One of the main problems in automatic Directory Assistance (DA) for business listings is that customers formulate their requests for the same listing with a great variability. In this paper we show that an automatic approach allows to detect, from field data, user formulations that were not foreseen by the designers, and that can be added, as variants, to the denominations already included in the system to reduce its failures.

Telecom ltalia has deployed since the beginning of year 2001 a nationwide automatic Directory Assistance (DA) system that routinely serves customers asking for residential and business listings. DA for business listings is a challenging task: one of its main problems is that customers formulate their requests for the same listing with a great variability. Since it is difficult to reliably predict a priori the user formula tions, in this paper we ' propose a procedure for detecting, from field data, user formulations that were not foreseen by the designers. These formulations can be added, as variants, to the denominations already included in the system to reduce its failures.We show that using a large database ass ociating phonetic tran scriptions of user utterances with the phone number provided by the automatic service, a completely unsupervised approach detects most of the old formulations. Furthermore, our proce dure is able to filter a huge amount of calls routed to the op erators, and to detect B limited number of phonetic strings that are good candidate to be included as new formulation variants in the system vocabulary. l. IntroductionDA is the most used service that Telecom operators otTer to their customers. This service is expensive because it relies on a multitude of human operators. A strategy for reducing these costs is to reduce the work time of the operators providing information collected by an Automatic Speech Recognizer, another strategy is to rely as much as possible to complete automation.Several ASR technology providers have worked on problems related to DA, but most of the work has been concentrated 01\ locality and penon name recogniti on [3), [5], for example. This is not surprising because it is difficult to reliably predict a priori the user formulations for business listings. However, since the vast majority of the calls to the DA services are related to business listings, to reduce the service costs, most of the efforts should be devoted to this category of calls.The second strategy has been selected by Telecom Italia, that has deployed since the beginning of year 2001 a nationwide automatic DA system, jointly developed with Loquendo (formerly CSELT), that routinely serves customers asking for residential and business listings. Whenever the automatic system is unable to terminate the transaction with the cus tomer, the call is routed to a human operator. A description of the system, related to the management of the residential calls, has been presented in [1 J. 0-7803-7402-9/02/$17.00 «':)2002 IEEE 1-17The analysis of the traffi c has shown that about 80% of the DA customer accesses are related to business listings. it is important, thus, to improve the percentage of success of the automatic system for this class of calls. The Loquendo approac h to DA for business listing is based on large vocabulary isolated word recognition technology, where the sequence of words of a business listing is concate nated and transcribed as a single word, with possible silences in between . Since the co...

No abstract

Automatic Directory Assistance (DA) for business listings poses many application specific problems. One of the main problem is that customers formulate their requests for the same listing with a great variability. This paper presents the results of a study aiming at the evaluation of an approach towards automatic learning, from field data, of expressions typically used by customers to formulate their requests for the most frequent business listings. We use a clustering procedure that exploits the association of the phonetic string produced by a lexical unconstrained search for a given denomination pronounced by the user and the phone number provided by the system or by the human operator, in case of failure of the automatic DA service. We show that an unsupervised approach allows to detect user formulations that were not foreseen by the designers, and that can be added, as variants, to the denominations already included in the system to reduce its failures.

<p>A collaboration between the Department of Environmental, Land and Infrastructure Engineering of Politecnico di Torino and the theatre group Faber Teater resulted in “<strong>Cambiare il clima</strong>” (Eng: Change the climate, trailer: https://youtu.be/3LTOE3wIoZM): a <strong>theatre play</strong> taking inspiration from research on <strong>climate change</strong> monitoring, adaptation and mitigation solutions carried out at Politecnico di Torino, to stimulate reflection on the phenomenon in a wide audience.</p> <p>The wide theme of climate-related consequences for humankind urges to <strong>enter into mainstream storytelling</strong>. For a long while, the narrative around climate change struggled to find its place in literature, cinema and other arts (see A. Gosh, The Great Derangement). This play attempts to create such a space by telling a story about what science can do about climate change and the importance to intertwine technological progress with economic and political decisions.</p> <p>The <strong>main challenge</strong> in creating the play was to communicate the exciting world of academic research, without giving up scientific rigor and to highlight the <strong>surprising common ground of science and theatre</strong>, namely their human, practical and even artisanal dimension. Towards this end, <strong>artists</strong> had to dive into science and engineering while <strong>researchers</strong> had to raise their awareness about how their work can stimulate emotions, which are key to deliver important messages to society, such as those related to climate change. The goal was to balance lightness, irony and drama, conveying urgency to the audience, without surrendering to sensationalism.</p> <p>The play was first performed in November 2020 at Politecnico di Torino during Biennale Tecnologia (an important event about technology, in Italy). Since then, it was repeated several times in festivals, events for science communication, schools, etc. It has also received two <strong>awards</strong>: (1) it was selected among the works published in the Climate ChanCe 2022 creative communication competition organised by Shylock - University Theatre Centre, Venice; (2) one of the videos composing the play won the "Future Earth" award of the Earth Futures Festival, an initiative promoted by UNESCO - International Geoscience Programme and the International Union of Geological Sciences in 2022.</p> <p>The presentation will include:</p> <p>- preferably an oral <strong>presentation</strong>, summarizing the process that led to the design of the play, the incentives that moved both the researchers and the actors in undertaking this initiative, the challenges they faced and the lessons learnt;</p> <p>- a <strong>short video displaying some excerpts from “Cambiare il clima”</strong> (with English subtitles), to show the structure of the play, what the researchers’ role was and how they interacted with the actors.</p> <p> </p> <p><strong><em>Note to the Conveners</em></strong>: since some of the researchers involved in the play – besides the authors - will attend EGU2023, it will be possible also to involve them to listen about their experience, during the presentation or next to the display.</p>