Xerox Corporation

Conduent Business Services, LLC

Shachar Mirkin

Sriram Venkatapathy

Jean-Luc Meunier

Marc Dymetman

A system and method predict an optimal machine translation system for a first of a set of users. The method includes, for each of the users, providing a respective user profile which includes rankings for at least some machine translation systems from a set of machine translation systems. The user profile of the first user is updated, based on the user profiles of at least a subset of the other users. The updating includes generating at least one missing ranking. An optimal translation system for the first user from the set of machine translation systems is predicted, based on the updated user profile computed for the first user.

System and method for predicting an optimal machine translation system for a user based on an updated user profile

Agent utterances are generated for implementing dialog acts recommended by a dialog manager of a call center. To this end, a set of word lattices, each represented as a weighted finite state automaton (WFSA), is constructed from training dialogs between call center agents and second parties (e.g. customers). The word lattices are assigned conditional probabilities over dialog act type. For each dialog act received from the dialog manager, the word lattices are ranked by the conditional probabilities for the dialog act type. At least one word lattice is chosen from the ranking, and is instantiated to generate a recommended agent utterance for implementing the recommended dialog act. The word lattices may be constructed by clustering agent utterances of training dialogs using context features from preceding second party utterances and grammatical dependency link features between words within agent utterances. Path variations of the word lattices may define slots or paraphrases.

Learning generation templates from dialog transcripts

A method for updating a reordering model of a statistical machine translation system includes, at a first time, receiving new training data for retraining an existing statistical machine translation system, the new training data including at least one sentence pair, each pair including a source sentence in a source language and a target sentence in a target language. Phrase pairs are extracted from the new training data and used to generate a new reordering file. A reordering model of the existing statistical machine translation system is updated, based on the new reordering file. The reordering model includes a reordering table. At a second time after the first time, new training data is received. The extracting of phrase pairs, generating of the new reordering file and the updating the reordering model is reiterated, based on the new training data received at the second time.

System and method for incrementally updating a reordering model for a statistical machine translation system

An authoring method includes generating an authoring interface configured for assisting a user to author a text string in a source language for translation to a target string in a target language. Initial source text entered by the user is received through the authoring interface. Source phrases are selected that each include at least one token of the initial source text as a prefix and at least one other token as a suffix. The source phrase selection is based on a translatability score and optionally on fluency and semantic relatedness scores. A set of candidate phrases is proposed for display on the authoring interface, each of the candidate phases being the suffix of a respective one of the selected source phrases. The user may select one of the candidate phrases, which is appended to the source text following its corresponding prefix, or may enter alternative text. The process may be repeated until the user is satisfied with the source text and the SMT model can then be used for its translation.

Growing community of inventors

Meylan, France

Shachar Mirkin