# Constructing Temporal Dynamic Knowledge Graphs from Interactive Text-based Games

arXiv: https://arxiv.org/abs/2311.01928 · HTML: https://mlsanity.com/paper/2311.01928/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 3 Nov 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [Interactive Fiction Games: A Colossal Adventure](https://mlsanity.com/paper/1909.05398/) (2019)
- [Learning to Speak and Act in a Fantasy Text Adventure Game](https://mlsanity.com/paper/1903.03094/) (2019)
- [Auxiliary Tasks in Multi-task Learning](https://mlsanity.com/paper/1805.06334/) (2018)
- [Retrieval-Augmented Generation for Code Summarization via Hybrid GNN](https://mlsanity.com/paper/2006.05405/) (2020)
- [Graph Constrained Reinforcement Learning for Natural Language Action Spaces](https://mlsanity.com/paper/2001.08837/) (2020)
- [Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning](https://mlsanity.com/paper/1812.01628/) (2018)
- [Learning Dynamic Belief Graphs to Generalize on Text-Based Games](https://mlsanity.com/paper/2002.09127/) (2020)
- [Learning Knowledge Graph-based World Models of Textual Environments](https://mlsanity.com/paper/2106.09608/) (2021)
- [Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge](https://mlsanity.com/paper/2005.00811/) (2020)
- [Modeling Worlds in Text](https://mlsanity.com/paper/2106.09578/) (2021)
- [Contextualized Non-local Neural Networks for Sequence Learning](https://mlsanity.com/paper/1811.08600/) (2018)
- [Building Dynamic Knowledge Graphs from Text-based Games](https://mlsanity.com/paper/1910.09532/) (2019)

## Built on by (most cited first, 1 of 1)

- [AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents](https://mlsanity.com/paper/2407.04363/) (2024)

## Abstract (arXiv)

In natural language processing, interactive text-based games serve as a test bed for interactive AI systems. Prior work has proposed to play text-based games by acting based on discrete knowledge graphs constructed by the Discrete Graph Updater (DGU) to represent the game state from the natural language description. While DGU has shown promising results with high interpretability, it suffers from lower knowledge graph accuracy due to its lack of temporality and limited generalizability to complex environments with objects with the same label. In order to address DGU's weaknesses while preserving its high interpretability, we propose the Temporal Discrete Graph Updater (TDGU), a novel neural network model that represents dynamic knowledge graphs as a sequence of timestamped graph events and models them using a temporal point based graph neural network. Through experiments on the dataset collected from a text-based game TextWorld, we show that TDGU outperforms the baseline DGU. We further show the importance of temporal information for TDGU's performance through an ablation study and demonstrate that TDGU has the ability to generalize to more complex environments with objects with the same label. All the relevant code can be found at urlhttps://github.com/yukw777/temporal-discrete-graph-updater.