Papers with binary classification problem
Pointwise Paraphrase Appraisal is Potentially Problematic (2020.acl-srw)
Copied to clipboard
| Challenge: | prevailing methods for paraphrase identification models are binary classification problems . current methods do not provide consistent and robust performance on unseen samples and real world problems. |
| Approach: | They propose to use binary classification to evaluate paraphrase identification models . they propose to improve methods for fine-tuning BERT models by pairing two sentences as one sequence . |
| Outcome: | The proposed methods may fail on simple tasks like identifying pairs with two identical sentences. |
An Experimental Analysis on Evaluating Patent Citations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Graph Neural Networks (GNNs)-based methods can predict patent citations using only patent text. |
| Approach: | They propose to use Graph Neural Networks to predict citations for patents based on their semantic similarities to generate a semantic graph of patents. |
| Outcome: | The proposed methods produce 94% recall for patents with high citations and outperform baselines. |
Content-Based Conflict of Interest Detection on Wikipedia (L18-1)
Copied to clipboard
| Challenge: | Conflict-of-Interest (CoI) editing is a problem on Wikipedia that is highly subjective . a key feature of Wiki sites is to allow people from all over the world to add or modify articles anonymously and without consequence. |
| Approach: | They frame CoI detection as a binary classification problem and explore features for it . they find that stylometric features outperform other types of features and give an F-measure of 0.63 . |
| Outcome: | The proposed method outperforms other features and gives an F-measure of 0.63 . the proposed method is not certain that the set of non-CoI articles contains any CoI articles . |
Syntactically Aware Neural Architectures for Definition Extraction (N18-2)
Copied to clipboard
| Challenge: | Existing approaches to identify definitional knowledge in text corpora are based on Wikipedia-like definitions. |
| Approach: | They propose to combine Convolutional and Recurrent Neural Networks to train definitional knowledge in text corpora. |
| Outcome: | The proposed models can be applied to more noisy domain-specific corpora. |
Knowledge-Guided Paraphrase Identification (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for paraphrase identification (PI) are limited due to lack of professional knowledge. |
| Approach: | They propose to leverage Wikipedia knowledge to accurately identify paraphrases by mining outline knowledge of given sentences from Wikipedia. |
| Outcome: | The proposed framework outperforms state-of-the-art models on two public datasets: PARADE and clinicalSTS2019. |
Data Expansion Using WordNet-based Semantic Expansion and Word Disambiguation for Cyberbullying Detection (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to identify cyberbullying from text are limited due to the complexity of the content and the lack of labeled large-scale corpus. |
| Approach: | They propose a data augmentation-based approach that could enhance the automatic detection of cyberbullying in social media texts. |
| Outcome: | The proposed approach overcomes limitations of social media posts with word sense disambiguation and synonymy relation . results show that the proposed approach improves on the existing classifiers with and without data augmentation. |
Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities (2022.naacl-main)
Copied to clipboard
| Challenge: | Identifying related entities and events within and across documents is fundamental to natural language understanding. |
| Approach: | They propose an approach to entity and event coreference resolution using contrastive representation learning. |
| Outcome: | The proposed method achieves state-of-the-art results on key metrics on the ECB+ corpus and is competitive on others. |
Task-Aware Representation of Sentences for Generic Text Classification (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to text classification use a transformer architecture with a linear layer on top. |
| Approach: | They propose a transformer-based approach that outputs a class distribution for a given prediction problem. |
| Outcome: | The proposed model outperforms existing approaches on small training data and can learn to predict new classes even with no training examples. |
Argument Pair Extraction via Attention-guided Multi-Layer Multi-Cross Encoding (2021.acl-long)
Copied to clipboard
| Challenge: | Argument pair extraction (APE) is a research task for extracting arguments from two passages and identifying potential argument pairs. |
| Approach: | They propose a novel attention-guided multi-layer multi-cross encoding scheme that processes two passages with two individual sequence encoders and updates their representations using each other’s attention. |
| Outcome: | The proposed model significantly improves the performance over several alternatives. |
XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks for assessing distinct meanings of words are tied to sense inventories, restricting their usage to knowledge-based representation techniques. |
| Approach: | They propose a multilingual benchmark that models distinct meanings of words in English . they use a binary disambiguation task with gold standards in 12 new languages . |
| Outcome: | The proposed model can model distinct meanings of words in English even when no tagged instances are available for a target language. |
Developing a Dataset of Overridden Information in Wikipedia (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to detect information overridden by the Web are not accurate and require a user's perspective to make the decision. |
| Approach: | They propose a task to detect whether a reference sentence has overridden a target sentence by using sentence pairs from the difference between two versions of Wikipedia. |
| Outcome: | The proposed task is formalized as a binary classification problem to determine whether a reference sentence has overridden a target sentence. |
Deep One-Class Hate Speech Detection Model (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing approaches to hate speech detection neglect distinct attributes of hate speeches from other sentimental types such as “aggressive” and “racist”. |
| Approach: | They propose a one-class model where the detection classifier is trained with hate-class samples only. |
| Outcome: | The proposed model outperforms existing models with four benchmark datasets and shows that it performs better than existing models. |
LLMSegm: Surface-level Morphological Segmentation Using Large Language Model (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to morphological segmentation split word into its morphemes . LLMSegm is applicable in low-data settings and low-resourced languages . |
| Approach: | They propose a novel approach to surface-level morphological segmentation leveraging large language models. |
| Outcome: | The proposed method is applicable in low-data settings and low-resource languages. |
How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Jailbreak attacks, where harmful prompts bypass generative models’ built-in safety, raise serious concerns about model vulnerability. |
| Approach: | They propose to reframe the standard generation task as a binary classification problem to assess model refusal tendencies for both harmful and benign queries. |
| Outcome: | The proposed defenses improve model safety or optimize the trade-off between safety and helpfulness. |
MOSAIC: Multiple Observers Spotting AI Content (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made it easier for all to produce harmful, toxic, faked or forged content. |
| Approach: | They propose to use large language models to automatically discriminate from human-written texts by comparing their probability distributions over a document to see if they can detect forged or harmful content. |
| Outcome: | The proposed approach harnesses each model’s capabilities, leading to strong detection performance on a variety of domains. |