Papers by George Tsatsaronis
Extracting, Detecting, and Generating Research Questions for Scientific Articles (2025.coling-main)
Copied to clipboard
Sina Taslimi, Artemis Capari, Hosein Azarbonyad, Zi Long Zhu, Zubair Afzal, Evangelos Kanoulas, George Tsatsaronis
| Challenge: | Existing tools to generate and extract RQs from scientific articles lack a definition of RQ in articles. |
| Approach: | They propose to use a set of regular expressions to identify articles with well-defined RQs and a detection component to identify more complex RQ's in articles. |
| Outcome: | The proposed pipeline can detect and generate RQs from scientific articles and generate high-quality ones. |
Novelty Goes Deep. A Deep Neural Solution To Document Level Novelty Detection (C18-1)
Copied to clipboard
Tirthankar Ghosal, Vignesh Edithal, Asif Ekbal, Pushpak Bhattacharyya, George Tsatsaronis, Srinivasa Satya Sameer Kumar Chivukula
| Challenge: | Existing methods for document-level novelty detection are limited and do not require manual feature engineering. |
| Approach: | They propose a deep Convolutional Neural Networks based model to classify a document as novel or redundant on the basis of documents already seen by the system. |
| Outcome: | The proposed model outperforms the state-of-the-art on a document-level novelty detection dataset by a margin of 5% in terms of accuracy. |
Scalable Patent Classification with Aggregated Multi-View Ranking (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing classification-based models struggle with scaling to large numbers of labels and generalizing to new labels. |
| Approach: | They propose a ranking-based method that integrates different views of patents and a meta-model that aggregates and ranks the labels given by the ranking models. |
| Outcome: | The proposed method outperforms the current state-of-the-art methods on two datasets . it can alleviate the limitations and achieve a significant performance improvement . |
Few-shot initializing of Active Learner via Meta-Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in few-shot and zero-shot learning have limited performance in domain specific applications. |
| Approach: | They propose to initialize an active learner with meta-learned parameters and generate task dependent softmax weights for active learning. |
| Outcome: | The proposed method performs better than the baseline at low budget, the authors show . they show that adding meta-learned learning rates and generating the softmax have negative consequences . |
Find the Funding: Entity Linking with Incomplete Funding Knowledge Bases (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to identifying and linking funding entities are suboptimal for the funding domain. |
| Approach: | They propose an entity linking model that can perform NIL prediction and overcome data scarcity issues in a time and data-efficient manner. |
| Outcome: | The proposed model outperforms existing baselines and overcomes data scarcity issues in a time and data-efficient manner. |
EigenSent: Spectral sentence embeddings using higher-order Dynamic Mode Decomposition (P19-1)
Copied to clipboard
| Challenge: | Existing methods for calculating word embeddings use weighted averages or learn word representations, but this is not the case. |
| Approach: | They propose to use spectral methods of signal representation and summarization to construct word-sequence embeddings in unsupervised fashion by using a spectrally-based decomposition and signal summarizing technique on text. |
| Outcome: | The proposed method can summarize transitions in a sequence of words and generate an embedding that can represent well the sequence itself. |
Unsupervised Dense Retrieval for Scientific Articles (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing lexical search models suffer from lexica gap problems and are not fast enough to solve these problems. |
| Approach: | They build a dense retrieval based semantic search engine on scientific articles from Elsevier that generates high-quality pseudo training labels. |
| Outcome: | The proposed model significantly outperforms the currently deployed lexical search engine on the two test sets. |