rgtjf / Semantic Texual Similarity Toolkits
Licence: mit
Semantic Textual Similarity (STS) measures the degree of equivalence in the underlying semantics of paired snippets of text.
Stars: ✭ 87
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Semantic Texual Similarity Toolkits
Nested Ner Tacl2020 Transformers
Implementation of Nested Named Entity Recognition using BERT
Stars: ✭ 76 (-12.64%)
Mutual labels: natural-language-processing
Deepmoji
State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc.
Stars: ✭ 1,215 (+1296.55%)
Mutual labels: natural-language-processing
Greek Bert
A Greek edition of BERT pre-trained language model
Stars: ✭ 84 (-3.45%)
Mutual labels: natural-language-processing
Dialogue Understanding
This repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study
Stars: ✭ 77 (-11.49%)
Mutual labels: natural-language-processing
Text Dependency Parser
🏄 依存关系分析，NLP，自然语言处理
Stars: ✭ 78 (-10.34%)
Mutual labels: natural-language-processing
Opennmt Tf
Neural machine translation and sequence learning using TensorFlow
Stars: ✭ 1,223 (+1305.75%)
Mutual labels: natural-language-processing
Rutermextract
Term extraction for Russian language
Stars: ✭ 75 (-13.79%)
Mutual labels: natural-language-processing
Turkish Bert Nlp Pipeline
Bert-base NLP pipeline for Turkish, Ner, Sentiment Analysis, Question Answering etc.
Stars: ✭ 85 (-2.3%)
Mutual labels: natural-language-processing
Practical 3
Oxford Deep NLP 2017 course - Practical 3: Text Classification with RNNs
Stars: ✭ 78 (-10.34%)
Mutual labels: natural-language-processing
Simplednn
SimpleDNN is a machine learning lightweight open-source library written in Kotlin designed to support relevant neural network architectures in natural language processing tasks
Stars: ✭ 81 (-6.9%)
Mutual labels: natural-language-processing
Abigsurvey
A collection of 500+ survey papers on Natural Language Processing (NLP) and Machine Learning (ML)
Stars: ✭ 1,203 (+1282.76%)
Mutual labels: natural-language-processing
Chinese Xlnet
Pre-Trained Chinese XLNet（中文XLNet预训练模型）
Stars: ✭ 1,213 (+1294.25%)
Mutual labels: natural-language-processing
Typenovel
A simple markup language to write novel with types.
Stars: ✭ 80 (-8.05%)
Mutual labels: natural-language-processing
Monkeylearn Ruby
Official Ruby client for the MonkeyLearn API. Build and consume machine learning models for language processing from your Ruby apps.
Stars: ✭ 76 (-12.64%)
Mutual labels: natural-language-processing
Scanrefer
[ECCV 2020] ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
Stars: ✭ 84 (-3.45%)
Mutual labels: natural-language-processing
Awesome Bert Japanese
📝 A list of pre-trained BERT models for Japanese with word/subword tokenization + vocabulary construction algorithm information
Stars: ✭ 76 (-12.64%)
Mutual labels: natural-language-processing
Ja.text8
Japanese text8 corpus for word embedding.
Stars: ✭ 79 (-9.2%)
Mutual labels: natural-language-processing
Ml
A high-level machine learning and deep learning library for the PHP language.
Stars: ✭ 1,270 (+1359.77%)
Mutual labels: natural-language-processing
Practical Open
Oxford Deep NLP 2017 course - Open practical
Stars: ✭ 84 (-3.45%)
Mutual labels: natural-language-processing
Spacy Graphql
🤹♀️ Query spaCy's linguistic annotations using GraphQL
Stars: ✭ 81 (-6.9%)
Mutual labels: natural-language-processing
Semantic Textual Similarity Toolkits
This is the code by ECNU team submitted to SemEval STS Task.
Installation
# download the repo
git clone https://github.com/rgtjf/Semantic-Texual-Similarity-Toolkits.git
# download the dataset and stanford CoreNLP tools
sh download.sh
# run the demo
python demo.py
Results
you can configure sts_model.py to see the performance of different features on STSBenchmark dataset.
STSBenchmark
| Methods | Dev | Test |
|---|---|---|
| RF | 0.8333 | 0.7993 |
| GB | 0.8356 | 0.8022 |
| EN-seven | 0.8466 | 0.8100 |
| ---------------------- | -------- | -------- |
| aligner | 0.6991 | 0.6379 |
| idf_aligner | 0.7969 | 0.7622 |
| BOWFeature-True | 0.7584 | 0.6472 |
| BOWFeature-False | 0.7788 | 0.6874 |
| nGramOverlapFeature | 0.7817 | 0.7453 |
| BOWFeature | 0.7639 | 0.6847 |
| AlignmentFeature | 0.8163 | 0.7748 |
| WordEmbeddingFeature | 0.8011 | 0.7128 |
Reference
Contacts
Any questions, please feel free to contact us: rgtjf1 AT 163 DOT com
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].