Patents by Inventor Radu Soricut
Radu Soricut has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10984429Abstract: A prediction of the cost associated with translating textual content in a source language can be determined. A first quantity estimation of first textual content may be determined. The first textual content is to be translated via human translation. A second quantity estimation of second textual content may also be determined. The second textual content is to be translated via machine translation. An indication of a target language is obtained, wherein the source language and the target language form a language pair. The prediction of the cost associated with translating the first textual content and the second textual content from the source language to the target language is then determined. The prediction is based at least in part on the first quantity estimation, the second quantity estimation, and the language pair.Type: GrantFiled: June 18, 2019Date of Patent: April 20, 2021Assignee: SDL Inc.Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
-
Publication number: 20190303952Abstract: A prediction of the cost associated with translating textual content in a source language can be determined. A first quantity estimation of first textual content may be determined. The first textual content is to be translated via human translation. A second quantity estimation of second textual content may also be determined. The second textual content is to be translated via machine translation. An indication of a target language is obtained, wherein the source language and the target language form a language pair. The prediction of the cost associated with translating the first textual content and the second textual content from the source language to the target language is then determined. The prediction is based at least in part on the first quantity estimation, the second quantity estimation, and the language pair.Type: ApplicationFiled: June 18, 2019Publication date: October 3, 2019Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
-
Patent number: 10417646Abstract: A prediction of the cost associated with translating textual content in a source language can be determined. A first quantity estimation of first textual content may be determined. The first textual content is to be translated via human translation. A second quantity estimation of second textual content may also be determined. The second textual content is to be translated via machine translation. An indication of a target language is obtained, wherein the source language and the target language form a language pair. The prediction of the cost associated with translating the first textual content and the second textual content from the source language to the target language is then determined. The prediction is based at least in part on the first quantity estimation, the second quantity estimation, and the language pair.Type: GrantFiled: March 9, 2010Date of Patent: September 17, 2019Assignee: SDL Inc.Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
-
Patent number: 8990064Abstract: A document containing text in a source language may be translated into a target language based on content associated with that document, in conjunction with the present technology. An indication to perform an optimal translation of a document into a target language may be received via a user interface. The document may then be accessed by a computing device. The optimal translation is executed by a preferred translation engine of a plurality of available translation engines. The preferred translation engine is the most likely to produce the most accurate translation of the document among the plurality of available translation engines. Additionally, the preferred translation engine may be identified based on content associated with the document. The document is translated into the target language using the preferred translation engine to obtain a translated document, which may then be outputted by a computing device.Type: GrantFiled: July 28, 2009Date of Patent: March 24, 2015Assignee: Language Weaver, Inc.Inventors: Daniel Marcu, Radu Soricut, Narayanaswamy Viswanathan
-
Patent number: 8886517Abstract: Systems and methods for generating trust scores for translations are described herein. According to some embodiments, methods for generating a trust score for a translation may include establishing a trust score for at least a portion of a first translation of a source text translated by a trusted translation system, the trust score representing an accuracy level for the first translation, comparing the first translation of the source text generated by the trusted translation system to a second translation of the source text generated by an untrusted translation system, and determining a trust score for the second translation based upon the comparison.Type: GrantFiled: June 29, 2012Date of Patent: November 11, 2014Assignee: Language Weaver, Inc.Inventors: Radu Soricut, Daniel Marcu
-
Patent number: 8676563Abstract: Customers having a translation project to select a translation method from a variety of options, ranging from a completely human translation to a completely automated translation. For human translations, translation job information may be communicated through one or more network service modules which execute within a network service application, such as a web-based networking application. A network service module may register a user having an account with the network service application as a translator and communicate translation jobs to the user. One or more users who express interest in performing the translation are selected to perform a translation job, each job comprising at least a portion of the translation project. After a user provides a translation for the translation job, the translation is analyzed to generate a trust level prediction for the translation. A user translation profile may be updated after each translation to reflect the user's performance.Type: GrantFiled: June 21, 2010Date of Patent: March 18, 2014Assignee: Language Weaver, Inc.Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
-
Publication number: 20140006003Abstract: Systems and methods for generating trust scores for translations are described herein. According to some embodiments, methods for generating a trust score for a translation may include establishing a trust score for at least a portion of a first translation of a source text translated by a trusted translation system, the trust score representing an accuracy level for the first translation, comparing the first translation of the source text generated by the trusted translation system to a second translation of the source text generated by an untrusted translation system, and determining a trust score for the second translation based upon the comparison.Type: ApplicationFiled: June 29, 2012Publication date: January 2, 2014Inventors: Radu Soricut, Daniel Marcu
