An AI application web developed by python using Django Web Framework
Support
Quality
Security
License
Reuse
A collection of Python scripts for creating topic models for Serendip. Uses Mallet and Gensim
Support
Quality
Security
License
Reuse
Tool for Text Mining
Support
Quality
Security
License
Reuse
Dead simple conditional build tool
Support
Quality
Security
License
Reuse
System for suggesting new concepts for vocabularies
Support
Quality
Security
License
Reuse
Mã nguồn cho lộ trình hoc python backend - vimentor.com
Support
Quality
Security
License
Reuse
Neural morphological tagging with Modern Hebrew (Keras)
Support
Quality
Security
License
Reuse
O
OtomatikSesTranskripsiyonuby Selennurdlsz
JavaScript 3 Version:Current License: No License (No License)
Bitirme Tezi-Derin öğrenme tabanlı ses-text çevirimi gerçekleştirilerek metin işleme ile textler 5 kategoride sınıflandırılıp yeni girilen ya da kaydedilen textin kategorisini bulmayı sağlayan uygulamadır.
Support
Quality
Security
License
Reuse
A novel approach to Passage Ranking Problem using BERT model.
Support
Quality
Security
License
Reuse
A simple token generation application to demonstrate three ways of token generation
Support
Quality
Security
License
Reuse
An intelligent tool to help find best job for you
Support
Quality
Security
License
Reuse
A toolkit for comparative evaluation of outputs of two or more NLP systems
Support
Quality
Security
License
Reuse
ETIP research repo about nested named entity recognition
Support
Quality
Security
License
Reuse
Proposing model for embedding sentences into vectors that capture both semantic and syntactical information in a computationally effective manner.
Support
Quality
Security
License
Reuse
A curated list of papers and experiments in the field of Natural Language Processing (NLP)
Support
Quality
Security
License
Reuse
Text to Image Generation
Support
Quality
Security
License
Reuse
Server for the Year 2 university group project
Support
Quality
Security
License
Reuse
Flask based application to extract entities from text using Spacy.
Support
Quality
Security
License
Reuse
Python package containing functions that may be useful for word research.
Support
Quality
Security
License
Reuse
Random Semantically-Unpredictable Sentence Generator with NLTK
Support
Quality
Security
License
Reuse
BERT model, tested for CNTK and Tensorflow
Support
Quality
Security
License
Reuse
WASP: Web Audio Sound Programming
Support
Quality
Security
License
Reuse
Chinese nlp tasks finetuning with google bert
Support
Quality
Security
License
Reuse
BI-DIRECTIONAL ATTENTION FLOW FOR MACHINE COMPREHENSION
Support
Quality
Security
License
Reuse
P
Part-of-Speech-Tagging-with-HMMby lukysummer
Python 3 Version:Current License: No License (No License)
Automatic Part-of-Speech Tagging (labelling words as noun, verb, adjective, etc.) using Hidden Markov Model, trained on Brown Corpus
Support
Quality
Security
License
Reuse
Applies Canonical Correlation Analysis to the task of visual dialogue.
Support
Quality
Security
License
Reuse
N
Neural_machine_translation-with-Attentionby naveenkumarg651
Python 3 Version:Current License: No License (No License)
English to hindi NMT using attention written in Python using Keras
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
Fictional language toolbox in Java. Generate random languages, mix them together, generate text in them, reversibly translate English text to a fictional language, etc.
Support
Quality
Security
License
Reuse
A small esoteric programming language developed for CMSI 488 - Language Translation and Implementation at Loyola Marymount University.
