Prosecution Insights
Last updated: April 19, 2026
Application No. 18/595,675

APPARATUS AND METHOD FOR DEEP LEARNING-BASED COREFERENCE RESOLUTION USING DEPENDENCY RELATION

Non-Final OA §101§103
Filed
Mar 05, 2024
Examiner
MCCORD, PAUL C
Art Unit
2692
Tech Center
2600 — Communications
Assignee
ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
OA Round
1 (Non-Final)
69%
Grant Probability
Favorable
1-2
OA Rounds
3y 5m
To Grant
96%
With Interview

Examiner Intelligence

Grants 69% — above average
69%
Career Allow Rate
393 granted / 569 resolved
+7.1% vs TC avg
Strong +27% interview lift
Without
With
+26.6%
Interview Lift
resolved cases with interview
Typical timeline
3y 5m
Avg Prosecution
41 currently pending
Career history
610
Total Applications
across all art units

Statute-Specific Performance

§101
10.5%
-29.5% vs TC avg
§103
54.0%
+14.0% vs TC avg
§102
6.8%
-33.2% vs TC avg
§112
20.9%
-19.1% vs TC avg
Black line = Tech Center average estimate • Based on career data from 569 resolved cases

Office Action

§101 §103
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 . DETAILED ACTION 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. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . Claims 1-20 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. Claim(s) 1, 10, 17 is/are directed to a system, method, etc. for generating a coreference resolution model. The claims rely on well understood, routine, and conventional structures such as a processor, memory, data structure, etc. to instruct the system along methods by which input data in the form of plural documents is analyzed sentence wise to determine dependency relations among the language elements within the document, sentences, etc. and to thereby generate an embedding vector for a neural network trained on data determined from the documents. The claims are considered a manner by which data resolves more data, in this case a plural documents, elements therein or determined therefrom based on analysis are used to resolve data in the form of neural network embedding(s) and the neural network is used to generate subsequent data in the form of a model; the claims are also considered a stand in for human behavior as the claims steps are substantially similar to the manner in which a human being might parse sentences to resolve relationships therein. As such the claims cannot be considered to integrate the judicial exceptions of an abstract idea and are considered data per se or programs per se nor do the claims integrate the judicial exception of human activity and/or mental processes such as operations performed in the human mind, human activity, human behavior; etc. as the claims do not include substantially more than the performance of such exceptions upon a computer claimed at a high level of generality and based on models intended to mimic or replicate human cognitive processes. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception as they are claimed at a high level of generality and essentially comprise a computer. Dependent claims 2-9, 11-15, 18-20 do not remedy and are similarly rejected as the claims further address additional subject matter which may be seen as the generation of data from data; a stand in for human behavior, and/or human application of agency in concert with assistive instructions, mathematic concepts, AI models, etc. 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 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 of this title, 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. The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. Claims 1-20 rejected under 35 U.S.C. 103 as being unpatentable over Chen: 20240037339 hereinafter Che further in view of Fei: 20210240929. Regarding claim 1 Che teaches: An apparatus for learning-based coreference resolution (Che: Abstract: a dependency graph maps entity relations), comprising: a data generation module that extracts one or more natural language sentences from a natural language paragraph (Che: Abstract; ¶ 15, 45, 48, 49: for each input document unstructured natural-language sentences are provided as input to a machine-learning model to generate contextual word embeddings by building a coreference relation graph based on all the words of received sentences in an input document and determining a sentence level dependency graph by parsing the document sentence wise) and performs dependency parsing on the natural language sentences to generate dependency relation data of the natural language sentences (Che: ¶ 2, 34, 37: sentence level dependency relations or parse sentences operable to generate a dependency tree); an embedding module that generates an integrated embedding vector for the natural language paragraph based on the natural language sentence and the dependency relation data (Che: Abstract; ¶ 45-49, 65; Fig 5: system generates a graphs based on sentences, words, etc. of input documents, generates a graph of dependencies a graph of coreferences in concert with determined embeddings and provides same to a graph neural network wherein the embedding layer of the system receives a matrix of word vectors, values etc. as input and at least the embedding and encoding layers of the system output vectors); and a coreference resolution module that trains a graph learning neural network based on the integrated embedding vector (Che: Abstract; ¶ 45-49, 65; Fig 5: system determines global coreference relations and local dependency relation to generate embedding vectors and thereby train a fusion layer of the graph neural network) and a first coreference mention preset (Che: Abstract; ¶ 54, 63; Fig 5: such as a golden label or other labelled data for training) for the natural language paragraph to generate a named entity resolution model (Che: Abstract; ¶ 15, etc.; Fig 5, etc.). Che does not explicitly teach the generate a coreference resolution model such as by using deep learning-based coreference resolution in concert with the employ of a training data generation module. In a related field of endeavor Fei teaches a deep reinforcement learning system and method (Fei: Title; ¶ 27, 29) for coreference resolution (Fei: ¶ 29, 30) such as by iteratively generating training data such as co-reference graphs for input document used over a plurality of epochs (Fei: ¶ 29, 30; Fig 1, 2; claims 2, 16) and a first coreference mention preset (Fei: ¶ 5, 6, etc.; claim 1, 2: such as the recited ground truth coreference information for a document and operable for training a coreference resolution model) for the natural language paragraph to generate, train, improve, etc. a coreference resolution model (Fei: Abstract; ¶ 5; claim 1). It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to utilize integrated embeddings and annotated labelled mentions such as those discussed by Che to train the Pei coreference model for at least the purpose of deterring mentions and performing coreference recognition based thereon; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 2 Che in view of Fei teaches or suggests: The apparatus of claim 1, wherein the training data generation module includes: a natural language sentence extraction unit that extracts the natural language sentence from the natural language paragraph (Che: ¶ 47-50; Fig 5: system performs sentence extraction from documents reliably consisting of paragraphs, sections, etc.); a dependency parsing unit that performs the dependency parsing on the natural language sentence (Che: ¶ 47-50; Fig 5: system parses sentences to determine dependency arcs); and a dependency relation extraction unit that generates the dependency relation data by extracting the dependency relation between words included in the natural language sentence based on a dependency parsing result of the dependency parsing unit (Che: ¶ 47-50; Fig 5: system parses sentences to determine dependency arcs thereby generating token-wise or word-wise graphs of dependency relations). The claim is considered obvious over Che as modified by Fei as addressed in the base claim as it would have been obvious to apply the further teaching of Che and/or Fei to the modified device of Che and Fei; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 3 Che in view of Fei teaches or suggests: The apparatus of claim 1, wherein the embedding module includes: a natural language embedding unit that embeds the words included in the natural language sentence to generate a natural language embedding vector (Che: ¶ 45-50: system uses bert to determine embedding layer data including embeddings, word vector data input thereto, vectors output thereby to an embedding layer which subsequently outputs vectors to an encoding layer for a GNN operative upon and outputting matrices of vectors; adjacency matrices, etc.); (Fei: ¶ 51-62; Fig 4, 6: embeddings of spans input to coreference module to generate conference scores ; a dependency relation embedding unit that embeds the dependency relation data to generate a dependency relation embedding vector that integrates the natural language embedding vector and the dependency relation embedding vector to generate the integrated embedding vector (Che: 45-50, 53, 54; Fig 5; and an integrated embedding unit provides vectorized data to the GNN which propagates the information for combining with the vectorized embedding and encoding outputs to generate output recognition data); (Fei: ¶ 51-62; Fig 4, 6). It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to utilize the dependency mention representations of Che as vectorized inputs representing span embeddings to the Fei taught coreference module for at least the purpose of determining coreference scores thereby; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 4 Che in view of Fei teaches or suggests: The apparatus of claim 1, wherein the coreference resolution module includes: a deep learning neural network calculation unit that inputs the integrated embedding vector (see claim 1 supra: Che: Abstract, Fig 5, etc. system generates an integrated embedding vector as input to a neural network) to the deep learning neural network (Fei: ¶ 5, 6, 23, 28, 31, 41; Fig 1, 4; Claim 4: a policy network inputs documents, spans thereof by generating character, word, etc. embeddings from the document and utilizes same as input to the deep learning framework to calculate scores, probabilities, etc. based thereon and with respect to the input embedding vector of such a network such as to detect mentions); a mention detection unit that detects a mention in the natural language paragraph based on a calculation result of the deep learning neural network (Fei: ¶ 5, 6, 31: policy network generates first, second, etc. coreference mentions based on a set of antecedent mentions, scores thereof which are calculated by the deep learning system); a coreference recognition unit that generates a second coreference mention of the natural language paragraph based on a result of the mention detection (Fei: ¶ 5, 6, 31: policy network generates first, second, etc. coreference mentions based on a set of antecedent mentions, scores thereof which are calculated by the deep learning system); and a training unit that trains the deep learning neural network based on the first coreference mention and the second coreference mention to generate the coreference resolution model (Fei: ¶ 31, 58; claim 2: a ground truth first coreference mention integrated with coreference mentions and antecedents thereof to thereby compute, resolve, etc. a reward, gradient based thereon and to update, train, etc. the policy network thereby). The claim is considered obvious over Che as modified by Fei as addressed in the base claim as it would have been obvious to apply the further teaching of Che and/or Fei to the modified device of Che and Fei; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 5 Che in view of Fei teaches or suggests: The apparatus of claim 1, wherein the deep learning neural network is a neural network based on a long short-term memory (LSTM) (Che: ¶ 38, 40; Fig 5: GNN comprises, based on, etc. LSTM layer); (Fei: ¶ 6, 42, etc.: neural system integrated with LSTM layer). The claim is considered obvious over Che as modified by Fei as addressed in the base claim as it would have been obvious to apply the further teaching of Che and/or Fei to the modified device of Che and Fei; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 6 Che in view of Fei teaches or suggests: The apparatus of claim 1, wherein the deep learning neural network is a neural network based on bidirectional encoder representations from transformers (BERT) (Che: ¶ 45, 46, etc.: system based on BERT). The claim is considered obvious over Che as modified by Fei as addressed in the base claim as it would have been obvious to apply the further teaching of Che and/or Fei to the modified device of Che and Fei; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 7 Che in view of Fei teaches or suggests: The apparatus of claim 4, wherein the training unit calculates a coreference recognition error between the first coreference mention and the second coreference mention, and trains the deep learning neural network based on the error (Fei: ¶ 31, 58; claim 2:a ground truth first coreference mention integrated with coreference mentions and antecedents thereof to thereby compute, resolve, etc. a reward, gradient based thereon and to update, train, etc. the policy network thereby, such as with respect to optimizing epochs, error level, iterations, etc.). The claim is considered obvious over Che as modified by Fei as addressed in the base claim as it would have been obvious to apply the further teaching of Che and/or Fei to the modified device of Che and Fei; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 8 Che in view of Fei teaches or suggests: The apparatus of claim 4, wherein the training unit calculates a coreference recognition error between the first coreference mention and the second coreference mention, and trains a mention detection parameter of the mention detection unit based on the error (Fei: ¶ 31, 58; claim 2:a ground truth first coreference mention integrated with coreference mentions and antecedents thereof to thereby compute, resolve, etc. a reward, gradient based thereon and to update, train, etc. the policy network thereby, such as with respect to optimizing epochs, error level, iterations, etc.). The claim is considered obvious over Che as modified by Fei as addressed in the base claim as it would have been obvious to apply the further teaching of Che and/or Fei to the modified device of Che and Fei; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 9 Che in view of Fei teaches or suggests: The apparatus of claim 4, wherein the training unit calculates a coreference recognition error between the first coreference mention and the second coreference mention, and trains a coreference recognition parameter of the coreference recognition unit based on the error (Fei: ¶ 31, 58; claim 2:a ground truth first coreference mention integrated with coreference mentions and antecedents thereof to thereby compute, resolve, etc. a reward, gradient based thereon and to update, train, etc. the policy network thereby, such as with respect to optimizing epochs, error level, iterations, etc.). The claim is considered obvious over Che as modified by Fei as addressed in the base claim as it would have been obvious to apply the further teaching of Che and/or Fei to the modified device of Che and Fei; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 10 Che teaches: An apparatus for learning-based coreference resolution (Che: Abstract: a dependency graph maps entity relations), comprising: a first data storage that stores a natural language paragraph and a first coreference mention preset for the natural language paragraph (Che: ¶ 23, 24, 27, 45, 46, 54, 63; Fig 2, 3, 5: first storage devices 16 provide data to dialog computer; dialog computer processes input documents and stores same in second memory 32, 34 and/or in cache memory associated with processor 30; dialog computer stores received text and encodes same for processing and buffering by a graph learning architecture as depicted in figure 5; golden labels and structured, labelled, etc. data are additionally stored and retrieved for training of the figure 5 graph learning architecture); a second data storage (id.: the memory of the dialog computer); a data generation module that extracts the natural language paragraph (Che: Abstract; ¶ 15, 45, 48, 49: for each input document unstructured natural-language sentences are provided as input to a machine-learning model to generate contextual word embeddings by building a coreference relation graph based on all the words of received sentences in an input document and determining a sentence level dependency graph by parsing the document sentence wise); and the first coreference mention from the first data storage (Che: ¶ 54, 63, etc.: such as the stored labelled data or golden data), extracts one or more natural language sentences from the natural language paragraph Che: Abstract; ¶ 15, 45, 48, 49), performs dependency parsing on the natural language sentence to generate dependency