Papers by Isabel Cachola
Evaluating the Evaluators: Are readability metrics good measures of readability? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Plain language summarization (PLS) aims to distill complex documents into accessible summaries for non-expert audiences. |
| Approach: | They conduct a thorough survey of literature on plain language summarization (PLS) and find that traditional readability metrics are not compared to human judgments. |
| Outcome: | The proposed language models better capture deeper measures of readability, with the best-performing model achieving a Pearson correlation of 0.56 with human judgments. |
Knowledge-Centric Templatic Views of Documents (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work on document generation has tackled the creation of each separate format as a different task, leading to fragmented learning processes, redundancy in models and methods, and disjointed evaluation. |
| Approach: | They propose a method that unifies the generation and evaluation of templatic views of documents in multiple formats. |
| Outcome: | The proposed method improves performance for heterogeneous downstream applications while reducing the need for task specific evaluation metrics. |
Why Swear? Analyzing and Inferring the Intentions of Vulgar Expressions (D18-1)
Copied to clipboard
| Challenge: | Vulgar words are employed in language use for several different functions, including expressing aggression, signaling group identity or the informality of the communication. |
| Approach: | They present a dataset of 7,800 tweets with six categories of vulgarity in which all instances of vulgar words are annotated with one of the six categories. |
| Outcome: | The proposed model can predict the category of a vulgar word based on the immediate context it appears in with 67.4 macro F1 across six classes. |
Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats (2025.acl-long)
Copied to clipboard
| Challenge: | Dog whistles are coded expressions with dual meanings that slip by content moderation filters . a new study finds that state-of-the-art systems fail to identify novel dog whistles . |
| Approach: | They propose a task to find novel dog whistles in massive social media corpora . they use a strong baseline system that combines vector databases and Large Language Models to identify new dog whistle. |
| Outcome: | The proposed system fails to identify dog whistles across three social media cases . it combines vector databases and Large Language Models to efficiently and effectively identify new dog whistle expressions. |
TLDR: Extreme Summarization of Scientific Documents (2020.findings-emnlp)
Copied to clipboard
| Challenge: | TLDR generation requires expert background knowledge and understanding of complex domain-specific language. |
| Approach: | They propose a learning strategy that exploits titles as an auxiliary training signal. |
| Outcome: | The proposed method improves upon strong baselines under both automated metrics and human evaluations. |
Expressively vulgar: The socio-dynamics of vulgarity and its effects on sentiment analysis in social media (C18-1)
Copied to clipboard
| Challenge: | Vulgarity is a common linguistic expression and is used to perform several linguistic functions. |
| Approach: | They analyze vulgarity using tweets from users with known demographics and sentiment ratings for vulgar tweets to study sentiment analysis performance. |
| Outcome: | The proposed model can boost sentiment analysis performance by analyzing vulgar tweets and tweet sentiment ratings. |
Explaining Relationships Between Scientific Documents (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to explain relationships between scientific documents using natural language text can be useful for research efficiency. |
| Approach: | They propose a task of explaining relationships between scientific documents using natural language text. |
| Outcome: | The proposed models can be automated and humanely evaluated. |