Challenge: Exaggerations in health news can have tremendous adverse effects on the lifestyle of the common masses who feed themselves mostly on such news instead of the source scientific publication.
Approach: They propose a three-step approach that extracts relation phrases from a scientific paper and then classifies the strength of the relationship phrase extracted.
Outcome: The proposed approach outperforms baseline models that compare state-of-the-art embedding of the statement pairs through a binary classifier or recast the problem as a textual entailment task.

Similar Papers

Measuring Correlation-to-Causation Exaggeration in Press Releases (2020.coling-main)

Copied to clipboard

Challenge: Recent studies have found that press releases are a major source of exaggeration in science communication, which is later spread to mainstream media.
Approach: They propose an NLP approach to identify exaggerated causal claims in health press releases that report on observational studies.
Outcome: The proposed approach can identify causal claims in press releases that report on observational studies.
Understanding Fine-grained Distortions in Reports of Scientific Findings (2024.findings-acl)

Copied to clipboard

Challenge: a fine-grained understanding of how scientific findings are reported is crucial, says a new study . a recent study found that tweets distort scientific findings more often than news reports .
Approach: They propose to annotate 1,600 scientific findings from academic papers paired with corresponding tweets . they also establish baselines for automatically detecting these characteristics .
Outcome: The proposed method outperforms few-shot prompting in detecting distortions in unpaired data.
An Interactive Framework for Profiling News Media Sources (2024.naacl-long)

Copied to clipboard

Challenge: Existing tools for detecting fake news are difficult for automated systems . e.g., we focus on the source level, and ask: Is this source factual or politically biased?
Approach: They propose an interactive framework for news media profiling that uses graphs and pre-trained large language models to characterize social context on social media.
Outcome: The proposed framework can detect fake and biased news media with as little as 5 human interactions . it can scale better, as often sources publish have same factuality/political bias as source .
Identifying Exaggerated Language (2020.emnlp-main)

Copied to clipboard

Challenge: Recent studies on metaphor and metonymy have focused on hyperbole, but it is a relatively understudied phenomenon in the figurative language processing community.
Approach: They propose to use hyperbole detection to determine whether a sentence is hyperbolic . they also perform statistical and manual analyses of the corpus and address the automatic hyperbola detection task.
Outcome: The proposed dataset consists of 709 hyperbolic sentences with a non-hyperbolic version created by paraphrasing its hyperbolical counterpart.
Authorless Topic Models: Biasing Models Away from Known Structure (C18-1)

Copied to clipboard

Challenge: a recent study shows that topic models that highlight differences in authors are often not accurate . authors show that subsampling words that are highly correlated with metadata can reduce topic-metadata correlation .
Approach: They propose three metrics for identifying topics that are highly correlated with metadata . they find that subsampling words causes topic-metadata correlation, improve topic stability . authors propose to use topic models to infer word distributions that correspond to recognizable themes .
Outcome: The proposed model can predict which words cause the phenomenon and improve topic stability and quality.
Predicting Factuality of Reporting and Bias of News Media Sources (D18-1)

Copied to clipboard

Challenge: a new study examines the factuality of news media and its biases . social media has democratized content creation and spread information online .
Approach: They propose to characterize entire news media to predict factuality and bias . they experiment with news websites and a set of features derived from their content .
Outcome: The proposed model shows that the features of news websites perform better than baseline . the results show that the feature types are important for fact-checking systems .
Mind Your Bias: A Critical Review of Bias Detection Methods for Contextual Language Models (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for detection of biases in contextual language models are inconsistent and inconclusive.
Approach: They propose to use word embedding association test to detect biases in contextual language models to compare them with other methods.
Outcome: The proposed methods are inconsistent and inconclusive for language models with word embeddings.
Perturbation Sensitivity Analysis to Detect Unintended Model Biases (D19-1)

Copied to clipboard

Challenge: Recent research shows that data-driven NLP models may inadvertently capture, reflect and sometimes amplify various social biases present in the language data they are trained on.
Approach: They propose a generic evaluation framework that detects unintended model biases related to named entities and requires no new annotations or corpora.
Outcome: The proposed framework detects unintended model biases related to named entities and requires no new annotations or corpora.
A Computational Exploration of Exaggeration (D18-1)

Copied to clipboard

Challenge: a new computational approach to exaggeration detection is needed for non-literal phenomena . a corpus of overstatements (or hyperboles) is used to detect exaggrements .
Approach: They propose a computational approach to detect exaggerated sentences using crowdsourcing data . they build a corpus containing overstatements and then evaluate models trained on HYPO .
Outcome: The proposed approach can detect exaggerated sentences using a crowdsourced dataset.
Do Neural Language Models Overcome Reporting Bias? (2020.coling-main)

Copied to clipboard

Challenge: Recent studies show that pre-trained language models can overcome reporting bias by estimating the plausibility of rare but unspoken facts.
Approach: They revisit the experiments conducted by Gordon and Van Durme (2013) . they find that pre-trained language models overestimate the very rare .
Outcome: The proposed approach overestimates the rare at the expense of the rare, while minimizing reporting bias.

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