# Coalescing Global and Local Information for Procedural Text Understanding

arXiv: https://arxiv.org/abs/2208.12848 · HTML: https://mlsanity.com/paper/2208.12848/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 43 references that are in the map.
- First posted on arXiv 26 Aug 2022.

## Builds on (most cited first, 30 of 35)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer](https://mlsanity.com/paper/2110.07904/) (2021)
- [A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation](https://mlsanity.com/paper/2001.05139/) (2020)
- [Counterfactual Story Reasoning and Generation](https://mlsanity.com/paper/1909.04076/) (2019)
- [GLUCOSE: GeneraLized and COntextualized Story Explanations](https://mlsanity.com/paper/2009.07758/) (2020)
- [Reasoning about Goals, Steps, and Temporal Ordering with WikiHow](https://mlsanity.com/paper/2009.07690/) (2020)
- [Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning](https://mlsanity.com/paper/2010.05906/) (2020)
- [Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension](https://mlsanity.com/paper/1805.06975/) (2018)
- [Simulating Action Dynamics with Neural Process Networks](https://mlsanity.com/paper/1711.05313/) (2017)
- [Visual Goal-Step Inference using wikiHow](https://mlsanity.com/paper/2104.05845/) (2021)
- [Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering](https://mlsanity.com/paper/1910.14087/) (2019)
- [A Dataset for Tracking Entities in Open Domain Procedural Text](https://mlsanity.com/paper/2011.08092/) (2020)
- [Simpler Context-Dependent Logical Forms via Model Projections](https://mlsanity.com/paper/1606.05378/) (2016)
- [Reasoning about Actions and State Changes by Injecting Commonsense Knowledge](https://mlsanity.com/paper/1808.10012/) (2018)
- [Incorporating Structured Commonsense Knowledge in Story Completion](https://mlsanity.com/paper/1811.00625/) (2018)
- [Paragraph-level Commonsense Transformers with Recurrent Memory](https://mlsanity.com/paper/2010.01486/) (2020)
- [Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events](https://mlsanity.com/paper/2104.07635/) (2021)
- [Think about it! Improving defeasible reasoning by first modeling the question scenario](https://mlsanity.com/paper/2110.12349/) (2021)
- [Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding](https://mlsanity.com/paper/2109.04947/) (2021)
- [Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension](https://mlsanity.com/paper/1810.05682/) (2018)
- [Knowledge-Aware Procedural Text Understanding with Multi-Stage Training](https://mlsanity.com/paper/2009.13199/) (2020)
- [Procedural Reading Comprehension with Attribute-Aware Context Flow](https://mlsanity.com/paper/2003.13878/) (2020)
- [Tracking Discrete and Continuous Entity State for Process Understanding](https://mlsanity.com/paper/1904.03518/) (2019)

## Built on by (most cited first, 10 of 10)

- [Language Models of Code are Few-Shot Commonsense Learners](https://mlsanity.com/paper/2210.07128/) (2022)
- [FIRE: Food Image to REcipe generation](https://mlsanity.com/paper/2308.14391/) (2023)
- [A Study of Situational Reasoning for Traffic Understanding](https://mlsanity.com/paper/2306.02520/) (2023)
- [Knowledge-enhanced Agents for Interactive Text Games](https://mlsanity.com/paper/2305.05091/) (2023)
- [Understand the Dynamic World: An End-to-End Knowledge Informed Framework for Open Domain Entity State Tracking](https://mlsanity.com/paper/2304.13854/) (2023)
- [The Role of Semantic Parsing in Understanding Procedural Text](https://mlsanity.com/paper/2302.06829/) (2023)
- [Do large language models and humans have similar behaviors in causal inference with script knowledge?](https://mlsanity.com/paper/2311.07311/) (2023)
- [Transferring Procedural Knowledge across Commonsense Tasks](https://mlsanity.com/paper/2304.13867/) (2023)
- [From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning](https://mlsanity.com/paper/2310.18364/) (2023)
- [Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding](https://mlsanity.com/paper/2210.06444/) (2022)

## Abstract (arXiv)

Procedural text understanding is a challenging language reasoning task that requires models to track entity states across the development of a narrative. A complete procedural understanding solution should combine three core aspects: local and global views of the inputs, and global view of outputs. Prior methods considered a subset of these aspects, resulting in either low precision or low recall. In this paper, we propose Coalescing Global and Local Information (CGLI), a new model that builds entity- and timestep-aware input representations (local input) considering the whole context (global input), and we jointly model the entity states with a structured prediction objective (global output). Thus, CGLI simultaneously optimizes for both precision and recall. We extend CGLI with additional output layers and integrate it into a story reasoning framework. Extensive experiments on a popular procedural text understanding dataset show that our model achieves state-of-the-art results; experiments on a story reasoning benchmark show the positive impact of our model on downstream reasoning.