nlp_enjoyers at TextGraphs-17 Shared Task: Text-Graph Representations for Knowledge Graph Question Answering using all-MPNet
Nikita Kurdiukov, Viktoriia Zinkovich, Sergey Karpukhin, Pavel Tikhomirov
Abstract
This paper presents a model for solving the Multiple Choice Question Answering (MCQA) problem, focusing on the impact of subgraph extraction from a Knowledge Graph on model performance. The proposed method combines textual and graph information by adding linearized subgraphs directly into the main question prompt with separate tokens, enhancing the performance of models working with each modality separately. The study also includes an examination of Large Language Model (LLM) backbones and the benefits of linearized subgraphs and sequence length, with efficient training achieved through fine-tuning with LoRA. The top benchmark, using subgraphs and MPNet, achieved an F1 score of 0.3887. The main limitation of the experiments is the reliance on pre-generated subgraphs/triplets from the graph, and the lack of exploration of in-context learning and prompting strategies with decoder-based architectures.- Anthology ID:
- 2024.textgraphs-1.10
- Volume:
- Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Dmitry Ustalov, Yanjun Gao, Alexander Panchenko, Elena Tutubalina, Irina Nikishina, Arti Ramesh, Andrey Sakhovskiy, Ricardo Usbeck, Gerald Penn, Marco Valentino
- Venues:
- TextGraphs | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 126–130
- Language:
- URL:
- https://aclanthology.org/2024.textgraphs-1.10
- DOI:
- Cite (ACL):
- Nikita Kurdiukov, Viktoriia Zinkovich, Sergey Karpukhin, and Pavel Tikhomirov. 2024. nlp_enjoyers at TextGraphs-17 Shared Task: Text-Graph Representations for Knowledge Graph Question Answering using all-MPNet. In Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing, pages 126–130, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- nlp_enjoyers at TextGraphs-17 Shared Task: Text-Graph Representations for Knowledge Graph Question Answering using all-MPNet (Kurdiukov et al., TextGraphs-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.textgraphs-1.10.pdf