# Weakly Supervised Learning

This is a text-to-audio grounding model capable of predicting the probability of specific sound events occurring in audio segments.

WSPAlign is a pre-trained model for word alignment based on large-scale weakly supervised span prediction, supporting word alignment tasks for multiple language pairs.

This model is a fine-tuned version of facebook/levit-192 on an unlabeled dataset, demonstrating excellent performance in precision, recall, F1 score, and accuracy.

TAPAS is a table-based question answering model that handles conversational QA tasks on tabular data through pre-training and fine-tuning.

A named entity recognition model fine-tuned on BioBERT, specializing in identifying epidemiological information in rare disease abstracts.

This model is a small version of TAPAS, which has undergone intermediate pre-training and fine-tuning on the SQA dataset. It is suitable for table question answering tasks in dialogue scenarios.

TAPAS is a Transformer-based table question answering model, pre-trained in a self-supervised manner on English Wikipedia table data and fine-tuned with supervision on the WikiSQL dataset.

A text summarization generation model fine-tuned on the distilbart-cnn-12-6 model, trained for 1000 steps with weakly supervised data

TAPAS is a BERT-like Transformer model designed for table-based question answering tasks. It is pre-trained in a self-supervised manner on English Wikipedia table corpora and fine-tuned on the WikiSQL dataset.

This model is the large version of TAPAS, fine-tuned for sequential question answering (SQA) tasks, suitable for table-related question answering scenarios.

The TAPAS mini model is a table question answering model that underwent intermediate pretraining and fine-tuning on the SQA dataset, utilizing relative position embedding technology.

This model is a small version of TAPAS, specifically fine-tuned on the WikiTable Questions dataset for table-based question answering tasks.

AraRoBERTa is a single-dialect Arabic language model trained at the national level, based on RoBERTa's foundational configuration.

A weakly supervised topic label generation model based on BART, solving topic labeling tasks through generation rather than selection

This model is a mini version based on the TAPAS architecture, specifically fine-tuned for the WikiTable Questions (WTQ) dataset for table question answering tasks.

TAPAS is a QA model for tabular data. This tiny version is fine-tuned on the SQA dataset, suitable for table-based QA tasks in conversational scenarios.