Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2307.10443 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910297349947392 |
|---|---|
| author | Foolad, Shima Kiani, Kourosh |
| author_facet | Foolad, Shima Kiani, Kourosh |
| contents | Despite the significant progress made by transformer models in machine reading comprehension tasks, they still fall short in handling complex reasoning tasks due to the absence of explicit knowledge in the input sequence. To address this limitation, many recent works have proposed injecting external knowledge into the model. However, selecting relevant external knowledge, ensuring its availability, and requiring additional processing steps remain challenging. In this paper, we introduce a novel attention pattern that integrates reasoning knowledge derived from a heterogeneous graph into the transformer architecture without relying on external knowledge. The proposed attention pattern comprises three key elements: global-local attention for word tokens, graph attention for entity tokens that exhibit strong attention towards tokens connected in the graph as opposed to those unconnected, and the consideration of the type of relationship between each entity token and word token. This results in optimized attention between the two if a relationship exists. The pattern is coupled with special relative position labels, allowing it to integrate with LUKE's entity-aware self-attention mechanism. The experimental findings corroborate that our model outperforms both the cutting-edge LUKE-Graph and the baseline LUKE model across two distinct datasets: ReCoRD, emphasizing commonsense reasoning, and WikiHop, focusing on multi-hop reasoning challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_10443 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Integrating a Heterogeneous Graph with Entity-aware Self-attention using Relative Position Labels for Reading Comprehension Model Foolad, Shima Kiani, Kourosh Computation and Language Machine Learning Despite the significant progress made by transformer models in machine reading comprehension tasks, they still fall short in handling complex reasoning tasks due to the absence of explicit knowledge in the input sequence. To address this limitation, many recent works have proposed injecting external knowledge into the model. However, selecting relevant external knowledge, ensuring its availability, and requiring additional processing steps remain challenging. In this paper, we introduce a novel attention pattern that integrates reasoning knowledge derived from a heterogeneous graph into the transformer architecture without relying on external knowledge. The proposed attention pattern comprises three key elements: global-local attention for word tokens, graph attention for entity tokens that exhibit strong attention towards tokens connected in the graph as opposed to those unconnected, and the consideration of the type of relationship between each entity token and word token. This results in optimized attention between the two if a relationship exists. The pattern is coupled with special relative position labels, allowing it to integrate with LUKE's entity-aware self-attention mechanism. The experimental findings corroborate that our model outperforms both the cutting-edge LUKE-Graph and the baseline LUKE model across two distinct datasets: ReCoRD, emphasizing commonsense reasoning, and WikiHop, focusing on multi-hop reasoning challenges. |
| title | Integrating a Heterogeneous Graph with Entity-aware Self-attention using Relative Position Labels for Reading Comprehension Model |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2307.10443 |