that can represent and manipulate meanings of texts. As an example, ontologies can provide the difference in meaning for the word discharge, such as a discharge from the nose or a patient discharge from the hospital. However in addition to the meanings of words, grammar and logic are necessary to combine the meanings into a complete semantic representation. For example the word discharge can be used as a noun, verb or an adjective in the following sentences: " The patient's discharge was at 8 AM " The physician planned to discharge the patient the next morning. " The nurse gave the patient discharge instructions. Lexicons can provide the details of the grammatical structure of each word (morphology), its part of speech, and the meaning of the word in different textual contexts, e.g. depending on the word or punctuation mark before or after it. Traditional grammar c lassifies words based on eight parts of speech: the verb, the noun, the pronoun, the adjective, the adverb, the preposition, the conjunction, and the interjection. Each part of speech explains not what the word is, but how the word is used. The same word c an be a noun in one sentence and a verb or adjective in the next as seen the example of the word discharge above. TATRC requires consultation from personnel who are recognized experts in clinical and linguistic ontologies within the context of Natural Language Processing (NLP). The MHSCO was originally created by Language and Computing, Inc., with a normalized versio n of SNOMED CT? that was used both as a Domain Ontology and as an external terminology. The government seeks a vendor intimately familiar with Language and Computings ontologies to provide a white paper describing the advantages, benefits, approaches, a nd risks of approaches to adding natural language processing capability to the TSB Ontology B. Work Description: The vendor shall provide personnel with demonstrated experience and ability to provide enterprise-wide technical management and direction for problem definition, analysis and requirements, development and implementation, for very complex systems in the su bject matter area. The vendor must also be able to provide workable recommendations and advice to client executive management on emerging technology, system improvements and maintenance related to NLP-enabling the TSB. The vendor must be able to work with current MHS contractors also working in this domain, including Wisper/IMC, Inc.; NGIT; MEDICOMP; and Nuance, to determine alternatives to NLP enable the TSB and/or AHLTA to include a thorough analysis of costs and ben efits. Task 1 Natural Language Processing Use Case Requirements Workshop L&C will provide a one day workshop with the key stakeholders. Objectives include identifying the vision for using NLP in MHS and identifying the impact of such cases on the approach for enabling NLP in the TSB Ontology. L&C will provide background and f oundational training in natural language processing, ontologies, and lexicons to the participants in the workshop. TATRC Task Manager and L&C shall agree on the stated goals, objectives, and schedule prior to commencement of workshop. Task 2 White Paper " Create white paper describing the analysis, findings, advantages, benefits and risks of approaches to adding natural language processing capability to the TSB Ontology. " Investigate the possibility of creation and use of a Generic LinKBase/NLP ontology " Identify the levels and types of effort for creating the Generic LinKBase/NLP ontology " Describe the core design of solution and the investigation of viability " Identify the level and types of effort for modifying basic TeSSI platform to work with the components to work with the part of speech mapping/derivation from the Generic LinKBase/NLP ontology. " Analyze the effort of mapping Generic LinKBase/NLP ontology to TSB Ontology o Identify the options and effectiveness of automation o Identify the necessity to add a different upper level framework to the TSB Ontology o Analyze mapping requirements for the generic LinKBase NLP to the TSB Ontology " Initial questions to be considered: " When parts of speech, word classes, and features are extrapolated to children of concepts in the TSB Ontology and are attached to concepts in the Generic LinKBase without issues, what mechanisms can put place to ensure that lexicon information is being p ropagated through correct concept modeling? " What parties will manage the generated lexemes? " How will storage of lexemes be handled? Analyze options for adding and maintaining part of speech information to TSB ontology " Transposition from LinKBase and using the part of speech generator " Describe the design and effort of adding the required upper level framework to the TSB ontology in order to map part of speech information " Describe the design and effort of creating a mechanism to maintain part of speech generation for newly added terms in the TSB Ontology and the consequent changes in modeling processes. " Documentation of findings and analysis " Describe analysis, findings, advantages, benefits and risks of options for adding natural language processing technology to the TSB Ontology in a white paper. Task 3: Presentation of Findings " Create and deliver a presentation of analysis, findings, advantages, benefits and risks of options for adding natural language processing technology to the TSB Ontology. C. Deliverables - Due Dates to be determined by the Government 1 Requirements/Use Case Workshop 2 White Paper of Analysis, Findings and Recommendations 3 Presentation of Analysis, Findings and Recommendations, not to exceed one year from date of award D. Proposal Submission Requirements: The vendor shall provide the number of labor hours, labor categories, labor rates, travel costs, and other direct costs for each Task.
- Place of Performance
- Address: US Army Medical Research Acquisition Activity ATTN: MCMR-AAA, 820 Chandler Street Frederick MD
- Zip Code: 21702-5014
- Country: US
- Zip Code: 21702-5014
- Record
- SN01145384-W 20060917/060915221602 (fbodaily.com)
- Source
-
FedBizOpps Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's FBO Daily Index Page |