Improving Quantitative Understanding Using Spreadsheet Models

Improving speech understanding accuracy with limited training data using multiple language models and multiple understanding models

We aim to improve a speech understanding module with a small amount of training data. A speech understanding module uses a language model (LM) and a language understanding model (LUM). A lot of training data are needed to improve the models. Such data collection is, however, difficult in an actual process of development. We therefore design and develop a new framework that uses multiple LMs and...

Improving Spoken Dialogue Understanding Using Phonetic Mixture Models

Reasoning about sound similarities improves the performance of a Natural Language Understanding component that interprets speech recognizer output: we observed a 5% to 7% reduction in errors when we augmented the word strings with a phonetic representation, derived from the words by means of a dictionary. The best performance comes from mixture models incorporating both word and phone features....

Refactoring Smelly Spreadsheet Models

Identifying bad design patterns in software is a successful and inspiring research trend. While these patterns do not necessarily correspond to software errors, the fact is that they raise potential problematic issues, often referred to as code smells, and that can for example compromise maintainability or evolution. The identification of code smells in spreadsheets, which can be viewed as soft...

Spreadsheet-based GIS Models

Spreadsheet Visualisation to Improve End-user Understanding