TL;DR
This paper introduces a new task called Goal-Oriented Script Construction, enabling models to generate or retrieve step sequences for accomplishing goals across multiple languages, with promising zero-shot capabilities despite challenges.
Contribution
It presents the first multilingual script learning dataset from wikiHow and evaluates baseline generation and retrieval methods for the task.
Findings
The task is practical and feasible.
State-of-the-art models face challenges in performance.
Methods show decent zero-shot transfer across datasets.
Abstract
The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a sequence of steps to accomplish a given goal. We pilot our task on the first multilingual script learning dataset supporting 18 languages collected from wikiHow, a website containing half a million how-to articles. For baselines, we consider both a generation-based approach using a language model and a retrieval-based approach by first retrieving the relevant steps from a large candidate pool and then ordering them. We show that our task is practical, feasible but challenging for state-of-the-art Transformer models, and that our methods can be readily deployed for various other datasets and domains with decent zero-shot performance.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsAttention Is All You Need · Linear Layer · Absolute Position Encodings · Position-Wise Feed-Forward Layer · Label Smoothing · Residual Connection · Layer Normalization · Byte Pair Encoding · Adam · Dense Connections
