Papers by Grigorios Tsoumakas
LARD: Large-scale Artificial Disfluency Generation (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing datasets suffer from class imbalance issues, causing performance problems . Disfluency detection is a critical task in real-time dialogue systems . |
| Approach: | They propose a method for generating complex and realistic artificial disfluencies with little effort using a large-scale dataset. |
| Outcome: | The proposed method can handle repetitions, replacements, and restarts on a large-scale dataset with disfluencies. |
Topic-Controllable Summarization: Topic-Aware Evaluation and Transformer Methods (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for topic-controllable summarization are limited by their recurrent architectures and require modifications to the model's architecture for controlling the topic. |
| Approach: | They propose a new topic-oriented evaluation measure to automatically evaluate the generated summaries based on the topic affinity between the generated summary and the desired topic. |
| Outcome: | The proposed method achieves better performance compared to more complicated embedding-based approaches while also being significantly faster. |
Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue (2022.findings-acl)
Copied to clipboard
| Challenge: | Xu et al., 2019; Lewis e t al, 2019) show that Bayesian summarization methods can generate high quality summaries but suffer from a couple of issues when inputs lie far from the training data distribution. |
| Approach: | They propose to extend state-of-the-art summarization models with Monte Carlo dropout and perform multiple stochastic forward passes to approximate Bayesian inference. |
| Outcome: | The proposed method outperforms deterministic summarization models on multiple benchmark datasets. |