facebookresearch/TaBERT
This repository contains source code for the TaBERT model, a pre-trained language model for learning joint representations of natural language utterances and (semi-)structured tables for semantic parsing. TaBERT is pre-trained on a massive corpus of 26M Web tables and their associated natural language context, and could be used as a drop-in replacement of a semantic parsers original encoder to compute representations for utterances and table schemas (columns).
PythonNOASSERTION
Issues
- 0
- 3
- 3
- 2
RuntimeError: invalid argument 2: non-empty vector or matrix expected at /tmp/pip-req-build-4baxydiv/aten/src/THCUNN/generic/ClassNLLCriterion.cu:31
#27 opened by Deryuu - 2
- 0
Puzzling line of "attention_mask = (1.0 - attention_mask) * -10000.0" in the vertical_transform function
#26 opened by superctj - 0
- 3
TaBERT wit MAPO
#22 opened by soumikgith - 1
Notebook example
#15 opened by bpquestion - 2
- 1
Content Snapshot Code Missing
#23 opened by waytehsu - 1
404 Not Found Error on "extract_wiki_tables.sh"
#24 opened by canqin001 - 2
- 0
Problem of content snapshot generating.
#21 opened by YaooXu - 2
- 5
Loading large tabert_large_k3 giving span_based_prediction.prediction.decoder.bias error
#4 opened by monk1337 - 1
Minimal working example for Question answering on dataset using pre-trained model?
#10 opened by monk1337 - 0
- 0
Running into GPU out-of-memory issue during pretraining. Any suggestions to reduce GPU memory usage?
#17 opened by sythello - 1
Any plans to release the 26M Web tables?
#12 opened by sksq96 - 7
Preparing training data
#1 opened by psorianom - 0
Serving the model/doing inference
#13 opened by niviksha - 1
Load a pretrained model giving error
#11 opened by Vincentchhsu - 0
Prediction on large tables
#9 opened by Sharathmk99 - 0
- 2
- 0