DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Specification
The disclosure is objected to because of the following informalities: page 14 paragraphs 6 and 7 refer to “an obtaining module 610” and “a distilling module 620” which should read “an obtaining module 601” and “a distilling module 602.” Further references to these elements also need correction, either by correcting the specification or the drawings.
Appropriate correction is required.
Claim Objections
Claim 11 objected to because of the following informalities: line 4 reads “determining first language sentence and the second language sentence” so it is unclear if both sentences or one of the sentences is selected. For example, line 4 should read “determining a first” or “determining the first” or “determining between the first”. Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-11 and 16-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Using the subject matter eligibility test from page 74621 of the Federal Register Notice titled “2014 Interim Guidance on Patent Subject Matter Eligibility,” a two-step process is performed. Under step 1, the claims are analyzed to determine if the claim is directed to a process, machine, article of manufacture, or composition of matter. In this case, claims 1-15 are directed to a method, which is a process; claims 16-18 are directed to a device, which is a machine or an article of manufacture; claim 19 is directed to a storage medium, which is a machine or an article of manufacture; claim 20 is directed to a computer program product, which does not fall under any of the categories. Step 2A (part 1 of the Mayo test), using the guidance from pages 50-57 of the Federal Register Vol. 84 No. 4 from Monday, January 7, 2019, requires applying a two-prong inquiry. In Prong One, examiners evaluate whether the claim recites a judicial exception, determining if the claim is directed to a law of nature, a natural phenomenon, or an abstract idea. In this case, claim 1 recites distilling a sentence, which is a mental process. In Prong Two, examiners evaluate whether the judicial exception is integrated into a practical application that imposes a meaningful limit on the judicial exception. In this case, additional limitations of processor, memory, storage, and llm are generic computing components, while obtaining data, and inputting and receiving output from a model could also be considered mere extrasolution activity.
Step 2B (part 2 of the Mayo test) requires analyzing the claims to determine if they recite additional elements that amount to significantly more than the judicial exception. In this case, the claims do not include additional elements that are sufficient to amount to significantly more than the abstract idea itself.
Regarding claims 1, 16, and 19, distilling a sentence is a mental process, which is an abstract idea. Additional limitations of processor, memory, storage, and llm are generic computing components, while obtaining data, and inputting and receiving output from a model could also be considered mere extrasolution activity, none of which integrate the abstract idea into a practical application or constitute significantly more.
Regarding claims 2 and 17, determining a target is a mental process, which is an abstract idea. Additional limitations of obtaining the sentence pair is mere extrasolution activity of receiving data from the LLM, which does not integrate the abstract idea into a practical application or constitute significantly more.
Regarding claims 3 and 18, generating a prompt word and the sentence pair are mental processes, which is an abstract idea. Additional limitations of obtaining a sentence as output from an LLM is mere extrasolution activity, and does not integrate the abstract idea into a practical application or constitute significantly more.
Regarding claim 4, determining the sentence is a mental process, which is an abstract idea. Additional limitations of inputting a prompt is mere extrasolution activity of receiving data from the LLM, which does not integrate the abstract idea into a practical application or constitute significantly more.
Regarding claims 5 and 9, generating a prompt is a mental process, which is an abstract idea without integration into a practical application and without significantly more.
Regarding claims 6-7, determining the action to be performed, choosing a sentence, and generating prompts are mental processes, which is an abstract idea without integration into a practical application and without significantly more.
Regarding claims 8 and 11, choosing a sentence is a mental process, which is an abstract idea without integration into a practical application and without significantly more.
Regarding claim 10, choosing a sentence and generating prompts are mental processes, which is an abstract idea without integration into a practical application and without significantly more.
The limitations of the claims, taken alone, do not amount to significantly more than the above-identified judicial exception (the abstract idea). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. Applicable case law cited in the Federal Register includes, but is not limited to: Alice Corp., 134 S. Ct. at 2355-56, Digitech Image Tech., LLC v. Electronics for Imaging, Inc., 758 F.3d 1344 (Fed. Cir. 2014), Benson, 409 U.S. at 63.
