Growing Multi-Domain Glossaries from a Few Seeds using Probabilistic Topic Models

GlossBoot: Bootstrapping Multilingual Domain Glossaries from the Web

Seed Words Based Data Selection for Language Model Adaptation

We address the problem of language model customization in applications where the ASR component needs to manage domain-specific terminology; although current state-of-the-art speech recognition technology provides excelle…

Investigating automatic and manual filtering methods to produce MT-ready glossaries from existing ones

Commercial Machine Translation (MT) providers offer functionalities that allow users to leverage bilingual glossaries. This poses the question of how to turn glossaries that were intended to be used by a human translator…

Seed Stocking Via Multi-Task Learning

Sellers of crop seeds need to plan for the variety and quantity of seeds to stock at least a year in advance. There are a large number of seed varieties of one crop, and each can perform best under different growing cond…

Directed Probabilistic Watershed

The Probabilistic Watershed is a semi-supervised learning algorithm applied on undirected graphs. Given a set of labeled nodes (seeds), it defines a Gibbs probability distribution over all possible spanning forests disco…