mlsanityData to 7 Oct 2026

Alignment-based compositional semantics for instruction following

arXiv 1508.06491 ↗First posted 26 Aug 2015cs.CLcited by 21

Not on the map. Why?

Abstract (arXiv)

This paper describes an alignment-based model for interpreting natural language instructions in context. We approach instruction following as a search over plans, scoring sequences of actions conditioned on structured observations of text and the environment. By explicitly modeling both the low-level compositional structure of individual actions and the high-level structure of full plans, we are able to learn both grounded representations of sentence meaning and pragmatic constraints on interpretation. To demonstrate the model's flexibility, we apply it to a diverse set of benchmark tasks. On every task, we outperform strong task-specific baselines, and achieve several new state-of-the-art results.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Aug 2015.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 6; 2022: 5; 2023: 6; 2024: 3.

21 papers.

Sort:

By area:

  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  2. 2021Episodic Transformer for Vision-and-Language Navigationcited by 155
  3. 2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationcited by 117
  4. 2018Learning to Understand Goal Specifications by Modelling Rewardcited by 80
  5. 2022Correcting Robot Plans with Natural Language Feedbackcited by 68
  6. 2023Learning to Model the World with Languagecited by 66
  7. 2022A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learningcited by 60
  8. 2022Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigationcited by 50
  9. 2022Inferring Rewards from Language in Contextcited by 50
  10. 2021Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learningcited by 45
  11. 2023Lana: A Language-Capable Navigator for Instruction Following and Generationcited by 39
  12. 2021Diagnosing Vision-and-Language Navigation: What Really Matterscited by 36
9 more
  1. 2024Policy Improvement using Language Feedback Modelscited by 16
  2. 2024Grounding Language Plans in Demonstrations Through Counterfactual Perturbationscited by 11
  3. 2021SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmarkcited by 10
  4. 2023Conceptual Reinforcement Learning for Language-Conditioned Taskscited by 8
  5. 2022LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-trainingcited by 5
  6. 2023Learning Rational Subgoals from Demonstrations and Instructionscited by 5
  7. 2023Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operationscited by 5
  8. 2024Learning Planning Abstractions from Languagecited by 3
  9. 2021Are you doing what I say? On modalities alignment in ALFREDcited by 0