Marek Reformat
2024
Fine-tuning Language Models for Triple Extraction with Data Augmentation
Yujia Zhang
|
Tyler Sadler
|
Mohammad Reza Taesiri
|
Wenjie Xu
|
Marek Reformat
Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024)
Advanced language models with impressive capabilities to process textual information can more effectively extract high-quality triples, which are the building blocks of knowledge graphs. Our work examines language models’ abilities to extract entities and the relationships between them. We use a diverse data augmentation process to fine-tune large language models to extract triples from the text. Fine-tuning is performed using a mix of trainers from HuggingFace and five public datasets, such as different variations of the WebNLG, SKE, DocRed, FewRel, and KELM. Evaluation involves comparing model outputs with test-set triples based on several criteria, such as type, partial, exact, and strict accuracy.The obtained results outperform ChatGPT and even match or exceed the performance of GPT-4.
2023
Reinforcement Learning for Topic Models
Jeremy Costello
|
Marek Reformat
Findings of the Association for Computational Linguistics: ACL 2023
We apply reinforcement learning techniques to topic modeling by replacing the variational autoencoder in ProdLDA with a continuous action space reinforcement learning policy. We train the system with a policy gradient algorithm REINFORCE. Additionally, we introduced several modifications: modernize the neural network architecture, weight the ELBO loss, use contextual embeddings, and monitor the learning process via computing topic diversity and coherence for each training step. Experiments areperformed on 11 data sets. Our unsupervised model outperforms all other unsupervised models and performs on par with or better than most models using supervised labeling. Our model is outperformed on certain data sets by a model using supervised labeling and contrastive learning. We have also conducted an ablation study to provide empirical evidence of performance improvements from changes we made to ProdLDA and found that the reinforcement learning formulation boosts performance. We open-source our code implementation.
Search