Papers by Slobodan Vucetic
Regular Expression Guided Entity Mention Mining from Noisy Web Data (D18-1)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a subtask of the broader problem of Information Extraction (IE) from text. |
| Approach: | They propose a framework that uses Regular Expressions to identify entities from web data . they combine expressive power of REs with ability of deep learning to learn from large data a human expert is asked to label a small set of documents . |
| Outcome: | The proposed framework achieves impressive accuracy while requiring modest human effort. |
Spatial Aggregation Facilitates Discovery of Spatial Topics (P19-1)
Copied to clipboard
| Challenge: | a recent paper shows that topic discovery is a powerful tool for describing pertinent themes in a document corpus. |
| Approach: | They propose to use a traditional topic discovery algorithm to find spatially distinct topics by spatial aggregation. |
| Outcome: | The proposed method can efficiently discover spatially distinct topics from large documents. |
X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on few-shot and zero-shot learning, but label occurrences vary widely . authors propose a new classification challenge that can be used to manage labels across the full frequency spectrum . |
| Approach: | They propose a new classification challenge that allows for label co-occurrences without predefined limits. |
| Outcome: | The proposed system can handle freq-shot, few-shot and zero-shot labels without limits. |
Two-Pronged Human Evaluation of ChatGPT Self-Correction in Radiology Report Simplification (2024.findings-acl)
Copied to clipboard
| Challenge: | Radiology reports are highly technical documents aimed primarily at doctor-doctor communication. |
| Approach: | They propose a new evaluation protocol that employs radiologists and laypeople to produce high-quality simplifications. |
| Outcome: | The proposed evaluation protocol combines radiologists and laypeople to produce high-quality simplifications. |
Data Augmentation for Radiology Report Simplification (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to improve radiology reports are limited due to the high cost of manual simplification. |
| Approach: | They propose a data augmentation approach to generate simplifications of unlabeled radiology sentences using a pre-trained language model and paraphrasing of labeled radiologists sentences. |
| Outcome: | The proposed model generates simplifications of unlabeled radiology sentences and paraphrases labeled radiologists sentences. |
Improving Word Embeddings through Iterative Refinement of Word- and Character-level Models (2020.coling-main)
Copied to clipboard
| Challenge: | Embedding of rare and out-of-vocabulary words is an important open NLP problem . standard embedding models are not useful for recommending jobs to users with rare or unseen words . |
| Approach: | They propose to train a character-level neural network to reproduce word embeddings . they then use the model to assign vectors to any input string, including rare words . |
| Outcome: | The proposed method outperforms existing methods on word similarity data sets and can be applied to job title normalization in the e-recruitment domain. |