-
Patent number: 8380486Abstract: A quality-prediction engine predicts a trust level associated with translational accuracy of a machine-generated translation. Training a quality-prediction may include translating a document in a source language to a target language by executing a machine-translation engine stored in memory to obtain a machine-generated translation. The training may further include comparing the machine-generated translation with a human-generated translation of the document. The human-generated translation is in the target language. Additionally, the training may include generating a mapping between features of the machine-generated translation and features of the human-generated translation based on the comparison.Type: GrantFiled: October 1, 2009Date of Patent: February 19, 2013Assignee: Language Weaver, Inc.Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
-
Publication number: 20110225104Abstract: A prediction of the cost associated with translating textual content in a source language can be determined. A first quantity estimation of first textual content may be determined. The first textual content is to be translated via human translation. A second quantity estimation of second textual content may also be determined. The second textual content is to be translated via machine translation. An indication of a target language is obtained, wherein the source language and the target language form a language pair. The prediction of the cost associated with translating the first textual content and the second textual content from the source language to the target language is then determined. The prediction is based at least in part on the first quantity estimation, the second quantity estimation, and the language pair.Type: ApplicationFiled: March 9, 2010Publication date: September 15, 2011Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marca
-
Patent number: 7974833Abstract: A special notation that extends the notion of IDL by weighted operators. The Weighted IDL or WIDL can be intersected with a language model, for example an n-gram language model or a syntax-based language model. The intersection is carried out by converting the IDL to a graph, and unfolding the graph in a way which maximizes its compactness.Type: GrantFiled: June 21, 2005Date of Patent: July 5, 2011Assignee: Language Weaver, Inc.Inventors: Radu Soricut, Daniel Marcu
-
Publication number: 20110082683Abstract: A quality-prediction engine predicts a trust level associated with translational accuracy of a machine-generated translation. Training a quality-prediction may include translating a document in a source language to a target language by executing a machine-translation engine stored in memory to obtain a machine-generated translation. The training may further include comparing the machine-generated translation with a human-generated translation of the document. The human-generated translation is in the target language. Additionally, the training may include generating a mapping between features of the machine-generated translation and features of the human-generated translation based on the comparison. The mapping may allow determination of trust levels associated with translational accuracy of future machine-generated translations that lack corresponding human-generated translations.Type: ApplicationFiled: October 1, 2009Publication date: April 7, 2011Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
-
Publication number: 20110082684Abstract: Customers having a translation project to select a translation method from a variety of options, ranging from a completely human translation to a completely automated translation. For human translations, translation job information may be communicated through one or more network service modules which execute within a network service application, such as a web-based networking application. A network service module may register a user having an account with the network service application as a translator and communicate translation jobs to the user. One or more users who express interest in performing the translation are selected to perform a translation job, each job comprising at least a portion of the translation project. After a user provides a translation for the translation job, the translation is analyzed to generate a trust level prediction for the translation. A user translation profile may be updated after each translation to reflect the user's performance.Type: ApplicationFiled: June 21, 2010Publication date: April 7, 2011Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
-
Publication number: 20110029300Abstract: A document containing text in a source language may be translated into a target language based on content associated with that document, in conjunction with the present technology. An indication to perform an optimal translation of a document into a target language may be received via a user interface. The document may then be accessed by a computing device. The optimal translation is executed by a preferred translation engine of a plurality of available translation engines. The preferred translation engine is the most likely to produce the most accurate translation of the document among the plurality of available translation engines. Additionally, the preferred translation engine may be identified based on content associated with the document. The document is translated into the target language using the preferred translation engine to obtain a translated document, which may then be outputted by a computing device.Type: ApplicationFiled: July 28, 2009Publication date: February 3, 2011Inventors: Daniel Marcu, Radu Soricut, Narayanaswamy Viswanathan
-
Patent number: 7340388Abstract: A statistical machine translation (MT) system may use a large monolingual corpus to improve the accuracy of translated phrases/sentences. The MT system may produce a alternative translations and use the large monolingual corpus to (re)rank the alternative translations.Type: GrantFiled: March 26, 2003Date of Patent: March 4, 2008Assignee: University of Southern CaliforniaInventors: Radu Soricut, Daniel Marcu, Kevin Knight
-
Publication number: 20030233222Abstract: A statistical machine translation (MT) system may use a large monolingual corpus to improve the accuracy of translated phrases/sentences. The MT system may produce a alternative translations and use the large monolingual corpus to (re)rank the alternative translations.Type: ApplicationFiled: March 26, 2003Publication date: December 18, 2003Inventors: Radu Soricut, Daniel Marcu, Kevin Knight