skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation
Goal-oriented Script Generation is a new task of generating a list of steps that can fulfill the given goal. In this paper, we propose to extend the task from the perspective of cognitive theory. Instead of a simple flat structure, the steps are typically organized hierarchically — Human often decompose a complex task into subgoals, where each subgoal can be further decomposed into steps. To establish the benchmark, we contribute a new dataset, propose several baseline methods, and set up evaluation metrics. Both automatic and human evaluation verify the high-quality of dataset, as well as the effectiveness of incorporating subgoals into hierarchical script generation. Furthermore, We also design and evaluate the model to discover subgoal, and find that it is a bit more difficult to decompose the goals than summarizing from segmented steps.  more » « less
Award ID(s):
2105329
PAR ID:
10440674
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Findings of the Association for Computational Linguistics: ACL 2023
Page Range / eLocation ID:
10129 to 10147
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Proceedings of the 14th International Conference on Natural Language Generation)
    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. 
    more » « less
  2. ; ; ; ; ; (, Proceedings of the AAAI Conference on Artificial Intelligence)
    We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. RSGs can be learned from weakly-annotated data, in the form of unsegmented demonstration trajectories, paired with abstract task descriptions, which are composed of terms initially unknown to the agent (e.g., collect-wood then craft-boat then go-across-river). Our framework also discovers dependencies between RSGs, e.g., the task collect-wood is a helpful subgoal for the task craft-boat. Given a goal description, the learned subgoals and the derived dependencies facilitate off-the-shelf planning algorithms, such as A* and RRT, by setting helpful subgoals as waypoints to the planner, which significantly improves performance-time efficiency. 
    more » « less
  3. ; ; ; ; ; (, Proceedings IEEE International Conference on Robotics and Automation)
    ision-Language Models (VLM) can generate plausible high-level plans when prompted with a goal, the context, an image of the scene, and any planning constraints. However, there is no guarantee that the predicted actions are geometrically and kinematically feasible for a particular robot embodiment. As a result, many prerequisite steps such as opening drawers to access objects are often omitted in their plans. Robot task and motion planners can generate motion trajectories that respect the geometric feasibility of actions and insert physically necessary actions, but do not scale to everyday problems that require common-sense knowledge and involve large state spaces comprised of many variables. We propose VLM-TAMP, a hierarchical planning algorithm that leverages a VLM to generate goth semantically-meaningful and horizon-reducing intermediate subgoals that guide a task and motion planner. When a subgoal or action cannot be refined, the VLM is queried again for replanning. We evaluate VLMTAMP on kitchen tasks where a robot must accomplish cooking goals that require performing 30-50 actions in sequence and interacting with up to 21 objects. VLM-TAMP substantially outperforms baselines that rigidly and independently execute VLM-generated action sequences, both in terms of success rates (50 to 100% versus 0%) and average task completion percentage (72 to 100% versus 15 to 45%). 
    more » « less
  4. ; ; ; (, ACM Transactions on Computing Education)
    null (Ed.)
    The subgoal learning framework has improved performance for novice programmers in higher education, but it has only started to be applied and studied in K-12 (primary/secondary). Programming education in K-12 is growing, and many international initiatives are attempting to increase participation, including curricular initiatives like Computer Science Principles and non-profit organizations like Code.org. Given that subgoal learning is designed to help students with no prior knowledge, we designed and implemented subgoals in the introduction to programming unit in Code.org's Computer Science Principles course. The redesigned unit includes subgoal-oriented instruction and subgoal-themed pre-written comments that students could add to their programming activities. To evaluate efficacy, we compared behaviors and performance of students who received the redesigned subgoal unit to those receiving the original unit. We found that students who learned with subgoals performed better on problem-solving questions but not knowledge-based questions and wrote more in open-ended response questions, including a practice Performance Task for the AP exam. Moreover, at least one-third of subgoal students continued to use the subgoal comments after the subgoal-oriented instruction had been faded, suggesting that they found them useful. Survey data from the teachers suggested that students who struggled with the concepts found the subgoals most useful. Implications for future designs are discussed. 
    more » « less
  5. ; ; ; ; ; (, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing)
    Understanding what sequence of steps are needed to complete a goal can help artificial intelligence systems reason about human activities. Past work in NLP has examined the task of goal-step inference for text. We introduce the visual analogue. We propose the Visual Goal-Step Inference (VGSI) task, where a model is given a textual goal and must choose which of four images represents a plausible step towards that goal. With a new dataset harvested from wikiHow consisting of 772,277 images representing human actions, we show that our task is challenging for state-of-the-art multimodal models. Moreover, the multimodal representation learned from our data can be effectively transferred to other datasets like HowTo100m, increasing the VGSI accuracy by 15 - 20%. Our task will facilitate multimodal reasoning about procedural events. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email