• Search by Module
• Search by Words
• Search Projects

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

Project: Semantic-Texual-Similarity-Toolkits (GitHub Link)

• Semantic-Texual-Similarity-Toolkits-master
  • sts_model1.py
  • LICENSE
  • demo.py
  • data
    • stsbenchmark
      • correlation.pl
      • readme.txt
      • LICENSE.txt
  • stst
    • resources
      • dict_negation_terms.txt
      • dict_stopwords.txt
    • libs
      • kernel
        • vector_kernel.py
        • tree_kernels.py
        • test_tree_kernels.py
        • __init__.py
        • tree.py
      • sentence_similarity
        • __init__.py
        • short_sentence_similarity.py
      • word_aligner
        • util.py
        • config.py
        • Resources
        • corenlp_utils.py
        • __init__.py
        • README.md
        • aligner.py
        • .gitignore
        • wordSim.py
        • test_align.py
        • parseUtil.py
      • __init__.py
      • test.py
    • config.py
    • data
      • dict_utils.py
      • __init__.py
      • data_utils.py
      • sent_pair.py
    • __init__.py
    • utils.py
    • features
      • features_pos.py
      • features_dependency.py
      • features_tree_kernels.py
      • features_ngram.py
      • features_embedding.py
      • features_embedding_online.py
      • features_mt.py
      • features_align.py
      • features_nn.py
      • __init__.py
      • features_negative.py
      • features_wn.py
      • features_bow.py
      • upload.au3
      • features_sequence.py
    • metrics
      • evaluation.py
      • __init__.py
      • record.py
    • modules
      • features.py
      • model.py
      • __init__.py
      • classifier.py
    • parser
      • corenlp_utils.py
      • __init__.py
  • sts_tools.py
  • README.md
  • sts_model.py
  • requirements.txt
  • submitted_runs
    • sts_model_2.py
    • sts_model_3.py
    • sts_model_1.py
  • .gitignore
  • download.sh

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

STSBenchmark board

Contacts

Any questions, please feel free to contact us: rgtjf1 AT 163 DOT com