Papers by Slobodan Vucetic

6 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations