UNL-French deconversion as transfer & generation from an interlingua with possible quality enhancement through offline human interaction

MT Summit VII Sept. 1999 UNL-French deconversion as transfer & generation from an interlingua with possible quality enhancement through offline human interaction Gilles SÉRASSET & Christian BOITET GETA, CLIPS, IMAG-campus, F-38041 Grenoble cedex 9, France Gilles.Serasset@imag.fr, Christian.Boitet@imag.fr Abstract We present the architecture of the UNL- French deconverter, which "generates" from the UNL interlingua by first "localizing" the UNL form for French, within UNL, and then applying slightly adapted but classical transfer and generation techniques, implemented in GETA's Ariane-G5 environment, supplemented by some UNL-specific tools. Online interaction can be used during deconversion to enhance output quality and is now used for development purposes. We show how interaction could be delayed and embedded in the postedition phase, which would then interact not directly with the output text, but indirectly with several components of the deconverter. Interacting online or offline can improve the quality not only of the utterance at hand, but also of the utterances processed later, as various preferences may be automatically changed to let the deconverter "learn". Keywords UNL, interlingua, deconversion, transfer, generation, interaction, active postedition Introduction In the UNL project of network-oriented multilingual communication, the strategy of "deconverting" an (interlingual) UNL hypergraph into a NL utterance is free. The UNL-French deconverter under development first performs a "localization" operation within the UNL format, and then classical transfer and generation steps, using the Ariane-G5 environment and some UNL-specific tools, in particular an interesting graph-to-tree converter. Traditionally, interaction in MT concerns analysis, rarely transfer, never generation. But, in this framework, interaction can be used and is actually used for development purposes during deconversion (transfer part) to improve output quality. We also show how it could be used after deconversion, in offline mode, making it possible to perform what could be called "active learning postedition", by indirectly modifying default automatic lexical selections and other choices, re-deconverting automatically, and keeping track of the modifications by changing preferences in several components to personalize the deconverter. 1 Overview of UNL-FR within the UNL project 1.1 UNL UNL is a project of multilingual personal networking communication initiated by the University of United Nations based in Tokyo. The pivot paradigm is used: the representation of an utterance in the UNL interlingua (UNL stands for "Universal Networking Language") is a hypergraph where normal nodes bear UWs ("Universal Words", or interlingual acceptions) with semantic attributes, and arcs bear semantic relations (deep cases, such as agt, obj, goal, etc.). Hypernodes group a subgraph defined by a set of connex arcs. A UW denotes a collection of interlingual acceptions (word senses), although we often loosely speak of "the" word sense denoted by an UW. Because English is known by all UNL developers, the syntax of a normal UW is: "<English word or compound> ( <list of restrictions>)", e.g. "look for(icl>action, agt>human, obj>thing)". Going from a text to the corresponding "UNL text" or interactively constructing a UNL text is called "enconversion", while producing a text from a sequence of UNL graphs is called "deconversion". This departure from the standard terms of analysis and …

Content truncated to 500 words