Sap Se

Daniel Dahlmeier

Ruidan He

Marcus Roy

Gerd Moser

Basem Suleiman

Dominik Schrank

Methods, systems, and computer-readable storage media for receiving a vocabulary, the vocabulary including text data that is provided as at least a portion of raw data, the raw data being provided in a computer-readable file, associating each word in the vocabulary with a feature vector, providing a sentence embedding for each sentence of the vocabulary based on a plurality of feature vectors to provide a plurality of sentence embeddings, providing a reconstructed sentence embedding for each sentence embedding based on a weighted parameter matrix to provide a plurality of reconstructed sentence embeddings, and training the unsupervised neural attention model based on the sentence embeddings and the reconstructed sentence embeddings to provide a trained neural attention model, the trained neural attention model being used to automatically determine aspects from the vocabulary.

Unsupervised neural attention model for aspect extraction

Methods, systems, and computer-readable storage media for receiving a vocabulary that includes text data that is provided as at least a portion of raw data, the raw data being provided in a computer-readable file, providing word embeddings based on the vocabulary, the word embeddings including word vectors for words included in the vocabulary, clustering word embeddings to provide a plurality of clusters, each cluster representing an aspect inferred from the vocabulary, determining a respective association score between each word in the vocabulary and a respective aspect, and providing a word ranking for each aspect based on the respective association scores.

Unsupervised aspect extraction from raw data using word embeddings

Methods, systems, and computer-readable storage media for providing action items from audio within an enterprise context. In some implementations, actions include determining a context of audio that is to be processed, providing training data to a speech recognition component, the training data being provided based on the context, receiving text from the speech recognition component, processing the text to identify one or more action items by identifying one or more concepts within the text and matching the one or more concepts to respective transitions in an automaton, and providing the one or more action items for display to one or more users.

Growing community of inventors

Singapore, Singapore

Daniel Dahlmeier