Papers with classification errors
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. |