MOMO8966

hybrid-jaccard

Implementation of hybrid jaccard similarity

multi-head-selft-attention-lstm

在sts数据集上用多头注意力机制上进行测试。 pytorch torchtext 代码简练，非常适合新手了解多头注意力机制的运作。不想transformer牵扯很多层 multi-head attention + one layer lstm

semantic_similarity

Comparing TF-IDF, fastText, LASER, Sentence-BERT & USE for semantic similarity. One test with STS Benchmark and one test with self-made sentences.

NLP-beginner-Task3

基于注意力机制的文本匹配

chat

基于seq2seq的聊天系统，使用LSTM/GRU+注意力机制。使用框架pytorch。

IR-project

try different method on TaipeiQA and LCQMC datasets

Chinese-sentence-pair-modeling

Use deep models including BiLSTM, ABCNN, ESIM, RE2, BERT, etc. and evaluate on 5 Chinese NLP datasets: LCQMC, BQ Corpus, ChineseSTS, OCNLI, CMNLI

CHlikelihood

用于比较两个中文句子相似度的工具

stopwords

中文常用停用词表（哈工大停用词表、百度停用词表等）

BertSimilarity

Computing similarity of two sentences with google's BERT algorithm。利用Bert计算句子相似度。语义相似度计算。文本相似度计算。

document-similarity

Document Similarity using Word2Vec

Similarity

Calculate similarity between documents using TF-IDF weights

textreuse

Detect text reuse and document similarity

doc-similarity

Ranking documents using semantic similarity in Python

document_similarity_algorithms_experiments

Document similarity algorithms experiment - Jaccard, TF-IDF, Doc2vec, USE, and BERT.

sentence-similarity

对四种句子/文本相似度计算方法进行实验与比较

Similarity

文本相似度算法

text-similarity

用TF特征向量和simhash指纹计算中文文本的相似度

simple-effective-text-matching-pytorch

A pytorch implementation of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".

Text-Similarity

Text-Similarity Method in Pytorch

BiMPM

BiMPM: Bilateral Multi-Perspective Matching for Natural Language Sentences

ChineseVLBert

中文领域的多模态Bert

Trial2Vec

Findings of EMNLP'22 | Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision

aspect-document-embeddings

Code, dataset & models for the paper Specialized Document Embeddings for Aspect-based Similarity of Research Papers (#JCDL2022)

semeval-code

GateNLP-UShef at SemEval-2022 Task 8: Entity-Enriched Siamese Transformer for Multilingual News Article Similarity

deep-siamese-text-similarity

Tensorflow based implementation of deep siamese LSTM network to capture phrase/sentence similarity using character/word embeddings

text2vec

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

BERT-whitening

简单的向量白化改善句向量质量

JGDN