See "Preliminary Examination Instructions in view of the Supreme Court Decision in Alice Corporation Pty. Ltd. v. CLS Bank International, et al.," dated June 25, 2014, and the Federal Register notice titled "2014 Interim Guidance on Patent Subject Matter Eligibility" (79 FR 74618).
Claim 20 rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The instant claims are directed to a program for a computer. Computer programs do not fall into any statutory category of process, machine, manufacture, or composition of matter (In Re Nuijten, Fed. Cir. 2007). Rather, a program is a collection of executable instructions, in the absence of any physical structure or tangible material. Since the full scope of the claimed medium in light of the disclosure encompasses non-statutory subject matter, the claims as a whole would be non-statutory.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mehta et al. (US 2021/0073480 A1), hereinafter referred to as Mehta, in view of Yang et al. (Yang, W., & Nicolai, G. (2023). Neural machine translation data generation and augmentation using chatgpt. arXiv preprint arXiv:2307.05779.), hereinafter referred to as Yang.
Regarding claim 1, Mehta teaches:
An information processing method, comprising:
obtaining a first bilingual sentence pair, wherein the first bilingual sentence pair comprises a source language sentence and a target language sentence (para [0047-48], where source language sentences are translated to a target language using a translation system, and where ground truth translations also exist); and
obtaining a distilled second bilingual sentence pair by distilling a first language sentence in the first bilingual sentence pair , wherein the first language sentence is the source language sentence or the target language sentence (para [0041-42], where original translations are translated back to a source language, and where source sentences may be simplified in preprocessing).
Mehta does not teach:
based on a large language model (LLM)
Yang teaches:
based on a large language model (LLM) (Page 1 section 1 third paragraph, where chatGPT is used for translation)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Mehta by using the large language model of Yang (Yang page 1 section 1 third paragraph) as the translation model of Mehta (Mehta para [0032]), in order to provide extra data for lower-resourced language pairs (Yang page 1 section 1 third paragraph).
Regarding claim 2, Mehta in view of Yang teaches:
The method according to claim 1, wherein obtaining the distilled second bilingual sentence pair by distilling the first language sentence in the first bilingual sentence pair based on the LLM comprises:
determining a distillation target for the first bilingual sentence pair, wherein the distillation target is translation distillation or polishing distillation (Mehta para [0048], where both back translation and preprocessing are performed, interpreted as the translation and polishing distillations, respectively);
obtaining the distilled second bilingual sentence pair by distilling the first language sentence with the LLM according to the distillation target (Mehta para [0048], where both back translation and preprocessing are performed).
Regarding claim 3, Mehta in view of Yang teaches:
The method according to claim 2, wherein obtaining the distilled second bilingual sentence pair by distilling the first language sentence with the LLM according to the distillation target comprises:
generating a prompt word of the LLM according to the distillation target and the first bilingual sentence pair (Yang page 3 section 3.1.1, where prompts are provided to ChatGPT);
obtaining a third language sentence corresponding to the first language sentence by inputting the prompt word and at least one language sentence of the first bilingual sentence pairs into the LLM for distillation (Yang page 3 section 3.1.1, where the prompt and an input sentence are input to ChatGPT to produce an output sentence); and
generating the distilled second bilingual sentence pair based on a second language sentence in the first bilingual sentence pair and the third language sentence (Mehta para [0041], where original translations are translated back to a source language, constituting a new pair);
wherein, in a case that the first language sentence is the source language sentence, the second language sentence is the target language sentence; or in a case that the first language sentence is the target language sentence, the second language sentence is the source language sentence (Mehta para [0041], where original translations are translated back to a source language, constituting a new pair).
