# US 2015/0106076 A1 · Efficient Online Domain Adaptation

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

- Number: US 2015/0106076 A1
- Document ID: US20150106076A1
- Status: Published application
- Kind: A1
- Application number: 14/051,175
- Filed: 2013-10-10
- Published: 2015-04-16
- Earliest claimed: 2013-10-10
- Assignees: Language Weaver, Inc.
- Inventors: Felix Hieber; Jonathan May
- Web page: https://patentgrep.com/patent/US20150106076A1

## CPC

- G06F 40/51: Translation evaluation
- G06F 40/45: Example-based machine translation; Alignment
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems and methods for efficient online domain adaptation are provided herein. Methods may include receiving a post-edited machine translated sentence pair, updating a machine translation model by adjusting translation weights for a translation memory and a language model while generating test machine translations of the machine translated sentence pair until one of the test machine translations approximately matches the post-edits for the machine translated sentence pair, and retranslating the remaining machine translation sentence pairs that have yet to be post-edited using the updated machine translation model.

## Claims

### Claim 1

A method of immediately updating a machine translation system with post-edits during translation of a document, using a machine translation system that comprises a processor and a memory for storing logic that is executed by the processor to perform the method, comprising:
receiving a post-edited machine translated sentence pair, wherein the post-edited machine translated sentence pair comprises a source sentence unit and a post-edited target sentence unit;
updating a machine translation model by:
performing an alignment of the post-edits of the machine translated sentence pair to generate phrases; and
adding the phrases to the machine translation model;
adapting a language model from the target sentence unit of the post-edits;
calculating translation statistics for the post-edits;
adjusting translation weights using the translation statistics while generating test machine translations of the machine translated sentence pair until one of the test machine translations approximately matches the post-edits for the machine translated sentence pair; and
retranslating remaining machine translation sentence pairs that have yet to be post-edited using the updated machine translation model and the adjusted translation weights.

### Claim 2 (depends on 1)

The method according to claim 1, further comprising:
receiving a document for translation from a source language into a target language; and
performing a machine translation of the document to generate a set of machine translated sentence pairs.

### Claim 3 (depends on 1)

The method according to claim 1, wherein updating a machine translation model further comprises tokenizing the post-edit of the machine translated sentence pair.

### Claim 4 (depends on 3)

The method according to claim 3, wherein updating the machine translation model further comprises updating a vocabulary of source sentence units with unknown source sentence units included in the post-edit of the machine translated sentence pair and updating a vocabulary of target sentence units with unknown target sentence units included in the post-edit of the machine translated sentence pair.

### Claim 5 (depends on 4)

The method according to claim 4, further comprising extracting fractional counts from the post-edit of the machine translated sentence pair and adding the extracted fractional counts to a fractional count table.

### Claim 6 (depends on 5)

The method according to claim 5, further comprising adjusting probability distributions for the source sentence unit of the post-edit of the machine translated sentence pair.

### Claim 7 (depends on 1)

The method according to claim 1, further comprising updating a phrase table with counts that define a number of occurrences of the phrases in the phrase table; and reordering feature values for phrases in the phrase table based upon the counts.

### Claim 8 (depends on 1)

The method according to claim 1, wherein weighting for the machine translation system are adjusted using discriminative ridge regression.

### Claim 9 (depends on 1)

The method according to claim 1, wherein adapting a language model includes executing an ngram-count of post-edited machine translated sentence pair to update a count file that comprises counts for input sentence pairs; and recompiling the language model using a smoothing algorithm.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the alignment includes both forward and reverse alignments of the post-edited machine translated sentence pair.

### Claim 11

A machine translation system that immediately incorporates post-edits into a machine translation model during translation of a document, the machine translation system comprising:
a processor; and
a memory for storing logic that is executed by the processor to:
receive a post-edit of a target sentence unit of a machine translated sentence pair of a set of machine translated sentence pairs, wherein a machine translated sentence pair comprises a source sentence unit and the target sentence unit;
receive a post-edited machine translated sentence pair, wherein the post-edited machine translated sentence pair comprises a source sentence unit and a post-edited target sentence unit;
update a machine translation model by:
performing an alignment of the post-edits of the machine translated sentence pair to generate phrases; and
adding the phrases to the machine translation model;
adapt a language model from the target sentence unit of the post-edits;
calculate translation statistics for the post-edits;
adjusting translation weights using the translation statistics while generating test machine translations of the machine translated sentence pair until one of the test machine translations approximately matches the post-edits for the machine translated sentence pair; and
retranslating remaining machine translation sentence pairs that have yet to be post-edited using the updated machine translation model.

### Claim 12 (depends on 11)

The machine translation system according to claim 11, wherein the processor further executes the logic to:
receive a document for translation from a source language into a target language; and
perform a machine translation of the document to generate the set machine translated sentence pairs.

### Claim 13 (depends on 11)

The machine translation system according to claim 11, wherein the machine translation system updates a machine translation model by further tokenizing the post-edit of the machine translated sentence pair.

### Claim 14 (depends on 13)

The machine translation system according to claim 13, wherein the machine translation system updates the machine translation model by updating a vocabulary of source sentence units with unknown source sentence units included in the post-edit of the machine translated sentence pair and updating a vocabulary of target sentence units with unknown target sentence units included in the post-edit of the machine translated sentence pair.

### Claim 15 (depends on 14)

The machine translation system according to claim 14, wherein the processor further executes the logic to extract fractional counts from the post-edit of the machine translated sentence pair and adding the extracted fractional counts to a fractional count table.

### Claim 16 (depends on 15)

The machine translation system according to claim 15, wherein the processor further executes the logic to adjust probability distributions for the source sentence unit of the post-edit of the machine translated sentence pair.

### Claim 17 (depends on 11)

The machine translation system according to claim 11, wherein the processor further executes the logic to update a phrase table with counts that define a number of occurrences of the phrases in the phrase table; and reorder feature values for phrases in the phrase table based upon the counts.

### Claim 18 (depends on 11)

The machine translation system according to claim 11, wherein weighting for the machine translation system is adjusted using discriminative ridge regression.

### Claim 19 (depends on 11)

The machine translation system according to claim 11, wherein the machine translation system is configured to adapt a language model by executing an ngram-count of the post-edited machine translated sentence pair to update a count file that comprises counts for input sentence pairs; and recompiling the language model using a smoothing algorithm.

### Claim 20 (depends on 11)

The machine translation system according to claim 11, wherein the machine translation system is configured to:
receive post-edits for a retranslated machine translation sentence pair;
re-updated the machine translation model;
calculate translation statistics for the post-edits of the retranslated machine translation sentence pair;
adjusting translation weights using the translation statistics while generating test machine translations of the retranslated machine translated sentence pair until one of the test machine translations approximately matches the post-edits for the retranslated machine translation sentence pair; and
retranslating any remaining retranslated machine translation sentence pairs that have yet to be post-edited using the updated machine translation model and the translation weights.
