https://github.com/saiful9379/semantics-textual-similarity
The semantics textual similarity means textual similar between two sentence such as i am a good boy and i am not a bad boy those two sentence are same meaning. so i try to find out those sentences are same meaning or not. i use public open souces data that have three class category that are neutral,contradiction and entailment.
https://github.com/saiful9379/semantics-textual-similarity
tensorflow
Last synced: 3 months ago
JSON representation
The semantics textual similarity means textual similar between two sentence such as i am a good boy and i am not a bad boy those two sentence are same meaning. so i try to find out those sentences are same meaning or not. i use public open souces data that have three class category that are neutral,contradiction and entailment.
- Host: GitHub
- URL: https://github.com/saiful9379/semantics-textual-similarity
- Owner: saiful9379
- Created: 2020-02-02T18:01:44.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2020-02-03T13:52:48.000Z (over 6 years ago)
- Last Synced: 2025-12-30T08:57:21.604Z (6 months ago)
- Topics: tensorflow
- Language: Python
- Homepage:
- Size: 427 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Semantics-Textual-Similarity
The semantics textual similarity means textual similar between two sentence such as ``` i am a good boy``` and ``` i am not a bad boy``` those two sentence are same meaning. so i try to find out those sentences are same meaning or not. i use public open souces data that have three class category that are neutral,contradiction and entailment.
# Requirements
- python 2.7
- tensorflow 1.5
# Data format
the train and test sets require a tab-separated format. Each line in the train (or test) file corresponds to an instance, and it should be arranged as
label sentence#1 sentence#2 instanceID
For more details about the data format, you can download the SNLI and the Quora Question Pair datasets.
# Training
```
python train.py --config_path configs/snli.sample.config
```
# Testing
```
python src/Decoder.py --in_path data/snli/dev.tsv --word_vec_path data/snli/wordvec.txt --out_path result.txt --model_prefix logs/SentenceMatch.snli
```
Test Video [link](https://www.linkedin.com/posts/saiful-islam-907128ba_finding-semantics-textual-similarity-between-activity-6629800835121537024-SIC7)