| GRIT: Generative Role-filler Transformers for Document-level Event Entity Extraction | Aug 21, 2020 | DecoderRole-filler Entity Extraction | CodeCode Available | 1 |
| Inducing Language-Agnostic Multilingual Representations | Aug 20, 2020 | Cross-Lingual TransferSentence | CodeCode Available | 1 |
| Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos | Aug 19, 2020 | Moment RetrievalRetrieval | CodeCode Available | 1 |
| The Annotation Guideline of LST20 Corpus | Aug 12, 2020 | POSPOS Tagging | CodeCode Available | 1 |
| Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders | Aug 12, 2020 | Cross-Modal Information RetrievalCross-Modal Retrieval | CodeCode Available | 1 |
| Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversity | Aug 11, 2020 | DiversityMachine Translation | CodeCode Available | 1 |
| KR-BERT: A Small-Scale Korean-Specific Language Model | Aug 10, 2020 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach | Aug 10, 2020 | AttributeImage Captioning | CodeCode Available | 1 |
| Word Error Rate Estimation Without ASR Output: e-WER2 | Aug 8, 2020 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | CodeCode Available | 1 |
| Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards | Aug 6, 2020 | AttributeImage Captioning | CodeCode Available | 1 |
