Revision bad7a4d72cd3dafc1276316ee33a11b681344126 authored by Jun Chen on 09 October 2020, 19:26:22 UTC, committed by Facebook GitHub Bot on 09 October 2020, 19:28:06 UTC
Summary: Add DoCNN in TextEncoder. The embedding matrix uses the one in pytext transformer. And support to customize `conv_filters` and `mlp_sizes` in yaml config. # Performance | concat_bert model with text encoder | test/ap | test/accuracy | | docnn+pytext | **0.8998** | **0.8407** | | docnn | 0.8930 | 0.8346 | | xlm_roberta_base | 0.8843 | 0.8336 | Reviewed By: apsdehal Differential Revision: D23933438 fbshipit-source-id: 1cda7920e737d3342a6abf0afa54ca26660496d3
1 parent 14c0e2f
| File | Mode | Size |
|---|---|---|
| .circleci | ||
| .github | ||
| docs | ||
| mmf | ||
| mmf_cli | ||
| projects | ||
| tests | ||
| tools | ||
| website | ||
| .editorconfig | -rw-r--r-- | 191 bytes |
| .flake8 | -rw-r--r-- | 187 bytes |
| .gitignore | -rw-r--r-- | 255 bytes |
| .pre-commit-config.yaml | -rw-r--r-- | 1.1 KB |
| LICENSE | -rw-r--r-- | 1.5 KB |
| MANIFEST.in | -rw-r--r-- | 130 bytes |
| NOTICES | -rw-r--r-- | 2.7 KB |
| README.md | -rw-r--r-- | 2.2 KB |
| pyproject.toml | -rw-r--r-- | 820 bytes |
| requirements.txt | -rw-r--r-- | 254 bytes |
| setup.py | -rw-r--r-- | 5.0 KB |
Computing file changes ...
