Towards Answer Extraction: An application to Technical Domains
نویسندگان
چکیده
The shortcomings of traditional Information Retrieval are most evident when users require exact information rather than relevant documents. This practical need is pushing the research community towards systems that can exactly pinpoint those parts of documents that contain the information requested. Answer Extraction (AE) systems aim to satisfy this need. This paper presents one such system (ExtrAns) which works by transforming documents and queries into a semantic representation called Minimal Logical Form (MLF) and derives the answers by logical proof from the documents. MLFs use underspecification to overcome the problems associated with a complete semantic representation and offer the possibility of monotonic, non-destructive extension.
منابع مشابه
NLP for Answer Extraction in Technical Domains
In this paper we argue that questionanswering (QA) over technical domains is distinctly different from TREC-based QA or Web-based QA and it cannot benefit from data-intensive approaches. Technical questions arise in situations where concrete problems require specific answers and explanations. Finding a justification of the answer in the context of the document is essential if we have to solve a...
متن کاملAnswer Extraction in Technical Domains
In recent years, the information overload caused by the new media has made the shortcomings of traditional Information Retrieval increasingly evident. Practical needs of industry, government organizations and individual users alike push the research community towards systems that can exactly pinpoint those parts of documents that contain the information requested, rather than return a set of re...
متن کاملTerminology as Knowledge in Answer Extraction
It is well known that one of the greatest hurdles in automatically processing technical documentation is the large amount of specific terminology that characterizes these domains. Terminology poses two major challenges to the developers of NLP applications: how to identify domain specific terms in the documents and how to efficiently process them. In this paper we will present methodologies tha...
متن کاملAnswer Extraction Towards Better Evaluations Of NLP Systems
We argue that reading comprehension tests are not particularly suited for the evaluation of NLP systems. Reading comprehension tests are specifically designed to evaluate human reading skills, and these require vast amounts of world knowledge and common-sense reasoning capabilities. Experience has shown that this kind of full-fledged question answering (QA) over texts from a wide range of domai...
متن کاملTowards Cross-lingual Patent Wikification
This paper demonstrates the effectiveness of cross-lingual patent wikification, which links technical terms in a patent application document to their corresponding Wikipedia articles in different languages. The number of links increases definitely because different language versions of Wikipedia cover different sets of technical terms. We present an experiment of Japanese-to-English cross-lingu...
متن کامل