Interactive Multilingual Generation

Coch, José; Chevreau, Karine

doi:10.1007/3-540-44686-9_26

Cited by 5 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sending feedback automatically to developers is already done in some MT systems, notably in Taiwan (EKS) and at PAHO [14], but should be much more used than it is. The idea of coedition is also not new: UPM in Madrid uses it to create UNL graphs, Y. Lepage at ATR and Tang E. K. at USM (Penang) have developed editors of string-tree correspondences, Watanabe at IBM-Japan has a very nice interface to edit from a text its underlying dependency structure, the MULTIMETEO system [8] is in effect a coedition system for weather forecasts and their underlying semantic structure, in 6 languages, and there is a project at Xerox working on multilingual generation and free text normalization in restricted domains and typologies (pharmaceutical notices). In our case, by contrast, coedition is to happen at the consumer side, not (like at UPM) at the producer side, and there is no specific domain or typology.…”

Section: Related Researchmentioning

confidence: 99%

Coedition to share text revision across languages and improve MT a posteriori

Boitet¹,

Tsai²

2002

COLING-02 on Machine Translation in Asia -

View full text Add to dashboard Cite

Coedition of a natural language text and its representation in some interlingual form seems the best and simplest way to share text revision across languages. For various reasons, UNL graphs are the best candidates in this context. We are developing a prototype where, in the simplest sharing scenario, naive users interact directly with the text in their language (L0), and indirectly with the associated graph. The modified graph is then sent to the UNL-L0 deconverter and the result shown. If is is satisfactory, the errors were probably due to the graph, not to the deconverter, and the graph is sent to deconverters in other languages. Versions in some other languages known by the user may be displayed, so that improvement sharing is visible and encouraging. As new versions are added with appropriate tags and attributes in the original multilingual document, nothing is ever lost, and cooperative working on a document is rendered feasible. On the internal side, liaisons are established between elements of the text and the graph by using broadly available resources such as a L0-English or better a L0-UNL dictionary, a morphosyntactic parser of L0, and a canonical graph2tree transformation. Establishing a "best" correspondence between the "UNL-tree+L0" and the "MS-L0 structure", a lattice, may be done using the dictionary and trying to align the tree and the selected trajectory with as few crossing liaisons as possible. A central goal of this research is to merge approaches from pivot MT, interactive MT, and multilingual text authoring.

show abstract

Section: Related Researchmentioning

confidence: 99%

Coedition to share text revision across languages and improve MT a posteriori

Boitet¹,

Tsai²

2002

COLING-02 on Machine Translation in Asia -

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Recently there has been a surge of interest in interactive natural language generation systems (Paris et al, 1995;Power and Scott, 1998;Coch and Chevreau, 2001); such systems rely on a capability of generating a natural language text from an abstract content representation, but -contrary to traditional NLG (Natural Language Generation) systems -this representation is only partially available at the beginning of the text production process; it is then gradually completed by a human author, typically using content-selection menus correlated with regions of the evolving generated text.. One such system, MDA (Multilingual Document Authoring) (citation omitted) is based on a formal specification -using a variant of Definite Clause Grammars (DCGs) (Pereira and Warren, 1980) -of what counts as a valid abstract content representation. The different derivation trees in the grammar correspond to texts with different contents, and at each step of the authoring process the user is asked to make interactive choices on how to expand the current partial derivation tree one step further.…”

Section: Introductionmentioning

confidence: 99%

Text authoring, knowledge acquisition and description logics

Dymetman

2002

Proceedings of the 19th International Conference on Computational Linguistics -

View full text Add to dashboard Cite

We present a principled approach to the problem of connecting a controlled document authoring system with a knowledge base. We start by describing closed-world authoring situations, in which the knowledge base is used for constraining the possible documents and orienting the user's selections. Then we move to open-world authoring situations in which, additionally, choices made during authoring are echoed back to the knowledge base. In this way the information implicitly encoded in a document becomes explicit in the knowledge base and can be re-exploited for simplifying the authoring of new documents. We show how a Datalog KB is sufficient for the closed-world situation, while a Description Logic KB is better-adapted to the more complex open-world situation. All along, we pay special attention to logically sound solutions and to decidability issues in the different processes.

show abstract

An Evaluation of UNL Usability for High Quality Multilingualization and Projections for a Future UNL++ Language

Boitet¹,

Boguslavskij²,

Cardeñosa³

2007

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

In a recent experiment on translating a web site into 4 languages, we have confirmed that using MT results in "translator's mode" can reduce the human work to produce good translations of complex sentences (25 w) at a rate of 25 mn/p with all-purpose commercial MT and at 20 mn/p with lab quality MT. A subexperiment has shown that using deconversions from quality-checked interlingual representations (UNL graphs) reduced the time spent down to 10 mn/p. Reducing the considerable time now needed for producing and checking UNL graphs is possible, which leads to very good usability prospects in situations involving many target languages and allowing for interactive disambiguation of source text or correction of interlingua. An analysis of improvable aspects in both interlingua design and resource building leads to a "roadmap" towards "UNL++" in the framework of the U++C consortium, including strong mutualization (collaborative volunteer work) and open-source aspects.

show abstract

Interactive Multilingual Generation

Cited by 5 publications

References 5 publications

Coedition to share text revision across languages and improve MT a posteriori

Coedition to share text revision across languages and improve MT a posteriori

Text authoring, knowledge acquisition and description logics

An Evaluation of UNL Usability for High Quality Multilingualization and Projections for a Future UNL++ Language

Contact Info

Product

Resources

About