tag:blogger.com,1999:blog-19803222.post3653005519479876992..comments2024-03-18T01:45:45.724-06:00Comments on natural language processing blog: What Irks Me about E-mail Customer Servicehalhttp://www.blogger.com/profile/02162908373916390369noreply@blogger.comBlogger3125tag:blogger.com,1999:blog-19803222.post-57913808388998509322009-05-12T11:01:00.000-06:002009-05-12T11:01:00.000-06:00酒店經紀PRETTY GIRL 台北酒店經紀人 ,禮服店 酒店兼差PRETTY GIRL酒店公關 酒...酒店經紀PRETTY GIRL <A HREF="http://www.taipeilady.com/" REL="nofollow" TITLE="台北酒店經紀人">台北酒店經紀人</A> ,<A HREF="http://tw.myblog.yahoo.com/jw!qZ9n..6QEhhc0LkItOBm/" REL="nofollow" TITLE="禮服店">禮服店</A> 酒店兼差PRETTY GIRL<A HREF="http://www.mashow.org/" REL="nofollow" TITLE="酒店公關">酒店公關</A> 酒店小姐 彩色爆米花<A HREF="http://blog.xuite.net/jkl338801/blog/" REL="nofollow" TITLE="酒店兼職">酒店兼職</A>,酒店工作 彩色爆米花<A HREF="http://tw.myblog.yahoo.com/jw!BIBoU5SeBRs21nb_ajFpncbTqXds" REL="nofollow" TITLE="酒店經紀">酒店經紀</A>, <A HREF="http://mypaper.pchome.com.tw/news/thomsan/3/1310065116/20080905040949/" REL="nofollow" TITLE="酒店上班">酒店上班</A>,酒店工作 PRETTY GIRL<A HREF="http://tw.myblog.yahoo.com/jw!rybqykeeER6TH3AKz1HQ5grm/" REL="nofollow" TITLE="酒店喝酒">酒店喝酒</A>酒店上班 彩色爆米花<A HREF="http://mypaper.pchome.com.tw/news/jkl338801/" REL="nofollow" TITLE="台北酒店">台北酒店</A>酒店小姐 PRETTY GIRL<A HREF="http://www.mashow.org/" REL="nofollow" TITLE="酒店上班">酒店上班</A>酒店打工PRETTY GIRL<A HREF="http://www.tpangel.com/" REL="nofollow" TITLE="酒店打工">酒店打工</A>酒店經紀 彩色爆米花Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-19803222.post-4683418188343457502007-01-18T17:11:00.000-07:002007-01-18T17:11:00.000-07:00This is an interesting and a challenging research ...This is an interesting and a challenging research problem. IBM research, for example, does work on routing email messages at their service centers.<br /><br />To complicate matters, customer messages need not be grammatical. For example, consider bug report for a software product. If the interface is plain text then customers are free to write it any way they want!<br /><br />(Most customers like plain text interfaces instead of restrictive forms)<br /><br />Plain classification might not work again. Consider a complaint mentioning multiple parts of a device. Where should the email be routed? It is tempting to apply ideas from WSD here.Delip Raohttps://www.blogger.com/profile/17504663683160693696noreply@blogger.comtag:blogger.com,1999:blog-19803222.post-35677904071628301042007-01-07T18:34:00.000-07:002007-01-07T18:34:00.000-07:00Kana may interest you. They sell software to mak...<a href="http://www.kana.com">Kana</a> may interest you. They sell software to make handling customer email more efficient.<br /><br />From their description of their Kana Response product: "Based on configurable rules, KANA Response interprets message content to determine customer intent and uses templates to automatically send personalized acknowledgements and replies. Intelligent queuing and routing distribute messages to the appropriate departmental, priority, language and skill-based queues where automatically suggested, fully scripted answers reduce the time agents need to review and reply to inquiries. ...<br />Agent email response efficiency and effectiveness accelerate with a broad range of productivity tools including desktop population with most likely solutions, pre-filled replies that include context-specific customer data aggregated from back-end systems, canned phrase selection, user-defined hotkeys and a universal history of interactions that maintains context across channels." <br /><br />And from their description of their Kana IQ product: "The advice-driven desktop leverages expert reasoning to automate best-practice diagnostic processes for interpreting the customer’s intent and mapping intent to the right answer. Expert reasoning combines multiple information access methodologies that help agents rapidly find the correct solution. These include clarifying questions that turn Natural Language Queries into diagnostic conversations; guided interviews that eliminate answers until the best one is found; expert modeling which leverages specialists’ advice to present answers in order of relevance; and dynamic learning that polls solution history and usage to present solutions in order of popularity."David Gelbarthttps://www.blogger.com/profile/09930813569213912228noreply@blogger.com