US 2017/0371867 A1 · IDENTIFYING RISKY TRANSLATIONS

Abstract

Exemplary embodiments provide techniques for evaluating when words or phrases of a translation were generated with a low degree of confidence, and conveying this information when the translation is presented. For example, if a source language word is encountered in source material for translation, but the source language word was only encountered a few times (or not at all) in the training data used to train the translation system, then the resulting translation may be flagged as being of low confidence. Other situations, such as the generation of two equally-likely translations, or translation system model disagreement, may also indicate a questionable translation. When the translation is displayed, questionable words and phrases may be flagged, and possible alternative translations may be presented. If one of the alternatives is selected, this information may be used to update the translation system's models in order to improve translation quality in the future.

Claims20

Dependent claims

A method comprising:

receiving a request at a translation system to translate source material from a source language into a destination language;
translating the source material into destination material;
identifying one or more questionable words or phrases in the destination material that were translated with low confidence, wherein the translation system comprises a translation model to identify one or more hypotheses representing a translation of a source word or phrase into a destination word or phrase, and a language model that evaluates the one or more hypotheses in the context of the translated destination material, and identifying the questionable words or phrases comprises determining that the translation model identifies one of the hypotheses as being a most likely translation and determining that the language model identifies another of the hypotheses as being a most likely translation;
displaying the destination material;
and
visually distinguishing the questionable words or phrases in the destination material.

3 more elements

A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:

receive a request at a translation system to translate source material from a source language into a destination language;
translate the source material into destination material;
identify one or more questionable words or phrases in the destination material that were translated with low confidence, wherein the translation system comprises a translation model to identify one or more hypotheses representing a translation of a source word or phrase into a destination word or phrase, and a language model that evaluates the one or more hypotheses in the context of the translated destination material, and identifying the questionable words or phrases comprises determining that the translation model identifies one of the hypotheses as being a most likely translation and determining that the language model identifies another of the hypotheses as being a most likely translation;
display the destination material;
and
visually distinguish the questionable words or phrases in the destination material.

3 more elements

An apparatus comprising:

a network adapter configured to receive a request to translate source material from a source language into a destination language;
translation system logic, at least a portion of which is implemented in hardware, to implement a translation system, the translation system logic comprising logic to:
translate the source material into destination material, and
identify one or more questionable words or phrases in the destination material translated with low confidence, wherein the translation system comprises a translation model to identify one or more hypotheses representing a translation of a source word or phrase into a destination word or phrase, and a language model that evaluates the one or more hypotheses in the context of the translated destination material, and identifying the questionable words or phrases comprises determining that the translation model identifies one of the hypotheses as being a most likely translation and determining that the language model identifies another of the hypotheses as being a most likely translation;
and
a video adapter configured to:
display the destination material on a monitor, and
visually distinguish the questionable words or phrases in the destination material.

5 more elements

Dependencies are inferred from the claim text.

Identifying risky translations

Life of this patent

Identifying risky translations

Life of this patent

Abstract

Claims20