conftrace_
← Architectures
Deep Learning › Architectures ›

Transformers

9,294 papers

Papers per year

Papers

PASS: Perturb-and-Select Summarizer for Product Reviews IJCNLP 2021
Self-Supervised Multimodal Opinion Summarization IJCNLP 2021
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification IJCNLP 2021
Cascaded Head-colliding Attention IJCNLP 2021
Unsupervised Out-of-Domain Detection via Pre-trained Transformers IJCNLP 2021
More Identifiable yet Equally Performant Transformers for Text Classification IJCNLP 2021
Improving Zero-Shot Translation by Disentangling Positional Information IJCNLP 2021
Attention Calibration for Transformer in Neural Machine Translation IJCNLP 2021
Select, Extract and Generate: Neural Keyphrase Generation with Layer-wise Coverage Attention IJCNLP 2021
MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition IJCNLP 2021
Improving Formality Style Transfer with Context-Aware Rule Injection IJCNLP 2021
Glancing Transformer for Non-Autoregressive Neural Machine Translation IJCNLP 2021
Optimizing Deeper Transformers on Small Datasets IJCNLP 2021
EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets IJCNLP 2021
Towards Robustness of Text-to-SQL Models against Synonym Substitution IJCNLP 2021
Self-Guided Contrastive Learning for BERT Sentence Representations IJCNLP 2021
LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding IJCNLP 2021
Lightweight Cross-Lingual Sentence Representation Learning IJCNLP 2021
ERNIE-Doc: A Retrospective Long-Document Modeling Transformer IJCNLP 2021
Fast and Accurate Neural Machine Translation with Translation Memory IJCNLP 2021
G-Transformer for Document-Level Machine Translation IJCNLP 2021
Prevent the Language Model from being Overconfident in Neural Machine Translation IJCNLP 2021
Self-Attention Networks Can Process Bounded Hierarchical Languages IJCNLP 2021
H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences IJCNLP 2021
Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation IJCNLP 2021