Papers with classification errors

7 papers
The FEVER2.0 Shared Task (D19-66)

Copied to clipboard

Challenge: Existing deep neural models are becoming more complex and difficult to understand and characterize their behaviour.
Approach: They present the results of the second Fact Extraction and VERification (FEVER2.0) Shared Task.
Outcome: The proposed task was based on the second Fact Extraction and VERification (FEVER2.0) shared task.
Contextual Domain Classification with Temporal Representations (2021.naacl-industry)

Copied to clipboard

Challenge: Existing studies that incorporate context in SLU have focused on domains where context is limited to a few minutes.
Approach: They propose temporal representations that combine wall-clock second difference and turn order offset information to utilize both recent and distant context in a novel large-scale setup.
Outcome: The proposed model reduces 13.04% of classification errors compared to baseline . previous studies have focused on domains where context is limited to a few minutes .
BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews (2023.findings-acl)

Copied to clipboard

Challenge: Existing literature on Bangla Sentiment Analysis (SA) has limited data and cross-domain adaptability.
Approach: They present a large-scale dataset of Bangla book reviews with 158,065 samples . they employ a range of machine learning models to establish baselines including SVM, LSTM, and Bangla-BERT.
Outcome: The proposed model improves performance over models that rely on manual features.
An Algerian Corpus and an Annotation Platform for Opinion and Emotion Analysis (2020.lrec-1)

Copied to clipboard

Challenge: Currently, there are more than 4 billion Internet users worldwide . the number of social media users in Algeria has tripled over a year .
Approach: They propose a platform for crowdsourcing annotation of tweets at different levels of granularity.
Outcome: The proposed platform can be used to create the largest Algerian dialect subjectivity lexicon of about 9,000 entries.
Cross-Domain Classification of Moral Values (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods to identify moral values in text can be challenging for transferring knowledge between domains.
Approach: They compare a deep learning model with a domain-specific value classifier to find out whether it can transfer knowledge to new domains.
Outcome: The proposed model can generalize and transfer knowledge to novel domains, but introduce catastrophic forgetting.
Extracting Material Property Measurement Data from Scientific Articles (2021.emnlp-main)

Copied to clipboard

Challenge: a lack of large training datasets hampers machine learning-based prediction of material properties . relevant measurements and information exist only in unstructured formats such as the published literature .
Approach: They propose a framework for automatic property extraction using material solubility as the target property.
Outcome: The proposed framework extracts solubility data from scientific literature and compares it with other frameworks.
Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies fail to distinguish different classification errors with a standard cross-entropy classification loss and ignore the numbers in the fact description for predicting the term of penalty.
Approach: They propose to extract crime amounts from fact description and use them to learn distinguishable representations to exploit the numbers in the fact description for predicting the term of penalty.
Outcome: The proposed method achieves state-of-the-art results on real-world datasets and ablation studies demonstrate the effectiveness of each component.

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