Microsoft Technology Licensing, LLC

Maluuba Inc.

Philip Bachman

Adam Trischler

Xingdi Yuan

Zheng Ye

Alessandro Sordoni

Kaheer Suleman

Jing He

Hannes Schulz

Shikhar Sharma

Described herein are systems and methods for providing a natural language comprehension system that employs a two-stage process for machine comprehension of text. The first stage indicates words in one or more text passages that potentially answer a question. The first stage outputs a set of candidate answers for the question, along with a first probability of correctness for each candidate answer. The second stage forms one or more hypotheses by inserting each candidate answer into the question and determines whether a sematic relationship exists between each hypothesis and each sentence in the text. The second processing circuitry generates a second probability of correctness for each candidate answer and combines the first probability with the second probability to produce a score that is used to rank the candidate answers. The candidate answer with the highest score is selected as a predicted answer.

Machine comprehension of unstructured text

Examples of the present disclosure provide systems and methods relating to a machine comprehension test with a learning-based approach, harnessing neural networks arranged in a parallel hierarchy. This parallel hierarchy enables the model to compare the passage, question, and answer from a variety of perspectives, as opposed to using a manually designed set of features. Perspectives may range from the word level to sentence fragments to sequences of sentences, and networks operate on word-embedding representations of text. A training methodology for small data is also provided.

Parallel-hierarchical model for machine comprehension on small data

Described herein are systems and methods for providing a natural language comprehension system (NLCS) that iteratively performs an alternating search to gather information that may be used to predict the answer to the question. The NLCS first attends to a query glimpse of the question, and then finds one or more corresponding matches by attending to a text glimpse of the text.

Iterative alternating neural attention for machine reading

Described herein are systems and methods for providing a natural language generator in a spoken dialog system that considers both lexicalized and delexicalized dialog act slot-value pairs when translating one or more dialog act slot-value pairs into a natural language output. Each slot and value associated with the slot in a dialog act are represented as (dialog act+slot, value), where the first term (dialog act+slot) is delexicalized and the second term (value) is lexicalized. Each dialog act slot-value representation is processed to produce at least one delexicalized sentence as an output. A lexicalized sentence is produced by replacing each delexicalized slot with the value associated with the delexicalized slot.

Growing community of inventors

Montreal, Canada

Philip Bachman