Regarding claim 4, Mehta in view of Yang teaches:
The method according to claim 3, wherein inputting the prompt word and at least one language sentence of the first bilingual sentence pairs into the LLM for distillation comprises:
determining the at least one language sentence to be input into the LLM from the first bilingual sentence pair according to the distillation target (Mehta para [0041], where original translations are translated back to a source language, constituting a new pair); and
inputting the prompt word and the at least one language sentence into the LLM for distillation (Yang page 3 section 3.1.1, where the prompt and an input sentence are input to ChatGPT to produce an output sentence).
Regarding claim 5, Mehta in view of Yang teaches:
The method according to claim 3, wherein generating the prompt word of the LLM according to the distillation target and the first bilingual sentence pair comprises:
in a case that the distillation target is the translation distillation, generating a first prompt word of the LLM according to the distillation target and the second language sentence in the first bilingual sentence pair (Yang page 3 section 3.1.1, where the prompt and an input sentence are input to ChatGPT to produce an output sentence).
Regarding claim 6, Mehta in view of Yang teaches:
The method according to claim 5, wherein generating the first prompt word of the LLM according to the distillation target and the second language sentence in the first bilingual sentence pair comprises:
in a case that the second language sentence is the source language sentence, determining the translation distillation to be a target language distillation (Mehta para [0041], [0047], where source sentences are translated into original translations and where original translations are translated back to a source language); and
setting the second language sentence as a language sentence to be translated, and generating the first prompt word for translating the language sentence to be translated into a target language (Mehta para [0041], [0047], where source sentences are translated into original translations and where original translations are translated back to a source language, and Yang page 3 section 3.1.1, where the prompt and an input sentence are input to ChatGPT to produce an output sentence).
Regarding claim 7, Mehta in view of Yang teaches:
The method according to claim 5, wherein generating the first prompt word of the LLM according to the distillation target and the second language sentence in the first bilingual sentence pair comprises:
in a case that the second language sentence is the target language sentence, determining the translation distillation to be a source language distillation (Mehta para [0041], [0047], where source sentences are translated into original translations and where original translations are translated back to a source language); and
setting the second language sentence as a language sentence to be translated, and generating the first prompt word for translating the language sentence to be translated into a source language (Mehta para [0041], [0047], where source sentences are translated into original translations and where original translations are translated back to a source language, and Yang page 3 section 3.1.1, where the prompt and an input sentence are input to ChatGPT to produce an output sentence).
Regarding claim 8, Mehta in view of Yang teaches:
The method according to claim 5, wherein determining the at least one language sentence to be input into the LLM from the first bilingual sentence pair according to the distillation target comprises:
determining the second language sentence from the first bilingual sentence pair as a language sentence to be input into the LLM (Mehta para [0041], [0047], where source sentences are translated into original translations and where original translations are translated back to a source language).
Regarding claim 9, Mehta in view of Yang teaches:
The method according to claim 3, wherein generating the prompt word of the LLM according to the distillation target and the first language sentence pair comprises:
in a case that the distillation target is the polishing distillation, generating a second prompt word of the LLM according to the distillation target and the first language sentence (Yang page 3 section 3.1.1, where the prompt and an input sentence are input to ChatGPT to produce an output sentence).
Regarding claim 10, Mehta in view of Yang teaches:
The method according to claim 9, wherein generating the second prompt word of the LLM according to the distillation target and the first language sentence comprises:
setting the first language sentence as a language sentence to be polished, and generating the second prompt word for polishing the language sentence to be polished (Mehta para [0053], where both source sentences and back translations are preprocessed or polished, and Yang page 3 section 3.1.1, where the prompt and an input sentence are input to ChatGPT to produce an output sentence) .
Regarding claim 11, Mehta in view of Yang teaches:
The method according to claim 9, wherein determining the at least one language sentence to be input into the LLM from the first bilingual sentence pair according to the distillation target comprises:
determining first language sentence and the second language sentence in the first bilingual sentence pair as language sentences to be input into the LLM (Mehta para [0053], where both source sentences and back translations are preprocessed or polished).
