Контрастты шығын
Related Papers
Multimodal and Multi-view Models for Emotion Recognition
AbstractStudies on emotion recognition (ER) show that combining lexical and acoustic information results in more robust and accurate models. The majority of the studies focus on settings where both modalities …...
Contrastive Self-Supervised Learning for Commonsense Reasoning
AbstractWe propose a self-supervised method to solve Pronoun Disambiguation and Winograd Schema Challenge problems. Our approach exploits the characteristic structure of training corpora related to so-called “trigger” words, which are …...
Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack
AbstractZero-shot slot filling has widely arisen to cope with data scarcity in target domains. However, previous approaches often ignore constraints between slot value representation and related slot description representation in …...
Pre-training Entity Relation Encoder with Intra-span and Inter-span Information
AbstractIn this paper, we integrate span-related information into pre-trained encoder for entity relation extraction task. Instead of using general-purpose sentence encoder (e.g., existing universal pre-trained models), we introduce a span …...
Contrastive Fine-tuning Improves Robustness for Neural Rankers
The performance of state-of-the-art neural rankers can deteriorate substantially when ex- posed to noisy inputs or applied to a new domain. In this paper, we present a novel method for …...
Fine-grained Factual Consistency Assessment for Abstractive Summarization Models
AbstractFactual inconsistencies existed in the output of abstractive summarization models with original documents are frequently presented. Fact consistency assessment requires the reasoning capability to find subtle clues to identify whether …...
Understanding Hard Negatives in Noise Contrastive Estimation
AbstractThe choice of negative examples is important in noise contrastive estimation. Recent works find that hard negatives—highest-scoring incorrect examples under the model—are effective in practice, but they are used without …...
A Localized Geometric Method to Match Knowledge in Low-dimensional Hyperbolic Space
AbstractMatching equivalent entities across Knowledge graphs is a pivotal step for knowledge fusion. Previous approaches usually study the problem in Euclidean space. However, recent works have shown that hyperbolic space …...
Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring Tasks
AbstractThe use of contrastive loss for representation learning has become prominent in computer vision, and it is now getting attention in Natural Language Processing (NLP).Here, we explore the idea of …...
New Intent Discovery with Pre-training and Contrastive Learning
AbstractNew intent discovery aims to uncover novel intent categories from user utterances to expand the set of supported intent classes. It is a critical task for the development and service …...
So Different Yet So Alike! Constrained Unsupervised Text Style Transfer
AbstractAutomatic transfer of text between domains has become popular in recent times. One of its aims is to preserve the semantic content while adapting to the target domain. However, it …...
Improving Unsupervised Out-of-domain detection through Pseudo Labeling and Learning
AbstractUnsupervised out-of-domain (OOD) detection is a task aimed at discriminating whether given samples are from the in-domain or not, without the categorical labels of in-domain instances. Unlike supervised OOD, as …...
Leveraging Task Dependency and Contrastive Learning for Case Outcome Classification on European Court of Human Rights Cases
AbstractWe report on an experiment in case outcome classification on European Court of Human Rights cases where our model first learns to identify the convention articles allegedly violated by the …...
MarsEclipse at SemEval-2023 Task 3: Multi-lingual and Multi-label Framing Detection with Contrastive Learning
AbstractThis paper describes our system for SemEval-2023 Task 3 Subtask 2 on Framing Detection. We used a multi-label contrastive loss for fine-tuning large pre-trained language models in a multi-lingual setting, …...