All Projects → zheng5yu9 → siamese_dssm

zheng5yu9 / siamese_dssm

Licence: other
siamese dssm sentence_similarity sentece_similarity_rank tensorflow

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to siamese dssm

Similarity
similarity:相似度计算工具包,java编写。用于词语、短语、句子、词法分析、情感分析、语义分析等相关的相似度计算。
Stars: ✭ 760 (+1188.14%)
Mutual labels:  similarity
Html Similarity
Compare html similarity using structural and style metrics
Stars: ✭ 152 (+157.63%)
Mutual labels:  similarity
Sensegram
Making sense embedding out of word embeddings using graph-based word sense induction
Stars: ✭ 209 (+254.24%)
Mutual labels:  similarity
Ml Classify Text Js
Machine learning based text classification in JavaScript using n-grams and cosine similarity
Stars: ✭ 38 (-35.59%)
Mutual labels:  similarity
Nlp Journey
Documents, papers and codes related to Natural Language Processing, including Topic Model, Word Embedding, Named Entity Recognition, Text Classificatin, Text Generation, Text Similarity, Machine Translation),etc. All codes are implemented intensorflow 2.0.
Stars: ✭ 1,290 (+2086.44%)
Mutual labels:  similarity
Tensorflow Ml Nlp
텐서플로우와 머신러닝으로 시작하는 자연어처리(로지스틱회귀부터 트랜스포머 챗봇까지)
Stars: ✭ 176 (+198.31%)
Mutual labels:  similarity
Python String Similarity
A library implementing different string similarity and distance measures using Python.
Stars: ✭ 546 (+825.42%)
Mutual labels:  similarity
levenshtein.c
Levenshtein algorithm in C
Stars: ✭ 77 (+30.51%)
Mutual labels:  similarity
Dists
IQA: Deep Image Structure and Texture Similarity Metric
Stars: ✭ 101 (+71.19%)
Mutual labels:  similarity
Phash
pHash - the open source perceptual hash library
Stars: ✭ 208 (+252.54%)
Mutual labels:  similarity
Computervision Recipes
Best Practices, code samples, and documentation for Computer Vision.
Stars: ✭ 8,214 (+13822.03%)
Mutual labels:  similarity
Rltk
Record Linkage ToolKit (Find and link entities)
Stars: ✭ 71 (+20.34%)
Mutual labels:  similarity
Synt
Find similar functions and classes in your JavaScript/TypeScript code
Stars: ✭ 178 (+201.69%)
Mutual labels:  similarity
Node Damerau Levenshtein
Damerau - Levenstein distance function for node
Stars: ✭ 27 (-54.24%)
Mutual labels:  similarity
Wordsimilarity
基于哈工大同义词词林扩展版的单词相似度计算方法
Stars: ✭ 228 (+286.44%)
Mutual labels:  similarity
Dssim
Image similarity comparison simulating human perception (multiscale SSIM in Rust)
Stars: ✭ 668 (+1032.2%)
Mutual labels:  similarity
Text2vec
text2vec, chinese text to vetor.(文本向量化表示工具,包括词向量化、句子向量化、句子相似度计算)
Stars: ✭ 155 (+162.71%)
Mutual labels:  similarity
Simple-Sentence-Similarity
Exploring the simple sentence similarity measurements using word embeddings
Stars: ✭ 99 (+67.8%)
Mutual labels:  sentence-similarity
Pg similarity
set of functions and operators for executing similarity queries
Stars: ✭ 250 (+323.73%)
Mutual labels:  similarity
Customer Chatbot
中文智能客服机器人demo,包含闲聊和专业问答2个部分,支持自定义组件(Chinese intelligent customer chatbot Demo, including the gossip and the professional Q&A(FAQ) , support for custom components!)
Stars: ✭ 198 (+235.59%)
Mutual labels:  similarity

siamese_dssm

v1.0

simaese 判断句子相似度。

v2.0

添加 基于siamese的句子相似度排序,类似于 搜索召回

v3.0

添加 dssm,判断句子相似度

v4.0

dssm和 siamese融合,强化句子相似度排序

目前处于v3.0阶段

入口文件:train.py 执行方式:python train.py 句向量召回测试: infer.py 优化

语料:corpus.txt

所用版本: python=3.5.2 tensorflow=1.3.0

优化方式: 目前已做优化:

    1.余弦距离计算方式完善
    
    2.添加激活函数
    
尚待优化:

    1.更改相似度计算方式及损失函数,余弦距离+方差 改为其他诸如 交叉熵等等;

    2.更改句子向量获取方式,rnn改为cnn;

    3.rnn输出,output或者state作为下一步的变量
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].