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
Part-of-speech-specific implementation of Melamud et al. 2015 lexical substitution model
Support
Quality
Security
License
Reuse
Induction 2019 task
Support
Quality
Security
License
Reuse
DATA This assignment is about part-of-speech tagging on Twitter data. The data is located in ./data directory with a train and dev split. The test data is also included, but with false POS tags on purpose. You will develop and tune your models only using train and dev sets, and will generate predictions for the test data once you are done developing. The accuracy will be computed by TA with the goldstandard labels. This data set contains tweets annotated with their universal parts-of-speech tags, with 379 tweets for training and 112 for dev, and 12 possible part-of-speech labels. The test corpus will contain 295 tweets. The format of the data files is pretty straight forward. It contains a line for each token (with its label separated by a whitespace), and with sentences separated with empty line. See the below example an example, and examine the text files yourself (always a good idea). @paulwalk X It PRON 's VERB the DET view NOUN from ADP where ADV I PRON 'm VERB living VERB for ADP two NUM weeks NOUN . . Empire NOUN State NOUN Building NOUN = X ESB NOUN . . Pretty ADV bad ADJ storm NOUN here ADV last ADJ evening NOUN Files data.py: The primary entry point that reads the data, and trains and evaluates the tagger implementation. usage: python data.py [-h] [-m MODEL] [--test] optional arguments: -h, --help show this help message and exit -m MODEL, --model MODEL 'LR'/'lr' for logistic regression tagger 'CRF'/'crf' for conditional random field tagger --test Make predictions for test dataset tagger.py: Code for two sequence taggers, logistic regression and CRF. Both of these taggers rely on 'feats.py' and 'feat_gen.py' to compute the features for each token. The CRF tagger also relies on 'viterbi.py' to decode (which is currently incorrect), and on 'struct_perceptron.py' for the training algorithm (which also needs Viterbi to be working). feats.py & 'feat_gen.py: Code to compute, index, and maintain the token features. The primary purpose of 'feats.py' is to map the boolean features computed in 'feats_gen.py' to integers, and do the reverse mapping (if you want to know the name of a feature from its index). 'feats_gen.py' is used to compute the features of a token in a sentence, which you will be extending. The method there returns the computed features for a token as a list of string (so does not have to worry about indices, etc.). 'struct_perceptron.py': A direct port (with negligible changes) of the structured perceptron trainer from the 'pystruct' project. Only used for the CRF tagger. The description of the various hyperparameters of the trainer are available here, but you should change them from the constructor in 'tagger.py'. 'viterbi.py' (and 'viterbi_test.py'): General purpose interface to a sequence Viterbi decoder in 'viterbi.py', which currently has an incorrect implementation. Once you have implemented the Viterbi implementation, running 'python viterbi_test.py' should result in succesful execution without any exceptions. conlleval.pl: This is the official evaluation script for the CONLL evaluation. Although it computes the same metrics as the python code does, it supports a bunch of features, such as: (a) Latex formatted tables, by using -l, (b) BIO annotation by default, turned off using -r. In particular, when evaluating the output prediction files (~.pred) for POS tagging, $ ./conlleval.pl -r -d \t < ./predictions/twitter_dev.pos.pred
Support
Quality
Security
License
Reuse
OCR with Tesseract, Deep Learning, Python, Apache NiFi, ...
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
We propose a model based on the bag of mixed-gram terms to deal with sentiment classification task and extracting sentimental features. We obtain a very short-dimensional vector to represent sentiment and use the sentimental representations to complete the task of sentiment classification. Furthermore, since the sentimental representa- tions and some traditional word vectors have complementary advantages, we combine the sentimental representations with convolutional neural networks that use other word vectors and ultimately implement a more efficient classifier. Experimental results show that this combination method can use static word vectors to deal with sentimental classification tasks well, and the sentimental representations here play the role of fine-turned word vectors in previous research.
Support
Quality
Security
License
Reuse
Java and Python scripts used to prepare the training data for different NLU Services, query NLU Services and evaluate the performances
Support
Quality
Security
License
Reuse
The Java Package of Key Word Extractor.
Support
Quality
Security
License
Reuse
Language pipelines
Support
Quality
Security
License
Reuse
A new library for building PSL models in Python
Support
Quality
Security
License
Reuse
SENG 401 Winter 2020 Term project
Support
Quality
Security
License
Reuse
Using OOP to implement chess
Support
Quality
Security
License
Reuse
[Course] A pinyin inputer based on n-gram algorithm. (AI2017 Homework1)
Support
Quality
Security
License
Reuse
A sentiment analysis library for tweet objects and strings
Support
Quality
Security
License
Reuse
openAI gpt-2
Support
Quality
Security
License
Reuse
Dead — please use the new Origami Registry (https://github.com/Financial-Times/origami-registry-ui)
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
NLP100knock challenge in Ruby and Python3
Support
Quality
Security
License
Reuse
Clinical Acoustics & Text Processing (CATPro) provides tools for monitoring and predicting mental health disorders using acoustic signal processing and natural language processing.
Support
Quality
Security
License
Reuse
A
AiWebby wp931120
An AI application web developed by python using Django Web Framework
JavaScript 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
V
VEP_TMScriptsby uwgraphics
A collection of Python scripts for creating topic models for Serendip. Uses Mallet and Gensim
Python 3Updated: 4 y ago License: Permissive (BSD-2-Clause)
Support
Quality
Security
License
Reuse
l
language_miningby devudilip
Tool for Text Mining
Ruby 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
d
divergeby arboleya
Dead simple conditional build tool
JavaScript 3Updated: 3 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
F
Finto-suggestioby NatLibFi
System for suggesting new concepts for vocabularies
JavaScript 3Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
p
pythonbackenddemoby vimentor-com
Mã nguồn cho lộ trình hoc python backend - vimentor.com
Python 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
h
hebrew-morph-taggerby tsnaomi
Neural morphological tagging with Modern Hebrew (Keras)
Python 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
O
OtomatikSesTranskripsiyonuby Selennurdlsz
Bitirme Tezi-Derin öğrenme tabanlı ses-text çevirimi gerçekleştirilerek metin işleme ile textler 5 kategoride sınıflandırılıp yeni girilen ya da kaydedilen textin kategorisini bulmayı sağlayan uygulamadır.
