Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1809741, author = {Medveď, Marek and Sabol, Radoslav and Horák, Aleš}, address = {Brno}, booktitle = {Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)}, editor = {Horák, Rychlý, Rambousek}, keywords = {Question answering; Answer selection; Answer context; Evaluation}, howpublished = {tištěná verze "print"}, language = {eng}, location = {Brno}, isbn = {978-80-263-1670-1}, pages = {61-69}, publisher = {Tribun EU}, title = {Evaluating Long Contexts in the Czech Answer Selection Task}, url = {https://nlp.fi.muni.cz/raslan/raslan21.pdf#page=69}, year = {2021} }
TY - JOUR ID - 1809741 AU - Medveď, Marek - Sabol, Radoslav - Horák, Aleš PY - 2021 TI - Evaluating Long Contexts in the Czech Answer Selection Task PB - Tribun EU CY - Brno SN - 9788026316701 KW - Question answering KW - Answer selection KW - Answer context KW - Evaluation UR - https://nlp.fi.muni.cz/raslan/raslan21.pdf#page=69 N2 - In the search for the answer to an open-domain question, the size of the search window, or the answer context, can greatly influence the resulting determination of the answer. The presented paper offers a detailed evaluation of different sizes of the answer context in case of Czech question answering. We compare six different context types in four different lengths. The conclusion of the experiments is that prolonging the context can improve the precision for specific types but in general the best results are obtained with one-sentence contexts. ER -
MEDVEĎ, Marek, Radoslav SABOL and Aleš HORÁK. Evaluating Long Contexts in the Czech Answer Selection Task. In Horák, Rychlý, Rambousek. \textit{Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)}. Brno: Tribun EU, 2021, p.~61-69. ISBN~978-80-263-1670-1.
|