2018

Seq2Seq and Multi-Task Learning for joint intent and content extraction for domain specific interpreters

Velay, Marc, Daniel, Fabrice

Understand

This study evaluates the performances of an LSTM network for detecting and extracting the intent and content of com- mands for a financial chatbot.

  • It presents two techniques, sequence to sequence learning and Multi-Task Learning, which might improve on the previous task.

Built on

  • J. Huang et al (2013) Cross-Language knowledge transfer using multilingual deep neural network with shared hidden layers

    2013

    Earlier work this paper cites.

  • B. Liu & I. Lane (2016) Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling

    2016

    Earlier work this paper cites.

Similar

  • JK. Kim et al (2016) Intent detection using semantically enriched word embeddings

    2016

    Cited alongside, same era.

  • D. Golub & X. He (2016) Character-Level Question Answering with Attention

    2016

    Cited alongside, same era.

Then

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…