Regarding claim 12, Mehta in view of Yang teaches:
The method according to claim 1, after obtaining the distilled second bilingual sentence pair by distilling the first language sentence in the first bilingual sentence pair based on the LLM, further comprising:
generating an enhanced corpus library by combining the distilled second bilingual sentence pair and the first bilingual sentence pair, and training a student model based on the enhanced corpus library, wherein each corpus comprises the source language sentence and the target language sentence (Mehta para [0062], where the language pair parallel corpora is updated, and para [0053-54], where the automatic preprocessing model, interpreted as the student model, is trained based on the combined parallel corpus).
Regarding claim 13, Mehta in view of Yang teaches:
The method according to claim 12, wherein training the student model based on the enhanced corpus library comprises:
performing quality assessment on each corpus in the enhanced corpus library (Mehta Fig. 2 element 230, para [0052], where filtering module assigns a quality score to the translations);
obtaining a target enhanced corpus library by performing screening on the corpus in the enhanced corpus according to quality assessment information of each corpus (Mehta Fig. 2 element 230, para [0052], where filtering module removes translations that do not meet a threshold of quality); and
training the student model based on the target enhanced corpus library (Mehta para [0053-54], where the automatic preprocessing model is trained based on the combined parallel corpus).
Regarding claim 14, Mehta in view of Yang teaches:
The method according to claim 13, wherein obtaining the target enhanced corpus library by performing screening on the corpus in the enhanced corpus according to quality assessment information of the corpus comprises:
determining a corpus group corresponding to a same source language sentence (para [0052], where translations are compared to multiple reference texts, such as the source sentences or ground truth translations);
screening at least one target corpus corresponding to the same source language sentence from the corpus group according to the quality assessment information of each corpus in the corpus group (Mehta Fig. 2 element 230, para [0052], where filtering module removes translations that do not meet a threshold of quality).
Regarding claim 15, Mehta in view of Yang teaches:
The method according to claim 14, wherein screening at least one target corpus corresponding to the same source language sentence from the corpus group according to the quality assessment information of each corpus in the corpus group comprises:
comparing the quality assessment information of each corpus in the corpus group, and determining a corpus with a highest quality as the target corpus (Mehta Fig. 2 element 230, para [0052], where filtering module removes translations that do not meet a threshold of quality, where the threshold may be set to only allow the top quality corpus); or,
sorting corpora in the corpus group according to the quality assessment information of each corpus in the corpus group, and selecting a corpus ranked at the top as the target corpus (Mehta Fig. 2 element 230, para [0052], where filtering module removes translations that do not meet a threshold of quality, where the threshold may be set to only allow the top quality corpus); or
comparing the quality assessment information of each corpus in the corpus group with a preset quality assessment threshold, and selecting a corpus with quality assessment information greater than or equal to the preset quality assessment threshold as the target corpus (Mehta Fig. 2 element 230, para [0052], where filtering module removes translations that do not meet a threshold of quality).
Regarding claim 16, Mehta teaches:
An electronic device comprising:
at least one processor (Fig. 1 element 102, para [0023], where a processor is used); and
a memory communicatively coupled to the at least one processor (Fig. 1 element 116, para [0023], where memory is used); wherein,
the memory stores instructions executable by the at least one processor, when the instructions are executed by the at least one processor (Fig. 1 element 116, para [0029], where memory stores software programs to be executed by the processor), the at least one processor is configured to:
obtain a first bilingual sentence pair, wherein the first bilingual sentence pair comprises a source language sentence and a target language sentence (para [0047-48], where source language sentences are translated to a target language using a translation system, and where ground truth translations also exist); and
obtain a distilled second bilingual sentence pair by distilling a first language sentence in the first bilingual sentence pair, wherein the first language sentence is the source language sentence or the target language sentence (para [0041-42], where original translations are translated back to a source language, and where source sentences may be simplified in preprocessing).
