2 |
Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Joint Detection and Coreference Resolution of Entities and Events with Document-level Context Aggregation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
InfoSurgeon: Cross-Media Fine-grained Information Consistency Checking for Fake News Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Learning Shared Semantic Space for Speech-to-Text Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Fine-grained Information Extraction from Biomedical Literature based on Knowledge-enriched Abstract Meaning Representation ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Coreference by Appearance: Visually Grounded Event Coreference Resolution ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Learning speech embeddings for speaker adaptation and speech understanding
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Text Classification Using Label Names Only: A Language Model Self-Training Approach ...
|
|
|
|
Abstract:
Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Humans can perform classification without seeing any labeled examples but only based on a small set of words describing the categories to be classified. In this paper, we explore the potential of only using the label name of each class to train classification models on unlabeled data, without using any labeled documents. We use pre-trained neural language models both as general linguistic knowledge sources for category understanding and as representation learning models for document classification. Our method (1) associates semantically related words with the label names, (2) finds category-indicative words and trains the model to predict their implied categories, and (3) generalizes the model via self-training. We show that our model achieves around 90% accuracy on four benchmark datasets including topic and sentiment ... : EMNLP 2020. (Code: https://github.com/yumeng5/LOTClass) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.2010.07245 https://arxiv.org/abs/2010.07245
|
|
BASE
|
|
Hide details
|
|
17 |
COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Learning from Lexical Perturbations for Consistent Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|