21 |
Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
22 |
Extend, donÕt rebuild: Phrasing conditional graph modification as autoregressive sequence labelling ...
|
|
|
|
BASE
|
|
Show details
|
|
23 |
Treasures Outside Contexts: Improving Event Detection via Global Statistics ...
|
|
|
|
BASE
|
|
Show details
|
|
24 |
Cost-effective End-to-end Information Extraction for Semi-structured Document Images ...
|
|
|
|
BASE
|
|
Show details
|
|
25 |
Monitoring geometrical properties of word embeddings for detecting the emergence of new topics. ...
|
|
|
|
BASE
|
|
Show details
|
|
26 |
Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data ...
|
|
|
|
BASE
|
|
Show details
|
|
27 |
Robust Retrieval Augmented Generation for Zero-shot Slot Filling ...
|
|
|
|
BASE
|
|
Show details
|
|
28 |
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
30 |
Document-level Entity-based Extraction as Template Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
31 |
TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware Network ...
|
|
|
|
BASE
|
|
Show details
|
|
32 |
Synchronous Dual Network with Cross-Type Attention for Joint Entity and Relation Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
33 |
Data Augmentation for Cross-Domain Named Entity Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
34 |
Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
35 |
Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
36 |
Active Learning by Acquiring Contrastive Examples ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.51/ Abstract: Common acquisition functions for active learning use either uncertainty or diversity sampling, aiming to select difficult and diverse data points from the pool of unlabeled data, respectively. In this work, leveraging the best of both worlds, we propose an acquisition function that opts for selecting contrastive examples, i.e. data points that are similar in the model feature space and yet the model outputs maximally different predictive likelihoods. We compare our approach, CAL (Contrastive Active Learning), with a diverse set of acquisition functions in four natural language understanding tasks and seven datasets. Our experiments show that CAL performs consistently better or equal than the best performing baseline across all tasks, on both in-domain and out-of-domain data. We also conduct an extensive ablation study of our method and we further analyze all actively acquired datasets showing that CAL achieves a better trade-off ...
|
|
Keyword:
Computational Linguistics; Information Extraction; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
|
|
URL: https://underline.io/lecture/37821-active-learning-by-acquiring-contrastive-examples https://dx.doi.org/10.48448/fh95-3822
|
|
BASE
|
|
Hide details
|
|
38 |
Incorporating medical knowledge in BERT for clinical relation extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
39 |
Crosslingual Transfer Learning for Relation and Event Extraction via Word Category and Class Alignments ...
|
|
|
|
BASE
|
|
Show details
|
|
40 |
ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|