System Name
Amalgam
B2Z list of NLG systems
System Builders Gamon, Ringger, Corston-Oliver, Moore
Development Dates 2001-ongoing
Languages German, French, English
URL (if available) http://research.microsoft.com/nlp/Projects/AmalgamProject.aspx
who's who


Description:

Amalgam is a novel system developed in the Natural Language Processing group at Microsoft Research for sentence realization during natural language generation. Sentence realization is the process of generating (“realizing”) a fluent sentence from a semantic representation. From the outset, the goal of the Amalgam project has been to build a sentence realization system in a data-driven fashion using machine learning techniques. Amalgam accepts as input a logical form graph capturing the meaning of a sentence. Amalgam transforms the logical form into a fully articulated tree structure from which an output sentence is read.To date, we have implemented Amalgam for both German and French, with English in the works.

Example of Amalgam input

Example of Amalgam structural output

References

Simon Corston-Oliver, Michael Gamon, Eric Ringger, and Robert Moore.
An overview of Amalgam: A machine-learned generation module.
In Proceedings of the International Natural Language Generation Conference, pages 33--40, New York, USA, 2002. Association for Computational Linguistics.
link Main reference

Micheal Gamon, Eric Ringger, Zhu Zhang, Robert Moore, and Simon Corston-Oliver.
Extraposition: A case study in German sentence realization.
In Proceedings of COLING 2002, pages 301--307. Association for Computational Linguistics, 2002.
link

Martine Smets, Michael Gamon, Simon Corston-Oliver, and Eric Ringger.
The adaptation of a machine-learned sentence realization system to French.
In Proceedings of the 10th conference of the European Chapter of the Association for Computational Linguistics, pages 323--330, Budapest, Hungary, 2003.
link


Information last updated: 16.11.2003 (dd.mm.yy)
Page last generated: 25-1-2009 21:01:38