• Corpus ID: 12032370

Evaluation of Open-vs . Restricted-Domain Question Answering Systems in the Biomedical Field

@inproceedings{OlveraLobo2010EvaluationOO,
  title={Evaluation of Open-vs . Restricted-Domain Question Answering Systems in the Biomedical Field},
  author={Mar{\'i}a-Dolores Olvera-Lobo and Juncal Guti{\'e}rrez-Artacho},
  year={2010}
}
Question Answering Systems (hereinafter QA systems) tand as a new alternative for Information Retrieval Systems. We conducted a study to evaluate the efficiency of QA systems as terminological sources for physicians , pecialized translators, and users in general. To this end we anlysed the performance of two open-domain and two r estricteddomain QA systems. The research entailed a collectio n of one hundred fifty definitional questions from WebMed. We studied the sources that QA systems used to… 

Figures and Tables from this paper

Question-Answering and E-Health: An advanced perspective in Specialized Information Retrieval
TLDR
The state of Biomedical QA systems, the performance of those systems on the Web, and new trends in this emerging area of Information Retrieval are analyzed.
A Review and Future Perspectives of Arabic Question Answering Systems
  • S. Ray, K. Shaalan
  • Computer Science
    IEEE Transactions on Knowledge and Data Engineering
  • 2016
TLDR
The most commonly used architecture for the development of an Arabic QAS, known as pipeline architecture, has been presented and a list of techniques, tools, and computational linguistic resources, required to implement the components of the presented pipelined architecture, are described.
Trustworthiness and relevance in web-based clinical question answering.
TLDR
It is shown, however, in a comparative evaluation, that promoting trustworthiness has no negative effect on the relevance of the retrieved answers in the authors' clinical QA system and on the contrary, the answers found are in general more relevant.
Qcorp: an annotated classification corpus of Chinese health questions
TLDR
A Chinese health question corpus including 5000 manually annotated questions is developed and would contribute to the intelligent health QA system development and is openly accessible.
Evaluación del rendimiento de los sistemas de búsqueda de respuestas de dominio general
TLDR
Four answer search systems available online have been analyzed and they show that these systems, although each one different, are potentially valid for precise information retrieval of diverse types and thematic areas.
Nuevas tendencias en recuperación de información: la búsqueda de respuestas desde la perspectiva de la traducción
espanolEn el entorno de la Web la sobrecarga de informacion se deja sentir aun mas que en otros contextos. De esta forma, en demasiadas ocasiones, al plantear una determinada consulta en las

References

SHOWING 1-10 OF 40 REFERENCES
Question-answering systems as efficient sources of terminological information: an evaluation.
TLDR
Results obtained show the potential of this type of tool in the more general realm of information access, and the retrieval of health information, as a good, reliable and reasonably precise alternative in alleviating the information overload.
Towards a Medical Question-Answering System: a Feasibility Study
TLDR
The feasibility of a question-answering system for French in the health care domain, using UMLS Semantic Network relations, which is consistent with an existing QA prototype and covers 90% of the questions is studied.
Response Quality Evaluation in Heterogeneous Question Answering System: A Black-box Approach
TLDR
The inappropriateness of the existing measure for response quality evaluation is discussed, the call for new standard measures and the related considerations are brought forward and a black-box approach is presented using observation, classification scheme and a scoring mechanism to assess and rank three example systems.
A Cognitive Evaluation of Four Online Search Engines for Answering Definitional Questions Posed by Physicians
TLDR
The first cognitive evaluation of four state-of-the-art Internet search engines for answering definitional questions posed by physicians concludes that Google is an effective search engine for medical definitions, and that MedQA exceeds the other search engines in that it provides users direct answers to their questions; while the users of the other searches have to visit several sites before finding all of the pertinent information.
What about trust in the Question Answering world ?
TLDR
This paper presents a solution using an existing question answering system and investigates whether thequality of the answers extracted depends on the quality of the health web pages analysed.
Beyond Information Retrieval - Medical Question Answering
TLDR
The authors address physicians' information needs and described the design, implementation, and evaluation of the medical question answering system (MedQA), which aims to enable MedQA to answer all types of medical questions.
Question answering in biomedicine
The recent developments in Question Answering have kept with open-domain questions and collections, sometimes argued as being more di fficult than narrow domain-focused questions and corpora. The
New Directions in Question Answering
TLDR
Key areas of research and development include current methods, architecture requirements, and the history of question answering on the Web; the development of systems to address new types of questions; interactivity; reuse of answers; advanced methods; and knowledge representation and reasoning used to support question answering.
The TREC-8 Question Answering Track Report
TLDR
An overtemperature and overcurrent resistor fuse has a relatively low electrical resistance below a selected melting temperature and has an irreversible abrupt increase of electrical resistance above the selected meltingTemperature range caused by serious overload or overheating conditions.
...
...