Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/www2012/paper/409> ?p ?o. }
Showing items 1 to 15 of
15
with 100 items per page.
- 409 creator anna-shtok.
- 409 creator gideon-dror.
- 409 creator idan-szpektor.
- 409 creator yoelle-maarek.
- 409 type InProceedings.
- 409 label "Learning from the Past: Answering New Questions with Past Answers".
- 409 sameAs 409.
- 409 abstract "Community-based Question Answering sites, such as Yahoo! Answers and Baidu Zhidao allow users to get answers to complex, detailed and personal questions from other users. However, since answering a question depends on the ability and willingness of users to address the asker's needs, a significant fraction of the questions remain unanswered. We measured that in Yahoo! Answers, this fraction represents 15% of all incoming English questions. At the same time, we discovered that between 20% and 34% of questions in certain categories are recurrent, at least at the question-title level. We propose a method for reducing the rate of unanswered questions in Yahoo! Answers by reusing the large repository of past resolved questions, openly available on the site. More specifically, we estimate the probability that certain new questions be satisfactorily answered by a best answer from the past, using a statistical model specifically trained for this task. We leverage concepts and methods from query-performance prediction and natural language processing in order to extract a wide range of features for our model. The key challenge here is to serve high quality answers, while maintaining a reasonable coverage of answers for the incoming question flow. We evaluated our algorithm on offline data extracted from Yahoo! Answers, but more interestingly, also on online data by using three live answering robots that automatically provide past answers to new questions when a certain degree of confidence is reached. Analyzing the activity of these robots we show that the rate of best answers given by the question askers is similar or better than the one of an average user.".
- 409 hasAuthorList authorList.
- 409 isPartOf proceedings.
- 409 keyword "Community-based question answering".
- 409 keyword "Question Matching".
- 409 keyword "Question and Answer retrieval".
- 409 keyword "Yahoo! Answers".
- 409 title "Learning from the Past: Answering New Questions with Past Answers".