Text-to-text generation for question answering
| Autor: | Bosma, W.E., Marsi, Erwin, Krahmer, Emiel, Theune, Mariet, van den Bosch, Antal, Bouma, Gosse |
|---|---|
| Přispěvatelé: | van den Bosch, A., Bouma, G, Language and Communication, Language, Communication and Cognition |
| Jazyk: | angličtina |
| Rok vydání: | 2011 |
| Předmět: |
Information retrieval
Computer science business.industry IR-78522 EWI-20800 Information needs computer.software_genre METIS-281563 Fluency Text generation Question answering Graph (abstract data type) Artificial intelligence tf–idf business computer Natural language processing Sentence Selection system |
| Zdroj: | Bosma, W E, Marsi, E C, Krahmer, E J & Theune, M 2011, Text-to-text generation for question answering . in A van den Bosch & G Bouma (eds), Interactive Multi-modal Question-Answering . Theory and Applications of Natural Language Processing, no. 7, Springer Verlag, Heidelberg, Dordrecht, London, New York, pp. 117-148 . https://doi.org/10.1007/978-3-642-17525-1_6 Interactive Multi-modal Question-Answering, 117-145 STARTPAGE=117;ENDPAGE=145;TITLE=Interactive Multi-modal Question-Answering Interactive Multi-modal Question-Answering, 117-148 STARTPAGE=117;ENDPAGE=148;TITLE=Interactive Multi-modal Question-Answering Interactive Multi-modal question answering, 117-145 STARTPAGE=117;ENDPAGE=145;TITLE=Interactive Multi-modal question answering Interactive Multi-modal Question-Answering ISBN: 9783642175244 Interactive Multi-modal Question-Answering |
| DOI: | 10.1007/978-3-642-17525-1_6 |
| Popis: | In this chapter, we describe our efforts in text-to-text generation within the IMOGEN project. In particular, we describe two focus areas of research to improve the quality of the answer: (a) graph-based content selection to improve the answer in terms of usefulness, and (b) sentence fusion to improve the answer in terms of formulation. We use sentence fusion to join together multiple sentences in order to eliminate overlapping parts, thereby reducing redundancy. The results of this work have been applied in the IMIX system. This system uses a question answering system to pinpoint fragments of text which are relevant to the information need expressed by the user. A content selection system then uses these fragments as entry points in the text to formulate a more complete answer. Sentence fusion is applied to manipulate the result in order to increase the fluency of the text. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|