| MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System | Nov 17, 2021 | Sentence | —Unverified | 0 |
| High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics | Nov 17, 2021 | Machine TranslationSentence | —Unverified | 0 |
| High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency | Nov 17, 2021 | CPUDecoder | —Unverified | 0 |
| DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation | Nov 17, 2021 | DiversityImage Generation | —Unverified | 0 |
| Sentence-Level Discourse Parsing as Text-to-Text Generation | Nov 16, 2021 | Discourse ParsingDiscourse Segmentation | —Unverified | 0 |
| Effective Unsupervised Constrained Text Generation based on Perturbed Masking | Nov 16, 2021 | PositionSentence | —Unverified | 0 |
| Are All the Datasets in Benchmark Necessary? A Pilot Study of Dataset Evaluation for Text Classification | Nov 16, 2021 | AllSentence | CodeCode Available | 0 |
| Sentence-level Privacy for Document Embeddings | Nov 16, 2021 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Improving Neural Models for Radiology Report Retrieval with Lexicon-based Automated Annotation | Nov 16, 2021 | Information RetrievalRetrieval | —Unverified | 0 |
| RoMe: A Robust Metric for Evaluating Natural Language Generation | Nov 16, 2021 | Natural Language UnderstandingSemantic Similarity | —Unverified | 0 |
