HanLP - 自然语言处理 中文分词 词性标注 命名实体识别 依存句法分析 关键词提取 新词发现 短语提取 自动摘要 文本分类 拼音简繁

•    Java

---

汉语言处理包

nlp natural-language-processing hanlp crf hmm trie textrank doublearraytrie neural-network chinese-word-segmentation text-mining pos-tagging dependency-parser text-classification word2vec perceptron named-entity-recognition text-clustering

NCRFpp - NCRF++, an Open-source Neural Sequence Labeling Toolkit

•    Python

---

Sequence labeling models are quite popular in many NLP tasks, such as Named Entity Recognition (NER), part-of-speech (POS) tagging and word segmentation. State-of-the-art sequence labeling models mostly utilize the CRF structure with input word features. LSTM (or bidirectional LSTM) is a popular deep learning based feature extractor in sequence labeling task. And CNN can also be used due to faster computation. Besides, features within word are also useful to represent word, which can be captured by character LSTM or character CNN structure or human-defined neural features. NCRF++ is a PyTorch based framework with flexiable choices of input features and output structures. The design of neural sequence labeling models with NCRF++ is fully configurable through a configuration file, which does not require any code work. NCRF++ is a neural version of CRF++, which is a famous statistical CRF framework.

pytorch ner sequence-labeling crf lstm-crf char-rnn char-cnn named-entity-recognition part-of-speech-tagger chunking neural-networks nbest lstm cnn batch

pydensecrf - Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials

•    C++

---

This is a (Cython-based) Python wrapper for Philipp Krähenbühl's Fully-Connected CRFs (version 2, new, incomplete page). and provide a link to this repository as a footnote or a citation.

computer-vision machine-learning crf pairwise-potentials unary-potentials cython eigen

python-crfsuite - A python binding for crfsuite

•    Python

---

python-crfsuite is a python binding to CRFsuite. See docs and an example.

data-science crf crfsuite

CRFSharp

•    DotNet

---

CRFSharp is Conditional Random Fields implemented by .NET(C#), a machine learning algorithm for learning from labeled sequences of examples.

algorithms crf linguistic machine-learning morphology

WordSegment

•    

---

This project is used to segment text into tokens according its context and semantic. the segment use front-maximum matching and CRF algorithms to split text.

chinese crf crfsharp nlp word-segment wordbreaker

RNNSharp - RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on

•    CSharp

---

RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above version. This page introduces what is RNNSharp, how it works and how to use it. To get the demo package, you can access release page.

rnn crf deep-learning machine-learning c-sharp sequence-labeling rnn-model recurrent-neural-networks nlp lstm

bi-lstm-crf-tensorflow - Bidirectional LSTM + CRF (Conditional Random Fields) in Tensorflow

•    Jupyter

---

The notebook bi-lstm-crf-tensorflow.ipynb contains an example of a Bidirectional LSTM + CRF (Conditional Random Fields) model in Tensorflow. I tried to keep the problem and implementation as simple as possible so anyone can understand and change the model to meet their own problem and data.

bidirectional-lstm crf tensorflow

CRFSuite - Tree-Structured, First- and Higher-Order Linear Chain, and Semi-Markov CRFs

•    C

---

CRFSuite 0.13 is a fork of Naoaki Okazaki's implementation of conditional random fields (CRFs). Please refer to the web site for more information about the original software. To invoke tree-structured CRFs, you should provide the option --type=tree when running crfsuite learn and also specify this option when you later envoke crfsuite tag with the trained model.

machine-learning crf graphical-models

CRFSharp - CRFSharp is Conditional Random Fields implemented by

•    CSharp

---

CRFSharp is Conditional Random Fields (CRF) implemented by .NET(C#), a machine learning algorithm for learning from labeled sequences of examples. CRFSharp is Conditional Random Fields implemented by .NET(C#), a machine learning algorithm for learning from labeled sequences of examples. It is widely used in Natural Language Process (NLP) tasks, for example: word breaker, postaging, named entity recognized and so on.

crf nlp c-sharp machine-learning

ml - Re-usable low-level ML components

•    Java

---

Repository for low-level production-grade ML inference. The current motivating example is the CRF inference component which is used in the AI2 fork of Grobid and Science Parse. It's currently 100% Java, but can also have Scala too. You can use Markdown in your Javadoc using Pegdown.

lombok crf

ID-CNN-CWS - Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation"

•    Python

---

Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation". Both CPU and GPU are supported. GPU training is 10 times faster.

cws nlp cnn bilstm crf tensorflow

nlp - A collection of natural language processing algorithms for Go

•    Go

---

NLP is a go package meant to contain implementations of common natural language processing algorithms. So far there is a naive implementation of conditional random fields.

crf nlp natural-language-processing conditional-random-fields