JavaScript 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
P
PassageRankingby sjagrwl
A novel approach to Passage Ranking Problem using BERT model.
Python 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
t
tokenizerby relotnek
A simple token generation application to demonstrate three ways of token generation
Ruby 3Updated: 3 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
J
JobCatcherby ForestCold
An intelligent tool to help find best job for you
JavaScript 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
C
ComparEvalby dtuggener
A toolkit for comparative evaluation of outputs of two or more NLP systems
Python 3Updated: 4 y ago License: Strong Copyleft (GPL-3.0)
Support
Quality
Security
License
Reuse
N
Nested-NERby ETIP-team
ETIP research repo about nested named entity recognition
Python 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
s
sentence2vectorby HuyVu0508
Proposing model for embedding sentences into vectors that capture both semantic and syntactical information in a computationally effective manner.
Python 3Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
n
nlp-notesby murali1996
A curated list of papers and experiments in the field of Natural Language Processing (NLP)
Python 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
T
TransformerGenby anurag1paul
Text to Image Generation
Python 3Updated: 5 y ago License: Strong Copyleft (GPL-3.0)
Support
Quality
Security
License
Reuse
c
classi-serverby Rytchet
Server for the Year 2 university group project
JavaScript 3Updated: 3 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
e
entity-recognition-flask-appby ankitshaw
Flask based application to extract entities from text using Spacy.
Python 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
l
lexlibby cranndarach
Python package containing functions that may be useful for word research.
Python 3Updated: 5 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
S
SUSgenby ecooper7
Random Semantically-Unpredictable Sentence Generator with NLTK
Python 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
B
BERT-keras-TF-CNTKby Ivalua
BERT model, tested for CNTK and Tensorflow
Python 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
W
WASPby tanyamgoncalves
WASP: Web Audio Sound Programming
JavaScript 3Updated: 9 y ago License: Strong Copyleft (GPL-2.0)
Support
Quality
Security
License
Reuse
b
bert_zhby EternalFeather
Chinese nlp tasks finetuning with google bert
Python 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
B
BiDAFby Chiang97912
BI-DIRECTIONAL ATTENTION FLOW FOR MACHINE COMPREHENSION
Python 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
P
Part-of-Speech-Tagging-with-HMMby lukysummer
Automatic Part-of-Speech Tagging (labelling words as noun, verb, adjective, etc.) using Hidden Markov Model, trained on Brown Corpus
Python 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
C
CCA-visualdialogueby danielamassiceti
Applies Canonical Correlation Analysis to the task of visual dialogue.
Python 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
N
Neural_machine_translation-with-Attentionby naveenkumarg651
English to hindi NMT using attention written in Python using Keras
Python 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
D
DrQAChineseby mazzzystar
Python 3Updated: 5 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
G
Gabberby tommyettinger
Fictional language toolbox in Java. Generate random languages, mix them together, generate text in them, reversibly translate English text to a fictional language, etc.
Java 3Updated: 5 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
r
respeccby jmaiocco
A small esoteric programming language developed for CMSI 488 - Language Translation and Implementation at Loyola Marymount University.
