Information Extraction from Voicemail Transcripts

Information Extraction from Voicemail Transcripts Martin Jansche Department of Linguistics The Ohio State University Columbus, OH 43210, USA jansche.1@osu.edu Steven P. Abney AT&T Labs – Research 180 Park Avenue Florham Park, NJ 07932, USA abney@research.att.com Abstract Voicemail is not like email. Even such ba- sic information as the name of the caller/ sender or a phone number for returning calls is not represented explicitly and must be obtained from message transcripts or other sources. We discuss techniques for doing this and the challenges these tasks present. 1 Introduction When you’re away from the phone and someone takes a message for you, at the very least you’d ex- pect to be told who called and whether they left a number for you to call back. If the same call is picked up by a voicemail system, even such basic in- formation like the name of the caller and their phone number may not be directly available, forcing one to listen to the entire message1 in the worst case. By contrast, information about the sender of an email message has always been explicitly represented in the message headers, starting with early standard- ization attempts (Bhushan et al., 1973) and including the two decade old current standard (Crocker, 1982). Applications that aim to present voicemail messages through an email-like interface – take as an example the idea of a “uniform inbox” presentation of email, voicemail, and other kinds of messages2 – must deal with the problem of how to obtain information anal- ogous to what would be contained in email headers. 1The average message length in the corpus described below is 36 seconds. 2Similar issues arise with FAX messages, for example. Here we will discuss one way of addressing this problem, treating it exclusively as the task of extract- ing relevant information from voicemail transcripts. In practice, e.g. in the context of a sophisticated voicemail front-end (Hirschberg et al., 2001) that is tightly integrated with an organization-wide voice- mail system and private branch exchange (PBX), ad- ditional sources of information may be available: the voicemail system or the PBX might provide infor- mation about the originating station of a call, and speaker identification can be used to match a caller’s voice against models of known callers (Rosenberg et al., 2001). Restricting our attention to voicemail transcripts means that our focus and goals are sim- ilar to those of Huang et al. (2001), but the features and techniques we use are very different. While the present task may seem broadly similar to named entity extraction from broadcast news (Go- toh and Renals, 2000), it is quite distinct from the latter: first, we are only interested in a small subset of the named entities; and second, the structure of the voicemail transcripts in our corpus is very dif- ferent from broadcast news and certain aspects of this structure can be exploited for extracting caller names. Huang et al. (2001) discuss three approaches: hand-crafted rules; grammatical inference of subse- quential transducers; and log-linear classifiers with bigram …

Content truncated to 500 words