As an introduction to the first two papers, consider Wizard of Oz experiments such as used in collecting ATIS data. In such an experiment, the subject is asked to use a system to solve one or more problems. The "system" could be a person who simulates a proposed capability, for instance to determine language and interface properties for a proposed computer capability. Alternatively, the system ...

The VALIDATE project, with 19 partners in nine European countries, started work in late 1995 to verify the DVB standard for digital terrestrial TV broadcasting and to prepare for the launch of services. The work of the Project verified the DVB-T specification, ensuring its acceptance by ETSI, and is now facilitating the early introduction of services. The VALIDATE workplan includes prototype mo...

This paper will look at the challenges involved in creating a scalable wireless network capable of collecting and distributing data from vehicles traveling at arbitrary speeds and locations through the current public transportation system. Observations will be made of available technologies that could be used to provide solutions for the problems that are outlined within this paper. We will als...

Systems that automatically process sign language rely on appropriate data. We therefore present the ATIS sign language corpus that is based on the domain of air travel information. It is available for five languages, English, German, Irish sign language, German sign language and South African sign language. The corpus can be used for different tasks like automatic statistical translation and au...

SRI has developed a spoken language interface to the Official Airline Guide (OAG). Despite a funding gap for more than four months of the year, substantial improvements have been made in the component technologies. On recent ARPA benchmarks. SRI achieved 5.5% word error on the ATIS speech recognition task, 18.2% utterance error on the natural-language understanding task, and 20.7% utterance err...

To train a model for semantic slot filling, manually labeled data in which each word is annotated with a semantic slot label is necessary while manually preparing such data is costly. Starting from a small amount of manually labeled data, we propose a method to generate the labeled data with using the encoderdecoder LSTM. We first train the encoder-decoder LSTM that accepts and generates the sa...

Introduct ion The DARPA Spoken Language communi ty has just completed the first trial evaluation of spontaneous query/response pairs in the Air Travel (ATIS) domain. 1 Our goal has been to find a methodology for evaluating correct responses to user queries. To this end, we agreed, for the first trial evaluation, to constrain the problem in several ways: D a t a b a s e A p p l i c a t i o n : C...

smooth merging, and passing. The Super Smart Vehicle System studies, conducted from 1990 to 1992 by the Japanese Ministry of International Trade and Industry, proposed cooperative driving using intervehicle communication to make traffic safe and efficient. Studies of intervehicle communication had already started in the early ’80s at JSK (the Association of Electronic Technology for Automobile ...

We consider multi-hop multiple access (MAC) and broadcast channels (BC) where communication takes place with the assistance of relays that amplify and forward (AF) their received signals. For a two hop parallel AF relay MAC, assuming a sum power constraint across all relays we characterize optimal relay amplification factors and the resulting capacity regions. We find the sum rate capacity and ...

This paper presents a semantic parser that transforms an initial semantic hypothesis into the correct semantics by applying an ordered list of transformation rules. These rules are learnt automatically from a training corpus with no prior linguistic knowledge and no alignment between words and semantic concepts. The learning algorithm produces a compact set of rules which enables the parser to ...