Patent · US Active

Multitask learning as question answering

US10776581B2 · kind B2 · utility

26Cited by
6References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 8, 2018
Grant dateSep 15, 2020
Priority date
Expiry dateDec 2, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/1822
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Approaches for multitask learning as question answering include an input layer for encoding a context and a question, a self-attention based transformer including an encoder and a decoder, a first bi-directional long-term short-term memory (biLSTM) for further encoding an output of the encoder, a long-term short-term memory (LSTM) for generating a context-adjusted hidden state from the output of the decoder and a hidden state, an attention network for generating first attention weights based on an output of the first biLSTM and an output of the LSTM, a vocabulary layer for generating a distribution over a vocabulary, a context layer for generating a distribution over the context, and a switch for generating a weighting between the distributions over the vocabulary and the context, generating a composite distribution based on the weighting, and selecting a word of an answer using the composite distribution.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.