Infusing Commonsense World Models with Graph Knowledge

• URL: http://arxiv.org/abs/2301.05746v1
• Date: Fri, 13 Jan 2023 19:58:27 GMT
• Title: Infusing Commonsense World Models with Graph Knowledge
• Authors: Alexander Gurung, Mojtaba Komeili, Arthur Szlam, Jason Weston, and Jack Urbanek
• Abstract summary: We study the setting of generating narratives in an open world text adventure game. A graph representation of the underlying game state can be used to train models that consume and output both grounded graph representations and natural language descriptions and actions.
• Score: 89.27044249858332
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While language models have become more capable of producing compelling language, we find there are still gaps in maintaining consistency, especially when describing events in a dynamically changing world. We study the setting of generating narratives in an open world text adventure game, where a graph representation of the underlying game state can be used to train models that consume and output both grounded graph representations and natural language descriptions and actions. We build a large set of tasks by combining crowdsourced and simulated gameplays with a novel dataset of complex actions in order to to construct such models. We find it is possible to improve the consistency of action narration models by training on graph contexts and targets, even if graphs are not present at test time. This is shown both in automatic metrics and human evaluations. We plan to release our code, the new set of tasks, and best performing models.

Related papers

• GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs [74.98581417902201]
  We propose a novel framework to generate compositional 3D scenes from scene graphs. By exploiting node and edge information in scene graphs, our method makes better use of the pretrained text-to-image diffusion model. We conduct both qualitative and quantitative experiments to validate the effectiveness of GraphDreamer.
  arXiv  Detail & Related papers  (2023-11-30T18:59:58Z)
• Visual Storytelling with Question-Answer Plans [70.89011289754863]
  We present a novel framework which integrates visual representations with pretrained language models and planning. Our model translates the image sequence into a visual prefix, a sequence of continuous embeddings which language models can interpret. It also leverages a sequence of question-answer pairs as a blueprint plan for selecting salient visual concepts and determining how they should be assembled into a narrative.
  arXiv  Detail & Related papers  (2023-10-08T21:45:34Z)
• Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs [4.56877715768796]
  We show that ChatGPT achieves near state-of-the-art performance on some measures of the WebNLG 2020 challenge. We also show that there is a significant connection between what the LLM already knows about the data it is parsing and the quality of the output text.
  arXiv  Detail & Related papers  (2023-07-14T12:45:03Z)
• Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation [23.54754465832362]
  In conventional graph neural networks (GNNs) message passing on a graph is independent from text. This training regime leads to a semantic gap between graph knowledge and text. We propose a novel framework for knowledge graph enhanced dialogue generation.
  arXiv  Detail & Related papers  (2023-06-28T13:21:00Z)
• Modeling Worlds in Text [16.67845396797253]
  We provide a dataset that enables the creation of learning agents that can build knowledge graph-based world models of interactive narratives. Our dataset provides 24198 mappings between rich natural language observations and knowledge graphs. The training data is collected across 27 games in multiple genres and contains a further 7836 heldout instances over 9 additional games in the test set.
  arXiv  Detail & Related papers  (2021-06-17T15:02:16Z)
• GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph [53.70520466556453]
  We propose GraphFormers, where layerwise GNN components are nested alongside the transformer blocks of language models. With the proposed architecture, the text encoding and the graph aggregation are fused into an iterative workflow. In addition, a progressive learning strategy is introduced, where the model is successively trained on manipulated data and original data to reinforce its capability of integrating information on graph.
  arXiv  Detail & Related papers  (2021-05-06T12:20:41Z)
• Learning Chess Blindfolded: Evaluating Language Models on State Tracking [69.3794549747725]
  We consider the task of language modeling for the game of chess. Unlike natural language, chess notations describe a simple, constrained, and deterministic domain. We find that transformer language models can learn to track pieces and predict legal moves with high accuracy when trained solely on move sequences.
  arXiv  Detail & Related papers  (2021-02-26T01:16:23Z)
• Topic Adaptation and Prototype Encoding for Few-Shot Visual Storytelling [81.33107307509718]
  We propose a topic adaptive storyteller to model the ability of inter-topic generalization. We also propose a prototype encoding structure to model the ability of intra-topic derivation. Experimental results show that topic adaptation and prototype encoding structure mutually bring benefit to the few-shot model.
  arXiv  Detail & Related papers  (2020-08-11T03:55:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.