Downloads · 30 days
35
1% of all-time downloads
table-question-answering-tapas
Meena/table-question-answering-tapas
table-question-answering-tapas is a table question answering model from Meena. Use it for the table question answering task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
TAPAS, the model learns an inner representation of the English language used in tables and associated texts, which can then be used to extract features useful for downstream tasks such as answering questions about a t…
All-time downloads
3.7K
Public
Repo size
886 MB
Likes
9
Public
Repo makeup
Click a slice to open those files.
.bin443 MB · 100%
At a glance
- Task
- Table Question Answering
- Library
- transformers
- License
- apache-2.0
- Model type
- tapas
- Access
- Public
- Created
- Apr 25, 2022
- Updated
- Apr 26, 2022
- SHA
- d7a30699
Try a prompt
Datasets
Model card
From the Hugging Face model README
TABLE QUESTION ANSWERING
TAPAS model
TAPAS, the model learns an inner representation of the English language used in tables and associated texts, which can then be used to extract features useful for downstream tasks such as answering questions about a table, or determining whether a sentence is entailed or refuted by the contents of a table.
Model description
- It is a BERT-based model specifically designed (and pre-trained) for answering questions about tabular data
- TAPAS uses relative position embeddings and has 7 token types that encode tabular structure.
- It is pre-trained on the masked language modeling (MLM) objective on a large dataset comprising millions of tables from English Wikipedia and corresponding texts.
The model has been fine-tuned on several datasets
- SQA (Sequential Question Answering by Microsoft)
- WTQ (Wiki Table Questions by Stanford University)
- WikiSQL (by Salesforce).
Limitations
Unable to deal with large input files
- Task
- Table Question Answering
- Library
- transformers
- Type
- tapas
- License
- apache-2.0
- Languages
- en
- Created
- Apr 25, 2022
- Updated
- Apr 26, 2022