# US 2012/0253784 A1 · Language translation based on nearby devices

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2012/0253784 A1
- Document ID: US20120253784A1
- Status: Published application
- Kind: A1
- Application number: 13/077,110
- Filed: 2011-03-31
- Published: 2012-10-04
- Earliest claimed: 2011-03-31
- Assignees: International Business Machines Corporation
- Inventors: Sameer Maskey; Dimitri Kanevasky; Tara N. Sainath; Bhuvana Ramabhadran
- Web page: https://patentgrep.com/patent/US20120253784A1

## CPC

- G06F 40/58: Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A device, method, and computer program for performing language translation. An example embodiment may include a communications module configured to receive device data from a nearby device. A constraint module is configured to limit a translation domain of the language translation based on the device data. Language translation is performed within the limited translation domain.

## Claims

### Claim 1

A translation device for performing language translation, the translation device comprising:
a communications module to receive device data from a nearby device external to the translation device; and
a constraint module to limit a translation domain of the language translation based on the device data.

### Claim 2 (depends on 1)

The translation device of claim 1, further comprising:
wherein the device data includes data for identifying the purpose of the nearby device; and
wherein the constraint module is configured to limit the translation domain of the language translation based on the identified purpose of the nearby device.

### Claim 3 (depends on 1)

The translation device of claim 1, wherein the communication module includes at least one interface to receive the device data through at least one of bluetooth, wifi, and near field communications.

### Claim 4 (depends on 1)

The translation device of claim 1, wherein the constraint module limits the translation domain by a restriction on at least one of vocabulary, search space, grammar, and language model used for the language translation.

### Claim 5 (depends on 1)

The translation device of claim 1, further comprising:
wherein the device data includes measurement data from the nearby device; and
wherein the constraint module is configured to limit the translation domain of the language translation based on the measurement data.

### Claim 6 (depends on 1)

The translation device of claim 1, further comprising a translation module to receive at least one of the translation domain based on the device data and vocabulary words based on the device data.

### Claim 7 (depends on 1)

The translation device of claim 1, further comprising a speech-to-speech translation module to recognize spoken words and audibly output the language translation of the spoken words.

### Claim 8

A method for improving language translation accuracy, the method comprising:
receiving device data from a nearby device; and
limiting a translation domain of the language translation based on the device data.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
wherein the device data includes data for identifying the purpose of the nearby device;
identifying the purpose of the nearby device; and
limiting the translation domain of the language translation based on the purpose of the nearby device.

### Claim 10 (depends on 8)

The method of claim 8, wherein the device data is received through at least one of bluetooth, wifi, and near field communications.

### Claim 11 (depends on 8)

The method of claim 8, wherein limiting the translation domain comprises limiting by a restriction on at least one of vocabulary, search space, grammar, and language model used for language translation.

### Claim 12 (depends on 8)

The method of claim 8, further comprising:
wherein the device data includes measurement data from the nearby device; and
limiting the translation domain of the language translation based on the measurement data.

### Claim 13 (depends on 8)

The method of claim 8, further comprising receiving at least one of the translation domain based on the device data and vocabulary words based on the device data.

### Claim 14 (depends on 8)

The method of claim 8, further comprising recognizing spoken words and audibly outputting the language translation of the spoken words.

### Claim 15

A computer program product for performing language translation comprising:
a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code configured to:
receive device data from a nearby device; and
limit a translation domain of the language translation based on the device data.

### Claim 16 (depends on 15)

The computer program product of claim 15, further comprising:
wherein the device data includes data for identifying the purpose of the nearby device; and
wherein the computer readable program code is further configured to limit the translation domain of the language translation based on the purpose of the nearby device.

### Claim 17 (depends on 15)

The computer program product of claim 15, wherein the translation domain is limited by a restriction on at least one of vocabulary, search space, grammar, and language model used for language translation.

### Claim 18 (depends on 15)

The computer program product of claim 15, further comprising:
wherein the device data includes measurement data from the nearby device; and
wherein the computer readable program code is further configured to limit the translation domain of the language translation based on the measurement data from the nearby device.

### Claim 19 (depends on 15)

The computer program product of claim 15, wherein the computer readable program code is further configured to receive at least one of the translation domain based on the device data and vocabulary words based on the device data.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein the computer readable program code is further configured to recognize spoken words and audibly output the language translation of the spoken words.