JavaScript 3Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
X
Xtralingua-2.0by hocrt
JavaScript 3Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
l
lexsub_addcosby acocos
Part-of-speech-specific implementation of Melamud et al. 2015 lexical substitution model
Python 3Updated: 6 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
i
Support
Quality
Security
License
Reuse
P
Part-of-Speech-Taggingby srishb28
DATA This assignment is about part-of-speech tagging on Twitter data. The data is located in ./data directory with a train and dev split. The test data is also included, but with false POS tags on purpose. You will develop and tune your models only using train and dev sets, and will generate predictions for the test data once you are done developing. The accuracy will be computed by TA with the goldstandard labels. This data set contains tweets annotated with their universal parts-of-speech tags, with 379 tweets for training and 112 for dev, and 12 possible part-of-speech labels. The test corpus will contain 295 tweets. The format of the data files is pretty straight forward. It contains a line for each token (with its label separated by a whitespace), and with sentences separated with empty line. See the below example an example, and examine the text files yourself (always a good idea). @paulwalk X It PRON 's VERB the DET view NOUN from ADP where ADV I PRON 'm VERB living VERB for ADP two NUM weeks NOUN . . Empire NOUN State NOUN Building NOUN = X ESB NOUN . . Pretty ADV bad ADJ storm NOUN here ADV last ADJ evening NOUN Files data.py: The primary entry point that reads the data, and trains and evaluates the tagger implementation. usage: python data.py [-h] [-m MODEL] [--test] optional arguments: -h, --help show this help message and exit -m MODEL, --model MODEL 'LR'/'lr' for logistic regression tagger 'CRF'/'crf' for conditional random field tagger --test Make predictions for test dataset tagger.py: Code for two sequence taggers, logistic regression and CRF. Both of these taggers rely on 'feats.py' and 'feat_gen.py' to compute the features for each token. The CRF tagger also relies on 'viterbi.py' to decode (which is currently incorrect), and on 'struct_perceptron.py' for the training algorithm (which also needs Viterbi to be working). feats.py & 'feat_gen.py: Code to compute, index, and maintain the token features. The primary purpose of 'feats.py' is to map the boolean features computed in 'feats_gen.py' to integers, and do the reverse mapping (if you want to know the name of a feature from its index). 'feats_gen.py' is used to compute the features of a token in a sentence, which you will be extending. The method there returns the computed features for a token as a list of string (so does not have to worry about indices, etc.). 'struct_perceptron.py': A direct port (with negligible changes) of the structured perceptron trainer from the 'pystruct' project. Only used for the CRF tagger. The description of the various hyperparameters of the trainer are available here, but you should change them from the constructor in 'tagger.py'. 'viterbi.py' (and 'viterbi_test.py'): General purpose interface to a sequence Viterbi decoder in 'viterbi.py', which currently has an incorrect implementation. Once you have implemented the Viterbi implementation, running 'python viterbi_test.py' should result in succesful execution without any exceptions. conlleval.pl: This is the official evaluation script for the CONLL evaluation. Although it computes the same metrics as the python code does, it supports a bunch of features, such as: (a) Latex formatted tables, by using -l, (b) BIO annotation by default, turned off using -r. In particular, when evaluating the output prediction files (~.pred) for POS tagging, $ ./conlleval.pl -r -d \t < ./predictions/twitter_dev.pos.pred
Python 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
n
nifi-ocrby tspannhw
OCR with Tesseract, Deep Learning, Python, Apache NiFi, ...
Python 3Updated: 5 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
C
ChallengeTestsby YearOfProgramming
Python 3Updated: 6 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
S
SentimentRepresentationby GuoZhongyang
We propose a model based on the bag of mixed-gram terms to deal with sentiment classification task and extracting sentimental features. We obtain a very short-dimensional vector to represent sentiment and use the sentimental representations to complete the task of sentiment classification. Furthermore, since the sentimental representa- tions and some traditional word vectors have complementary advantages, we combine the sentimental representations with convolutional neural networks that use other word vectors and ultimately implement a more efficient classifier. Experimental results show that this combination method can use static word vectors to deal with sentimental classification tasks well, and the sentimental representations here play the role of fine-turned word vectors in previous research.
Python 3Updated: 5 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
N
NLU-Evaluation-Scriptsby xliuhw
Java and Python scripts used to prepare the training data for different NLU Services, query NLU Services and evaluate the performances
Python 3Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
K
KeyExtractby NLPIR-team
The Java Package of Key Word Extractor.
Java 3Updated: 6 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
l
Support
Quality
Security
License
Reuse
p
pypslby br-g
A new library for building PSL models in Python
Python 3Updated: 1 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
R
RateMyClassby ndarby
SENG 401 Winter 2020 Term project
JavaScript 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
c
Support
Quality
Security
License
Reuse
P
PinyinInputerby wangrunji0408
[Course] A pinyin inputer based on n-gram algorithm. (AI2017 Homework1)
C# 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
s
sentimentjsby crowd-parser
A sentiment analysis library for tweet objects and strings
JavaScript 3Updated: 7 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
o
Support
Quality
Security
License
Reuse
o
origami-registryby Financial-Times
Dead — please use the new Origami Registry (https://github.com/Financial-Times/origami-registry-ui)
PHP 3Updated: 6 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
a
arabic-text-classificationby agtaweel
Python 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
N
NLP100knock_2015by mille-f
NLP100knock challenge in Ruby and Python3
Ruby 3Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
c
catproby danielmlow
Clinical Acoustics & Text Processing (CATPro) provides tools for monitoring and predicting mental health disorders using acoustic signal processing and natural language processing.
Python 3Updated: 4 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse