International Business Machines Corporation

Chen Gao

Zhong Fang Yuan

Tong Liu

Li Ni Zhang

Yong Fang Liang

Xiang Yu Yang

Bin Shang

Wen Jie Wang

De Shuo Kong

Ci-Wei Lan

Li Juan Gao

Rong Fu He

Embodiments of the present invention provide an approach for compressing data, and more particularly, to large-scale text data encoding and compression using absolute overfitting on pre-trained language models. Large-scale data is parsed into sentences. A unique token is generated for each sentence to form a token list. A generative (or compression) model is trained from the tokens in the token list to produce the corresponding sentence of each token through absolute overfitting of a pre-trained language model. The compressed text data is stored as the token list and generative model, resulting in a storage space savings.

Large-scale text data encoding and compression

An approach is provided for optimizing a feedback-type question answering process. A training set is constructed to detect missing information of a question. A natural language generation model is trained using the missing information. The natural language generation model is executed to generate a rhetorical question. A response to the rhetorical question is combined with the question to generate an input to a language processor. A new question is generated. The new question is applied to a document library. A final answer is generated.

Question answering information completion using machine reading comprehension-based process

A method, system, and computer program product for reconstructing training data and building a new incremental learning model with the reconstructed training data that can be further trained. The method may include receiving new data to be inputted into a previously trained machine learning model, where the previously trained machine learning model has inaccessible training data. The method may also include generating simulated training data using a reverse form of the previously trained machine learning model. The method may also include verifying the simulated training data. The method may also include creating a new machine learning model using the simulated training data, where the new machine learning model includes a same structure as the previously trained machine learning model. The method may also include inputting the new data into the new machine learning model, where the new machine learning model is further trained with the new data.

Incremental learning through reverse data distribution

A method and related system detail a split of an architecture of a monolithic application into an architecture of a micro service application. The method receives source code for the monolithic application, and maps the source code into a directed graph. The graph is split into subgraphs and optimized. The method further provides the detailing of the micro service application split, based on the subgraphs.

Cognitive method to split monolithic architecture into microservice architecture

Provided is a method, computer program product, and system for fusing knowledge graphs to generate a larger knowledgebase for responding to cross document questions. A processor may extract contextual information from a plurality of documents. The processor may generate, based on the extracted contextual information, a knowledge graph for each document of the plurality of documents. The processor may analyze each knowledge graph to determine if one or more entities of each knowledge graph are linked. The processor may fuse, in response to an entity in a first knowledge graph being linked to an entity in a second knowledge graph, the first knowledge graph with the second knowledge graph to create a fused knowledge graph.

Knowledge graph fusion

Techniques are provided for mapping natural language to code segments. In one embodiment, the techniques involve receiving a document and software code, wherein the document comprises a natural language description of a use of the code, generating, via a vectorization process performed on the document, at least one vector or word embedding, generating, via a natural language processing technique performed on the at least one vector or word embedding, a first label set, generating, via a machine learning analysis of the software code, a second label set, determining, based on a comparison of the first label set and the second label set, a match confidence between the document and the software code, wherein the match confidence indicates a measure of similarity between the first label set and the second label set, and upon determining that the match confidence exceeds a predefined threshold, mapping the document to the software code.

Mapping natural language and code segments

A method, system, and computer program product for implementing automated cognitive software application error detection is provided. The method includes receiving data associated with model based self-learning software code. The annotated data is automatically divided with respect to specified categorization and grouping attributes and categorized groups comprising portions of the annotated data are generated and analyzed. At least one incorrect annotation associated a group of the categorized groups is detected and filtered. Likewise, a correct annotation for the group is detected and retrieved from a database. The correct annotation is appended to the group.

Growing community of inventors

Xi'an, China

Chen Gao