Amalgam

From NLG Systems Wiki

Jump to: navigation, search
(CSV import)
(2 images uploaded)
Line 3: Line 3:
|workers=[[worker::Gamon]], [[worker::Ringger]], [[worker::Corston-Oliver]], [[worker::Moore]]
|workers=[[worker::Gamon]], [[worker::Ringger]], [[worker::Corston-Oliver]], [[worker::Moore]]
|started=2001
|started=2001
-
|ended=ongoing
+
|ended=
|languages=[[language::German]], [[language::French]], [[language::English]]
|languages=[[language::German]], [[language::French]], [[language::English]]
|name=Amalgam
|name=Amalgam
|description=Amalgam is a sentence realization component based on data-driven, 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.
|description=Amalgam is a sentence realization component based on data-driven, 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.
-
|details=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.<H3>Example of Amalgam input</H3><IMG SRC=../images/amalgam-input.jpg><H3>Example of Amalgam structural output</H3><IMG SRC=../images/amalgam-output.jpg>
+
|details=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.
 +
<H3>Example of Amalgam input</H3>
 +
[[Image:amalgam-input.jpg]]
 +
<H3>Example of Amalgam structural output</H3>
 +
[[Image:amalgam-output.jpg]]
|timestamp=2003/11/16
|timestamp=2003/11/16
|framework=machine learning
|framework=machine learning

Revision as of 20:32, 22 October 2009

Personal tools