relation data of the natural language sentence (Che: ¶ 2, 34, 37: sentence level dependency relations or parse sentences operable to generate a dependency tree), and stores the natural language paragraph, the first coreference mention, the natural language sentence, and the dependency relation data in the second data storage (Che: Abstract; ¶ 45-49, 65; Fig 5: such as by buffering in memory 32, 34 and/or memory associated with processor 30); an embedding module that extracts the natural language sentence and the dependency relation data from the second data storage (Che: Abstract; ¶ 45-49, 65; Fig 5: system generates a graphs based on sentences, words, etc. of input documents, generates a graph of dependencies a graph of coreferences in concert with determined embeddings and provides same to a graph neural network wherein the embedding layer of the system receives a matrix of word vectors, values etc. as input and at least the embedding and encoding layers of the system output vectors); and generates an integrated embedding vector for the natural language paragraph based on the natural language sentence and the dependency relation data (id.); and a coreference resolution module that trains a graph learning neural network based on the integrated embedding vector and the first coreference mention to generate a coreference resolution model (Che: Abstract; ¶ 45-49, 65; Fig 5: system determines global coreference relations and local dependency relation to generate embedding vectors and thereby train a fusion layer of the graph neural network) and a first coreference mention preset (Che: Abstract; ¶ 54, 63; Fig 5: such as a golden label or other labelled data for training) for the natural language paragraph to generate a named entity resolution model (Che: Abstract; ¶ 15, etc.; Fig 5, etc.). In a related field of endeavor Fei teaches a deep reinforcement learning system and method (Fei: Title; ¶ 27, 29) for coreference resolution (Fei: ¶ 29, 30) such as by iteratively generating training data such as co-reference graphs for input document used over a plurality of epochs (Fei: ¶ 29, 30; Fig 1, 2; claims 2, 16). It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to utilize integrated embeddings and annotated labelled mentions such as those discussed by Che to train the Pei coreference model for at least the purpose of deterring mentions and performing coreference recognition based thereon; one of ordinary skill in the art would have expected only predictable results therefrom. Regarding claim 11, 18—the claims are considered to recite substantially similar subject matter to that of claim 2 and are similarly rejected. Regarding claim 12—the claim is considered to recite substantially similar subject matter to that of claim 3 and is similarly rejected. Regarding claim 13, 19—the claims are considered to recite substantially similar subject matter to that of claim 4 and are similarly rejected. Regarding claim 14—the claim is considered to recite substantially similar subject matter to that of claim 5 and is similarly rejected. Regarding claim 15—the claim is considered to recite substantially similar subject matter to that of claim 6 and is similarly rejected. Regarding claim 16—the claim is considered to recite substantially similar subject matter to that of claim 7 and is similarly rejected. Regarding claim 17—the claim is considered to recite substantially similar subject matter to that of claims 1, 10 and is similarly rejected. Regarding claim 20 Che in view of Fei teaches or suggests: The method of claim 17, further comprising inferring a third coreference mention for the natural language paragraph input by a user using the coreference resolution model Fei: ¶ 31, 58; claim 2: a ground truth first coreference mention integrated with coreference mentions and antecedents thereof to thereby compute, resolve, etc. a reward, gradient based thereon and to update, train, etc. the policy network thereby which when employed by a user operates to detect or resolve coreferences, scores thereof). The claim is considered obvious over Che as modified by Fei as addressed in the base claim as it would have been obvious to apply the further teaching of Che and/or Fei to the modified device of Che and Fei; one of ordinary skill in the art would have expected only predictable results therefrom. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to PAUL C MCCORD whose telephone number is (571)270-3701. The examiner can normally be reached 730-630 M-F. 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, CAROLYN EDWARDS can be reached at (571) 270-7136. 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. /PAUL C MCCORD/ Primary Examiner, Art Unit 2692 /CAROLYN R EDWARDS/ Supervisory Patent Examiner, Art Unit 2692
Read full office action

Prosecution Timeline

Mar 05, 2024
Application Filed
Jan 31, 2026
Non-Final Rejection — §101, §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12603094
ADAPTIVE PROCESSING WITH MULTIPLE MEDIA PROCESSING NODES
2y 5m to grant Granted Apr 14, 2026
Patent 12592238
INFORMATION PROCESSING METHOD, INFORMATION PROCESSING DEVICE, AND NON-TRANSITORY COMPUTER READABLE RECORDING MEDIUM STORING INFORMATION PROCESSING PROGRAM
2y 5m to grant Granted Mar 31, 2026
Patent 12593192
MEDIA PLAYBACK BASED ON SENSOR DATA
2y 5m to grant Granted Mar 31, 2026
Patent 12572323
DYNAMIC AUDIO CONTENT GENERATION
2y 5m to grant Granted Mar 10, 2026
Patent 12567003
TECHNOLOGIES FOR DECENTRALIZED FLEET ANALYTICS
2y 5m to grant Granted Mar 03, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
69%
Grant Probability
96%
With Interview (+26.6%)
3y 5m
Median Time to Grant
Low
PTA Risk
Based on 569 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month