Abstract | ||
---|---|---|
In QAC-4, we dened question answering task using any type of question, mainly fo- cused on non-factoid questions. There are 8 participants and 14 runs from these par- ticipants. In the evaluation, four kinds of criterion were used for some portion of par- ticipants answer set. The evaluation re- sults showed some of the participant sys- tems could focus on the area which correct answer contents exist but have tendency to fail to extract correct answer areas. It is caused by complex question types and dif- culty of correct answer scope extraction. |
Year | Venue | Field |
---|---|---|
2007 | NTCIR | Question answering,Information retrieval,Complex question,Mathematics,Multiple choice |
DocType | Citations | PageRank |
Conference | 9 | 1.01 |
References | Authors | |
2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Junichi Fukumoto | 1 | 120 | 16.22 |
Tsuneaki Kato | 2 | 271 | 38.70 |
Fumito Masui | 3 | 87 | 27.22 |
Tsunenori Mori | 4 | 9 | 1.01 |