Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

Extend, don’t rebuild: Phrasing conditional graph modification as autoregressive sequence labelling

Item Type:Conference or Workshop Item
Title:Extend, don’t rebuild: Phrasing conditional graph modification as autoregressive sequence labelling
Creators Name:Weber, L. and Münchmeyer, J. and Garda, S. and Leser, U.
Abstract:Deriving and modifying graphs from natural language text has become a versatile basis technology for information extraction with applications in many subfields, such as semantic parsing or knowledge graph construction. A recent work used this technique for modifying scene graphs (He et al. 2020), by first encoding the original graph and then generating the modified one based on this encoding. In this work, we show that we can considerably increase performance on this problem by phrasing it as graph extension instead of graph generation. We propose the first model for the resulting graph extension problem based on autoregressive sequence labelling. On three scene graph modification data sets, this formulation leads to improvements in accuracy over the state-of-the-art between 13 and 24 percentage points. Furthermore, we introduce a novel data set from the biomedical domain which has much larger linguistic variability and more complex graphs than the scene graph modification data sets. For this data set, the state-of-the art fails to generalize, while our model can produce meaningful predictions.
Source:Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Title of Book:Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Publisher:Association for Computational Linguistics
Page Range:1213-1224
Date:November 2021
Official Publication:http://doi.org/10.18653/v1/2021.emnlp-main.93

Repository Staff Only: item control page

Open Access
MDC Library