Papers with FN

6 papers
Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification (2023.acl-industry)

Copied to clipboard

Challenge: Item categorization (IC) aims to classify a product into leaf nodes in a categorical taxonomy due to scarce supervision.
Approach: They propose to use K-positive contrastive loss (KCL) to address IC task’s long-tail issue by re-weighting positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K+1 as close as possible.
Outcome: The proposed method improves on the long-tail issue in the image classification task and when using text-based contrastive learning, it can be applied on the IC task.
LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners (2022.findings-naacl)

Copied to clipboard

Challenge: LiST is an efficient method for fine-tuning large pre-trained language models in few-shot learning settings.
Approach: They propose a method for efficient fine-tuning of large pre-trained language models in few-shot settings using self-training and meta-learning.
Outcome: The proposed method outperforms GPT-3 in-context learning by 33% on few-shot tasks.
Re2-DocRED: Revisiting Revisited-DocRED for Joint Entity and Relation Extraction (2026.eacl-long)

Copied to clipboard

Challenge: Document-level Joint Entity and Relation Extraction benchmarks such as DocRED, Re-DocRED, and DocGNRE suffer from pervasive False Negatives (FN)
Approach: They propose a training-free annotation pipeline that leverages user-specifiable reasoning, enriched inverse/co-occurring relation schemas, and novel entity-level constraints to address FN gaps.
Outcome: The proposed pipeline improves on REDFM Mandarin dataset and shows that model recall scores drop on revised splits, whereas the training set mitigates this.
A Crowdsourced Frame Disambiguation Corpus with Ambiguity (N19-1)

Copied to clipboard

Challenge: Using crowdsourcing, we have found that inter-annotator disagreement is at least partly caused by ambiguity inherent to the text and frames.
Approach: They propose a crowdsourcing approach to capture inter-annotator disagreement by a list of frames with disagreement-based scores that express the confidence with which each frame applies to the word.
Outcome: The proposed approach captures disagreement between the annotations of 1,000 word-sentence pairs and scores on the likelihood that each frame applies to the word.
H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction (2021.findings-acl)

Copied to clipboard

Challenge: Existing work on distant supervision denoising introduces false-positive (FP) and falsenegative (FN) training instances to the generated datasets.
Approach: They propose a hierarchical false-negative denoising framework for distant supervision relation extraction that denoises false-positive and false- negative training instances.
Outcome: The proposed framework can revise FN instances correctly and maintain high F1 scores even when 50% of instances have been turned into negatives.
Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for relation extraction ignore the incompleteness of existing knowledge bases . current methods are too weak and cause noises when training and testing are not based on training data.
Approach: They propose a method to automatically align unstructured text with relation instances in a knowledge base . they use heuristics to leverage the memory mechanism of deep neural networks to find out possible FN samples .
Outcome: Experiments on two wildly-used benchmark datasets show the effectiveness of the proposed method.

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