{"type":"ScholarlyArticle","title":"A Predictive Approach to Help-Desk Response Generation","authors":[{"name":"Yuval Marom","slug":"yuval-marom","given":"Yuval","family":"Marom","affiliation":""},{"name":"Ingrid Zukerman","slug":"ingrid-zukerman","given":"Ingrid","family":"Zukerman","affiliation":""}],"abstract":"We are developing a corpus-based approach for the prediction of help-desk responses from features in customers' emails, where responses are represented at two levels of granularity: document and sentence. We present an automatic and human-based evaluation of our system's responses. The automatic evaluation involves textual comparisons between generated responses and responses composed by help-desk operators. Our results show that both levels of granularity produce good responses, addressing inquiries of different kinds. The human-based evaluation measures response informativeness, and confirms our conclusion that both levels of granularity produce useful responses.","doi":null,"url":"https://ijcai.org/proceedings/2007/269","pdf":"https://ijcai.org/proceedings/2007/0269.pdf","markdown":"https://ijcai.org/proceedings/2007/269.md","bibtex":"https://ijcai.org/proceedings/2007/bibtex/269","volume":{"slug":"2007","title":"Proceedings of the Twentieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2007","url":"https://ijcai.org/proceedings/2007/","year":2007,"location":"Hyderabad, India","dates":"","editors":"Ramon López de Mántaras","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":269,"pages":{"first":1665,"last":1669},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}