Papers with label prediction

11 papers
Modelling Uncertainty in Collaborative Document Quality Assessment (D19-55)

Copied to clipboard

Challenge: Existing work on document quality assessment relies on predicting the quality of a document relative to a putative gold standard, without paying attention to the subjectivity of this task.
Approach: They propose to use Gaussian processes and random forests to measure the uncertainty in document quality predictions.
Outcome: The proposed methods can predict the quality of Wikipedia articles while providing an estimate of uncertainty when there is inconsistency in the quality labels from the contributors.
Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition (2020.acl-srw)

Copied to clipboard

Challenge: In general, the labels used in sequence labeling consist of different types of elements.
Approach: They propose to integrate label component information as embeddings into sequence labeling models.
Outcome: The proposed method improves on English and Japanese fine-grained named entity recognition on low-frequency labels.
In-context Contrastive Learning for Event Causality Identification (2024.emnlp-main)

Copied to clipboard

Challenge: Recent prompt learning-based approaches have shown promising improvements on the ECI task . however, they are subject to the delicate design of multiple prompts and positive correlations between the main task and derivate tasks.
Approach: They propose an event causality identification model that uses contrastive learning to enhance both positive and negative demonstrations.
Outcome: The proposed model improves on the event-related causality identification task . it uses contrastive learning to enhance both positive and negative demonstrations .
Exploring Listwise Evidence Reasoning with T5 for Fact Verification (2021.acl-short)

Copied to clipboard

Challenge: Existing methods for fact verification use pretrained sequence-to-sequence transformers for sentence selection and label prediction.
Approach: They propose a framework for fact verification that leverages pretrained sequence-to-sequence transformer models for sentence selection and label prediction.
Outcome: The proposed framework scores higher than the second place approach on the blind test set . the proposed framework can be useful for a broader range of NLP tasks, the authors say .
Compositional Zero-Shot Domain Transfer with Text-to-Text Models (2023.tacl-1)

Copied to clipboard

Challenge: Existing approaches to zero-shot domain transfer are limited by domain gap and lack of in-domain labels.
Approach: They propose a compositional transfer learning framework (DoT51) that learns domain knowledge and task knowledge in a multi-task manner without access to in-domain labels.
Outcome: The proposed framework outperforms the current state-of-the-art in zero-shot domain transfer by over 7 absolute points in accuracy on RadNLI.
Long-tailed Extreme Multi-label Text Classification by the Retrieval of Generated Pseudo Label Descriptions (2023.findings-eacl)

Copied to clipboard

Challenge: Extreme Multi-label text classification (XMTC) is a tough challenge due to the sheer size of the label spaces and the severe data scarcity problem associated with the long tail of rare labels in highly skewed distributions.
Approach: They propose to use a trained bag-of-words classifier to generate pseudo label descriptions from a training bag- of-word classifier.
Outcome: The proposed approach outperforms the existing models in the tail label prediction problem and achieves state-of-the-art (SOTA) performance on XMTC benchmark datasets.
NormNet: Normalize Noun Phrases for More Robust NLP (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to debunk false features in deep NLP models are inadequate . previous work suggests that models learn spurious features instead of the true signals of the task .
Approach: They propose a normalization strategy to eliminate false features caused by the textual surfaces of noun phrases.
Outcome: The proposed normalization strategy eliminates false features caused by the textual surfaces of noun phrases.
Learning to Maximize Mutual Information for Chain-of-Thought Distillation (2024.findings-acl)

Copied to clipboard

Challenge: Knowledge distillation is a technique of transferring knowledge from large, complex models to smaller ones.
Approach: They propose a method utilizing chain-of-thought distillation to transfer knowledge from large, complex models to smaller ones by maximizing mutual information of the representation features of the two tasks.
Outcome: The proposed method outperforms the state-of-the-art knowledge distillation method on four datasets.
What Part of the Neural Network Does This? Understanding LSTMs by Measuring and Dissecting Neurons (D19-1)

Copied to clipboard

Challenge: Biological neural systems consist of a huge number of neurons, and can react to the environment in complicated ways.
Approach: They propose a metric to quantify the sensitivity of neurons to each label and conduct experiments to prove it.
Outcome: The proposed metric is based on a set of experiments that show that dropping an arbitrary neuron significantly degrades the accuracy of the model.
Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for ECPE fail to model specific features and interactive features in between, or suffer from inconsistency of label prediction.
Approach: They propose to align ECPE with a feature-task alignment mechanism to model emotion-&cause-specific features and the shared interactive feature.
Outcome: The proposed model outperforms existing systems on all ECA subtasks.
BoundRL: Efficient Token-level Structured Text Segmentation through Reinforced Boundary Generation (2026.findings-acl)

Copied to clipboard

Challenge: Structured texts often contain elements beyond plain language, such as code snippets, which conventional sentence-level segmentation methods cannot handle effectively.
Approach: They propose a token-level approach that performs efficient token-based text segmentation and label prediction for long structured texts.
Outcome: The proposed approach outperforms existing models on short-shot prompts and SFT and standard RLVR models on complex LLM prompts.

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