SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.16057 · NAACL · 2021

Grounding Open-Domain Instructions to Automate Web Support Tasks

Giovanni Campagna, Monica Lam, Larry Heck, James Landay, Nancy Xu, Sam Masling, Michael Du

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Grounding natural language instructions on the web to perform previously unseen tasks enables accessibility and automation. We introduce a task and dataset to train AI agents from open-domain, step-by-step instructions originally written for people. We build RUSS (Rapid Universal Support Service) to tackle this problem. RUSS consists of two models: First, a BERT-LSTM with pointers parses instructions to ThingTalk, a domain-specific language we design for grounding natural language on the web. Then, a grounding model retrieves the unique IDs of any webpage elements requested in ThingTalk. RUSS may interact with the user through a dialogue (e.g. ask for an address) or execute a web operation (e.g. click a button) inside the web runtime. To augment training, we synthesize natural language instructions mapped to ThingTalk. Our dataset consists of 80 different customer service problems from help websites, with a total of 741 step-by-step instructions and their corresponding actions. RUSS achieves 76.7% end-to-end accuracy predicting agent actions from single instructions. It outperforms stateof-the-art models that directly map instructions to actions without ThingTalk. Our user study shows that RUSS is preferred by actual users over web navigation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.16057")
get_code_for_paper("2103.16057")
have("2103.16057")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.16057.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.16057.svg)](https://syntology.ai/paper/2103.16057)

Connect an agent — have() is free.