Translation control: Learning from viruses, again

Machine Translation Again?

Machine translation (MT) remains the paradigm task for natural language processing (NLP) since its inception in the 1950s. Unless NIP can succeed with the central task of machine translation, it cannot be considered successful as a field. We maintain that the most profitable approach to MT at the present time is an interlingual and modular one. MT is one the precious few computational tasks fal...

Learning speech translation from interpretation

Globalization spurs the need for cross-lingual verbal communication. This is reflected in ongoing research in the field of speech translation. However, the development of deployable speech translation systems still happens only for a handful of languages. Prohibitively high costs attached to the acquisition of sufficient amounts of suitable training data are one of the main reasons for this sit...

LEARNING TRANSLATION TEMPLATES FROM EXAMPLESyH

Learning Translation Templates from Examples1

This paper proposes a mechanism for learning lexical level correspondences between two languages from a set of translated sentence pairs. The proposed mechanism is based on an analogical reasoning between two translation examples. Given two translation examples, the similar parts of the sentences in the source language must correspond the similar parts of the sentences in the target language. S...

From Exact Learning to Computing Boolean Functions and Back Again

The goal of the paper is to relate complexity measures associated with the evaluation of Boolean functions (certificate complexity, decision tree complexity) and learning dimensions used to characterize exact learning (teaching dimension, extended teaching dimension). The high level motivation is to discover non-trivial relations between exact learning of an unknown concept and testing whether ...