English

DREAM: Improving Situational QA by First Elaborating the Situation

Computation and Language 2022-05-06 v3 Artificial Intelligence

Abstract

When people answer questions about a specific situation, e.g., "I cheated on my mid-term exam last week. Was that wrong?", cognitive science suggests that they form a mental picture of that situation before answering. While we do not know how language models (LMs) answer such questions, we conjecture that they may answer more accurately if they are also provided with additional details about the question situation, elaborating the "scene". To test this conjecture, we train a new model, DREAM, to answer questions that elaborate the scenes that situated questions are about, and then provide those elaborations as additional context to a question-answering (QA) model. We find that DREAM is able to create better scene elaborations (more accurate, useful, and consistent) than a representative state-of-the-art, zero-shot model (Macaw). We also find that using the scene elaborations as additional context improves the answer accuracy of a downstream QA system, including beyond that obtainable by simply further finetuning the QA system on DREAM's training data. These results suggest that adding focused elaborations about a situation can improve a system's reasoning about it, and may serve as an effective way of injecting new scenario based knowledge into QA models. Finally, our approach is dataset-neutral; we observe improved QA performance across different models, with even bigger gains on models with fewer parameters. We make our dataset and model publicly available at https://github.com/allenai/dream.

Keywords

Cite

@article{arxiv.2112.08656,
  title  = {DREAM: Improving Situational QA by First Elaborating the Situation},
  author = {Yuling Gu and Bhavana Dalvi Mishra and Peter Clark},
  journal= {arXiv preprint arXiv:2112.08656},
  year   = {2022}
}

Comments

to be published in NAACL 2022

R2 v1 2026-06-24T08:19:48.909Z