Siemens Aktiengesellschaft

Drimco Gmbh

Pankaj Gupta

Bernt Andrassy

Florian Büttner

Yatin Chaudhary

Subburam Rajaram

Thomas A Runkler

Thomas Runkler

Khushbu Saxena

Various embodiments of the teachings herein include a computer-implemented method of fine-tuning Natural Language Processing (NLP) models. Some examples include: providing a training data set including a multitude of training text documents; providing a NLP model including a Neural Network (NN) based Topic Model (TM) having scalable TM parameters and a parallel large-scale pre-trained Language Model (LM) having scalable LM parameters; and fine-tuning the NLP model by jointly training the NN-based TM and the parallel large-scale pre-trained LM using a projected vector comprising a combination and projection of a document topic proportion generated by the NN-based TM based on the scalable TM parameters from an input training text document of the multitude of training text documents, and of a contextualized document representation generated by the large-scale pre-trained LM based on the scalable LM parameters from the same input training text document.

Decarbonizing BERT with topics for efficient document classification

Provided is a ticketing system adapted to retrieve a recommendation from a knowledge database in response to a received query, the ticketing system including a processor adapted to perform semantic similarity learning in textual description pairs by calculating similarity scores for similarities between the received query and tickets stored in the knowledge database of the ticketing system, wherein each textual description pair includes a textual description of the received query and a textual description of a ticket of a plurality of tickets stored in the knowledge database of the ticketing system, wherein the ticket having the maximum similarity score is identified and a solution of the identified ticket is output as the retrieved recommendation for the received query by the ticketing system.

Method for retrieving a recommendation from a knowledge database of a ticketing system

A method and system for automatically performing a discovery of topics within temporal ordered text document collections are provided. The method includes generating a bag of words vector for each text document collection using a predefined dictionary. The method also includes iteratively calculating, based on the generated bag of words vectors, for each text document collection, a hidden topic vector representing topics of the respective text document collection using a calculated hidden state vector memorizing a hidden state of all previous text document collections.

Method and system for automatic discovery of topics and trends over time

The invention refers to a natural language processing system configured for receiving an input sequence cof input words (v, v, . . . v) representing a first sequence of words in a natural language of a first text and generating an output sequence of output words (,, . . .) representing a second sequence of words in a natural language of a second text and modeled by a multinominal topic model, wherein the multinominal topic model is extended by an incorporation of language structures using a deep contextualized Long-Short-Term Memory model.

System and method for natural language processing with a multinominal topic model

Present invention concerns a method of relation extraction from a text corpus, the method comprising extracting instances from the text corpus based on seeds, wherein the seeds include at least one set of template seeds and at least one set of entity seeds. The invention also pertains to related devices and methods.

Joint bootstrapping machine for text analysis

The present invention concerns a text analysis system, the text analysis system being adapted for utilizing a topic model to provide a document representation. The topic model is based on learning performed on a text corpus utilizing hidden layer representations associated to words of the text corpus, wherein each hidden layer representation pertains to a specific word of the text corpus and is based on a word environment including words occurring before and after the specific word in a text of the text corpus.

Automatized text analysis

The invention refers to a natural language processing system configured for receiving an input sequence cof input words representing a first sequence of words in a natural language of a first text and generating an output sequence of output words representing a second sequence of words in a natural language of a second text and modeled by a multinominal topic model, wherein the multinominal topic model is extended by an incorporation of full contextual information around each word v, wherein both preceding words vand following words varound each word vare captured by using a bi-directional language modelling and a feed-forward fashion, wherein position dependent forward hidden layers {right arrow over (h)}and backward hidden layersfor each word vare computed.

System and method for natural language processing

Provided is a computer-implemented method for inter-sententially determining a semantic relationship between a first entity and a second entity in a natural language document, comprising at least the steps of:

Neural relation extraction within and across sentence boundaries

A Semantic Textual Similarity System comprising a first Long Short Term Memory, LSTM, branch adapted to be operative, to determine text similarity, on a first text corpus, the first text corpus comprising a plurality of first text elements; wherein each first text element has a first number of distinct subdivisions. The system also comprises a second LSTM branch adapted to be operative, to determine text similarity, on a second text corpus, the second text corpus comprising a plurality of second text elements, wherein each second text element has a second number of distinct subdivisions.

Semantic textual similarity system

A device for relation extraction in a natural language sentence having n words is suggested, the device comprising: a recurrent neural network for joint entity and relation extractions of entities and relations between the entities in the sentence, and an entity-relation table for storing entity labels for the entities and relation labels for the relations, wherein both the entity labels and the relation labels are defined as instances of binary relationships between certain words wand win the sentence, with i&#x2208;[1, . . . , n], and j&#x2208;[1, . . . , n], wherein each of the entity labels is a first binary relationship for i=j, and wherein each of the relation labels is a second binary relationship for i&#x2260;j, wherein the recurrent neural network is configured to fill the cells of the entity-relation table and includes a forward neural network and a backward neural network.

Growing community of inventors

Munich, Germany

Pankaj Gupta