SOTA Results
Related Papers
Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition
AbstractKnowledge of a disease includes information of various aspects of the disease, such as signs and symptoms, diagnosis and treatment. This disease knowledge is critical for many health-related and biomedical …...
Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications
AbstractSentence-level Quality estimation (QE) of machine translation is traditionally formulated as a regression task, and the performance of QE models is typically measured by Pearson correlation with human labels. Recent …...
Solving SCAN Tasks with Data Augmentation and Input Embeddings
AbstractWe address the compositionality challenge presented by the SCAN benchmark. Using data augmentation and a modification of the standard seq2seq architecture with attention, we achieve SOTA results on all the …...
Text Detoxification using Large Pre-trained Neural Models
AbstractWe present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and …...
MatchPrompt: Prompt-based Open Relation Extraction with Semantic Consistency Guided Clustering
AbstractRelation clustering is a general approach for open relation extraction (OpenRE). Current methods have two major problems. One is that their good performance relies on large amounts of labeled and …...
Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning
AbstractRecent research shows synthetic data as a source of supervision helps pretrained language models (PLM) transfer learning to new target tasks/domains. However, this idea is less explored for spatial language. …...
Program Synthesis for Complex QA on Charts via Probabilistic Grammar Based Filtered Iterative Back-Translation
AbstractAnswering complex reasoning questions from chart images is a challenging problem requiring a combination of natural language understanding, fine-grained perception, and analytical reasoning. Current chart-based Question Answering (QA) approaches largely …...