Mehta does not teach:
based on a large language model (LLM)
Yang teaches:
based on a large language model (LLM) (Page 1 section 1 third paragraph, where chatGPT is used for translation)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Mehta by using the large language model of Yang (Yang page 1 section 1 third paragraph) as the translation model of Mehta (Mehta para [0032]), in order to provide extra data for lower-resourced language pairs (Yang page 1 section 1 third paragraph).
Regarding claim 17, Mehta in view of Yang teaches:
The electronic device according to claim 16, wherein the at least one processor is configured to:
determine a distillation target for the first bilingual sentence pair, wherein the distillation target is translation distillation or polishing distillation (Mehta para [0048], where both back translation and preprocessing are performed, interpreted as the translation and polishing distillations, respectively);
obtain the distilled second bilingual sentence pair by distilling the first language sentence with the LLM according to the distillation target (Mehta para [0048], where both back translation and preprocessing are performed).
Regarding claim 18, Mehta in view of Yang teaches:
The electronic device according to claim 17, wherein the at least one processor is configured to:
generate a prompt word of the LLM according to the distillation target and the first bilingual sentence pair (Yang page 3 section 3.1.1, where prompts are provided to ChatGPT);
obtain a third language sentence corresponding to the first language sentence by inputting the prompt word and at least one language sentence of the first bilingual sentence pairs into the LLM for distillation (Yang page 3 section 3.1.1, where the prompt and an input sentence are input to ChatGPT to produce an output sentence); and
generate the distilled second bilingual sentence pair based on a second language sentence in the first bilingual sentence pair and the third language sentence (Mehta para [0041], where original translations are translated back to a source language, constituting a new pair);
wherein, in a case that the first language sentence is the source language sentence, the second language sentence is the target language sentence; or in a case that the first language sentence is the target language sentence, the second language sentence is the source language sentence (Mehta para [0041], where original translations are translated back to a source language, constituting a new pair).
Regarding claim 19, Mehta teaches:
A non-transitory computer-readable storage medium having computer instructions stored thereon (Fig. 1 element 114, para [0030], where storage stores software programs to be executed by the processor), wherein the computer instructions are configured to enable a computer to implement the method comprising:
obtaining a first bilingual sentence pair, wherein the first bilingual sentence pair comprises a source language sentence and a target language sentence (para [0047-48], where source language sentences are translated to a target language using a translation system, and where ground truth translations also exist); and
obtaining a distilled second bilingual sentence pair by distilling a first language sentence in the first bilingual sentence pair, wherein the first language sentence is the source language sentence or the target language sentence (para [0041-42], where original translations are translated back to a source language, and where source sentences may be simplified in preprocessing).
Mehta does not teach:
based on a large language model (LLM)
Yang teaches:
based on a large language model (LLM) (Page 1 section 1 third paragraph, where chatGPT is used for translation)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Mehta by using the large language model of Yang (Yang page 1 section 1 third paragraph) as the translation model of Mehta (Mehta para [0032]), in order to provide extra data for lower-resourced language pairs (Yang page 1 section 1 third paragraph).
Regarding claim 20, Mehta in view of Yang teaches:
A computer program product comprising computer programs, wherein when the computer programs are executed by a processor, steps of the method according to claim 1 are implemented (Mehta Fig. 1 element 114, para [0030], where storage stores software programs to be executed by the processor).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US 2024/0054767 A1 Fig. 1, para [0070-71], 0104-106] teaches augmenting training data by using back translation.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRYAN S BLANKENAGEL whose telephone number is (571)270-0685. The examiner can normally be reached 8:00am-5:30pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Richemond Dorvil can be reached at 571-272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/BRYAN S BLANKENAGEL/Primary Examiner, Art Unit 2658
Prosecution Insights