Unsupervised question answering data acquisition from local corpora
Proceedings of the thirteenth ACM international conference on Information and knowledge management
Question answering as question-biased term extraction: a new approach toward multilingual QA
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Hi-index | 0.00 |
This work presents a strategy to answer questions about locations based on a character alignment algorithm that ranks Google snippets according to their similarity with the query. Answer candidates are extracted by using a Name-Entity Recognizer and then ranked according to their position in this new rank. Results concerning questions on location of monuments and cities around the world are discussed.