The Pronto QA System at TREC 2007: Harvesting Hyponyms, Using Nominalisation Patterns, and Computing Answer Cardinality
نویسندگان
چکیده
The backbone of the Pronto QA system is linguistically-principled: Combinatory Categorial Grammar is used to generate syntactic analyses of questions and potential answer snippets, and Discourse Representation Theory is employed as semantic formalism to match the meanings of questions and answers. The key idea of the Pronto system is to use semantics to prune answer candidates, thereby exploiting lexical resources such as WordNet and NomLex to facilitate the selection of answers. The system performed well at TREC-2007 on factoid-questions with an answer accuracy of 22%, a score higher than the median accuracy score of all participating systems.
منابع مشابه
Answer Attenuation in Question Answering
Research in Question Answering (QA) has been dominated by the TREC methodology of black-box system evaluation. This makes it difficult to evaluate the effectiveness of individual components and requires human involvement. We have collected a set of answer locations within the AQUAINT corpus for a sample of TREC questions, in doing so we also analyse the ability of humans to retrieve answers. Ou...
متن کاملTALP-UPC at TREC 2005: Experiments Using a Voting Scheme Among Three Heterogeneous QA Systems
This paper describes the experiments of the TALPUPC group for factoid and ’other’ (definitional) questions at TREC 2005 Main Question Answering (QA) task. Our current approach for factoid questions is based on a voting scheme among three QA systems: TALP-QA (our previous QA system), Sibyl (a new QA system developed at DAMA-UPC and TALP-UPC), and Aranea (a web-based data-driven approach). For de...
متن کاملIITD-IBMIRL System for Question Answering Using Pattern Matching, Semantic Type and Semantic Category Recognition
A Question Answering (QA) system aims to return exact answers to natural language questions. While today information retrieval techniques are quite successful at locating within large collections of documents those that are relevant to a user’s query, QA techniques that extract the exact answer from these retrieved documents still do not obtain very good accuracies. We approached the TREC 2007 ...
متن کاملThe University of Amsterdam at the TREC 2007 QA Track
In our participation in the TREC 2007 Question Answering (QA) track, we focused on three tasks. First, we processed the new blog corpus and converted it to formats which could be used by our QA system. Second, we rewrote the module interface code in Java in order to improve the maintainability of the system. And third, we added a new table stream which has learned associations between question ...
متن کاملHuman Question Answering Performance using an Interactive Information Retrieval System
Every day, people widely use information retrieval (IR) systems to find documents that answer their questions. Compared to these IR systems, question answering (QA) systems aim to speed the rate at which users find answers by retrieving answers rather than documents. To better understand how IR systems compare to QA systems, we measured the performance of humans using an interactive IR system t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007