conftrace_
← Architectures
Deep Learning › Architectures ›

Transformers

10,397 papers

Papers per year

6
925
1792
'15
'20
'25

Papers

Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models IJCNLP 2021
Are Pretrained Convolutions Better than Pretrained Transformers? IJCNLP 2021
Continuous Language Generative Flow IJCNLP 2021
Mask-Align: Self-Supervised Neural Word Alignment IJCNLP 2021
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling IJCNLP 2021
Syntax-Enhanced Pre-trained Model IJCNLP 2021
Shortformer: Better Language Modeling using Shorter Inputs IJCNLP 2021
Math Word Problem Solving with Explicit Numerical Values IJCNLP 2021
What is Your Article Based On? Inferring Fine-grained Provenance IJCNLP 2021
PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check IJCNLP 2021
BASS: Boosting Abstractive Summarization with Unified Semantic Graph IJCNLP 2021
Controllable Open-ended Question Generation with A New Question Type Ontology IJCNLP 2021
Improving Paraphrase Detection with the Adversarial Paraphrasing Task IJCNLP 2021
StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling IJCNLP 2021
Discriminative Reranking for Neural Machine Translation IJCNLP 2021
N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses IJCNLP 2021
The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models IJCNLP 2021
A Span-based Dynamic Local Attention Model for Sequential Sentence Classification IJCNLP 2021
A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering IJCNLP 2021
Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation IJCNLP 2021
Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation IJCNLP 2021
On Orthogonality Constraints for Transformers IJCNLP 2021
Exploring Listwise Evidence Reasoning with T5 for Fact Verification IJCNLP 2021
Learning to Generate Task-Specific Adapters from Task Description IJCNLP 2021
Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling IJCNLP 2021