A Goal-Driven Natural Language Interface for Creating Application Integration Workflows

Authors

  • Michelle Brachman IBM Research
  • Christopher Bygrave IBM Cloud & Cognitive Software
  • Tathagata Chakraborti IBM Research
  • Arunima Chaudhary IBM Research
  • Zhining Ding Wellesley College
  • Casey Dugan IBM Research
  • David Gros University of California Davis
  • Thomas Gschwind IBM Research
  • James Johnson IBM Research
  • Jim Laredo IBM Research
  • Christoph Miksovic IBM Research
  • Qian Pan IBM Research
  • Priyanshu Rai Persistent Systems Limited
  • Ramkumar Ramalingam IBM Cloud & Cognitive Software
  • Paolo Scotton IBM Research
  • Nagarjuna Surabathina IBM Cloud & Cognitive Software
  • Kartik Talamadupula IBM Research

DOI:

https://doi.org/10.1609/aaai.v36i11.21712

Keywords:

Ai Planning, Abstract Meaning Representation, Amr, Knowledge Graph, Web Services, Composition, Integration, Natural Language Processing, Visualization, Search, Discovery

Abstract

Web applications and services are increasingly important in a distributed internet filled with diverse cloud services and applications, each of which enable the completion of narrowly defined tasks. Given the explosion in the scale and diversity of such services, their composition and integration for achieving complex user goals remains a challenging task for end-users and requires a lot of development effort when specified by hand. We present a demonstration of the Goal Oriented Flow Assistant (GOFA) system, which provides a natural language solution to generate workflows for application integration. Our tool is built on a three-step pipeline: it first uses Abstract Meaning Representation (AMR) to parse utterances; it then uses a knowledge graph to validate candidates; and finally uses an AI planner to compose the candidate flow. We provide a video demonstration of the deployed system as part of our submission.

Downloads

Published

2022-06-28

How to Cite

Brachman, M., Bygrave, C., Chakraborti, T., Chaudhary, A., Ding, Z., Dugan, C., Gros, D., Gschwind, T., Johnson, J., Laredo, J., Miksovic, C., Pan, Q., Rai, P., Ramalingam, R., Scotton, P., Surabathina, N., & Talamadupula, K. (2022). A Goal-Driven Natural Language Interface for Creating Application Integration Workflows. Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 13155-13157. https://doi.org/10.1609/aaai.v36i11.21712