Papers by Gerardo Ocampo Diaz
Measuring Cross-Text Cohesion for Segmentation Similarity Scoring (2024.lrec-main)
Copied to clipboard
| Challenge: | a new segmentation similarity metric is being developed for text segmentation . current metrics are content-agnostic and do not provide fine-grained scoring . |
| Approach: | They propose a word-embedding-based metric of cross-textual cohesion based on the formal linguistic definition of cohetion and incorporate it into a new segmentation similarity metric, SED. |
| Outcome: | The proposed metric provides fine-grained segmentation similarity scoring for 3 basic errors, avoiding limitations of traditional metrics. |
Aspect-Based Sentiment Analysis as Fine-Grained Opinion Mining (2020.lrec-1)
Copied to clipboard
| Challenge: | a large body of research has been done on aspect-based sentiment analysis (ABSA) for almost two decades . aspect-Based sentiment analysis is a task that extracts sentiment/opinions from text in terms of targets . |
| Approach: | They propose a meaning-preserving annotation scheme for aspect-based sentiment analysis . they then apply it to two popular ABSA datasets to examine their results . |
| Outcome: | The proposed approach improves the state of aspect-based sentiment analysis (ABSA) by preserving the meaning of the sentiment. |
Modeling and Prediction of Online Product Review Helpfulness: A Survey (P18-1)
Copied to clipboard
| Challenge: | review helpfulness modeling is a task that studies the mechanisms that affect review helpfuliness and attempts to accurately predict it. |
| Approach: | This paper provides an overview of the most relevant work in helpfulness prediction . it discusses the insights gained from said work and provides guidelines for future research . |
| Outcome: | This paper summarizes the most relevant work in helpfulness prediction and understanding in the past decade . it outlines the insights gained from the results and provides guidelines for future research . |