deep-scite🚣 A simple recommendation engine (by way of convolutions and embeddings) written in TensorFlow
Stars: ✭ 20 (-94.33%)
geometric embedding"Zero-Training Sentence Embedding via Orthogonal Basis" paper implementation
Stars: ✭ 19 (-94.62%)
AsammdfFast Python reader and editor for ASAM MDF / MF4 (Measurement Data Format) files
Stars: ✭ 255 (-27.76%)
pf-azure-sentinelParse pfSense/OPNSense logs using Logstash, GeoIP tag entities, add additional context to logs, then send to Azure Sentinel for analysis.
Stars: ✭ 24 (-93.2%)
mtgsqliveMTGJSON build scripts to generate alternative data formats
Stars: ✭ 40 (-88.67%)
img2vec-kerasImage to dense vector embedding. Clone of https://github.com/christiansafka/img2vec for Keras users
Stars: ✭ 36 (-89.8%)
python-yamlableA thin wrapper of PyYaml to convert Python objects to YAML and back
Stars: ✭ 28 (-92.07%)
icecast-parserNode.js module for getting and parsing metadata from SHOUTcast/Icecast radio streams
Stars: ✭ 66 (-81.3%)
VarCLRVarCLR: Variable Semantic Representation Pre-training via Contrastive Learning
Stars: ✭ 30 (-91.5%)
transformerBuild English-Vietnamese machine translation with ProtonX Transformer. :D
Stars: ✭ 41 (-88.39%)
UrlextractorInformation gathering & website reconnaissance | https://phishstats.info/
Stars: ✭ 341 (-3.4%)
ibleuA visual and interactive scoring environment for machine translation systems.
Stars: ✭ 27 (-92.35%)
TabInOutFramework for information extraction from tables
Stars: ✭ 37 (-89.52%)
parse-github-urlParse a Github URL into an object. Supports a wide variety of GitHub URL formats.
Stars: ✭ 114 (-67.71%)
007-TheBondThis Script will help you to gather information about your victim or friend.
Stars: ✭ 371 (+5.1%)
simple elmoSimple library to work with pre-trained ELMo models in TensorFlow
Stars: ✭ 49 (-86.12%)
deep-char-cnn-lstmDeep Character CNN LSTM Encoder with Classification and Similarity Models
Stars: ✭ 20 (-94.33%)
Tmxlitelightweight C++14 parser for Tiled tmx files
Stars: ✭ 248 (-29.75%)
ArticutapiAPI of Articut 中文斷詞 (兼具語意詞性標記):「斷詞」又稱「分詞」,是中文資訊處理的基礎。Articut 不用機器學習,不需資料模型,只用現代白話中文語法規則,即能達到 SIGHAN 2005 F1-measure 94% 以上,Recall 96% 以上的成績。
Stars: ✭ 252 (-28.61%)
Skrape.itA Kotlin-based testing/scraping/parsing library providing the ability to analyze and extract data from HTML (server & client-side rendered). It places particular emphasis on ease of use and a high level of readability by providing an intuitive DSL. It aims to be a testing lib, but can also be used to scrape websites in a convenient fashion.
Stars: ✭ 231 (-34.56%)
HttpUtilityHttpUtility is an open source MIT license project which is helpful in making HTTP requests and returns a decoded object from server. Right now this utility only parses JSON.
Stars: ✭ 28 (-92.07%)
ZipsonJSON parse and stringify with compression
Stars: ✭ 229 (-35.13%)
ParseGo parsers for web formats
Stars: ✭ 224 (-36.54%)
omegat-tencent-pluginThis is a plugin to allow OmegaT to source machine translations from Tencent Cloud.
Stars: ✭ 31 (-91.22%)
Tsql ParserLibrary Written in C# For Parsing SQL Server T-SQL Scripts in .Net
Stars: ✭ 203 (-42.49%)
PolyfuzzFuzzy string matching, grouping, and evaluation.
Stars: ✭ 292 (-17.28%)
Forensic ToolsA collection of tools for forensic analysis
Stars: ✭ 204 (-42.21%)
krokusA library to format numbers and a collection for localization patterns.
Stars: ✭ 16 (-95.47%)
PSPEPretrained Span and span Pair Encoder, code for "Pre-training Entity Relation Encoder with Intra-span and Inter-spanInformation.", EMNLP2020. It is based on our NERE toolkit (https://github.com/Receiling/NERE).
Stars: ✭ 17 (-95.18%)
ClusterTransformerTopic clustering library built on Transformer embeddings and cosine similarity metrics.Compatible with all BERT base transformers from huggingface.
Stars: ✭ 36 (-89.8%)
Flags⛳ Simple, extensible, header-only C++17 argument parser released into the public domain.
Stars: ✭ 187 (-47.03%)
datastories-semeval2017-task6Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".
Stars: ✭ 20 (-94.33%)
Snapdragonsnapdragon is an extremely pluggable, powerful and easy-to-use parser-renderer factory.
Stars: ✭ 180 (-49.01%)
SpeechTransProgressTracking the progress in end-to-end speech translation
Stars: ✭ 139 (-60.62%)
Libpypalibpypa is a Python parser implemented in pure C++
Stars: ✭ 172 (-51.27%)
InformationExtractionSystemInformation Extraction System can perform NLP tasks like Named Entity Recognition, Sentence Simplification, Relation Extraction etc.
Stars: ✭ 27 (-92.35%)
Preact Markup⚡️ Render HTML5 as VDOM, with Components as Custom Elements!
Stars: ✭ 167 (-52.69%)
desktopExtendable calculator for the 21st Century ⚡
Stars: ✭ 85 (-75.92%)
ParserA lexer and parser for GraphQL in .NET
Stars: ✭ 163 (-53.82%)
navecCompact high quality word embeddings for Russian language
Stars: ✭ 118 (-66.57%)
Bm25A Python implementation of the BM25 ranking function.
Stars: ✭ 159 (-54.96%)
Bash ParserParses bash into an AST
Stars: ✭ 151 (-57.22%)
NiuTrans.NMTA Fast Neural Machine Translation System. It is developed in C++ and resorts to NiuTensor for fast tensor APIs.
Stars: ✭ 112 (-68.27%)
XponentsGeographic Place, Date/time, and Pattern entity extraction toolkit along with text extraction from unstructured data and GIS outputters.
Stars: ✭ 39 (-88.95%)
xml-to-jsonSimple API that converts dynamic XML feeds to JSON through a URL or pasting the raw XML data. Made 100% in PHP.
Stars: ✭ 38 (-89.24%)
ParjsJavaScript parser-combinator library
Stars: ✭ 145 (-58.92%)
HetuA high-performance distributed deep learning system targeting large-scale and automated distributed training.
Stars: ✭ 78 (-77.9%)
code-compassa contextual search engine for software packages built on import2vec embeddings (https://www.code-compass.com)
Stars: ✭ 33 (-90.65%)
SubGNNSubgraph Neural Networks (NeurIPS 2020)
Stars: ✭ 136 (-61.47%)
odinsonOdinson is a powerful and highly optimized open-source framework for rule-based information extraction. Odinson couples a simple, yet powerful pattern language that can operate over multiple representations of text, with a runtime system that operates in near real time.
Stars: ✭ 59 (-83.29%)
Open Entity Relation ExtractionKnowledge triples extraction and knowledge base construction based on dependency syntax for open domain text.
Stars: ✭ 350 (-0.85%)
InstagramA simple imitation of Instagram app .
Stars: ✭ 346 (-1.98%)
Contextualized Topic ModelsA python package to run contextualized topic modeling. CTMs combine BERT with topic models to get coherent topics. Also supports multilingual tasks. Cross-lingual Zero-shot model published at EACL 2021.
Stars: ✭ 318 (-9.92%)
ZhihuThis repo contains the source code in my personal column (https://zhuanlan.zhihu.com/zhaoyeyu), implemented using Python 3.6. Including Natural Language Processing and Computer Vision projects, such as text generation, machine translation, deep convolution GAN and other actual combat code.
Stars: ✭ 3,307 (+836.83%)
Tacred RelationPyTorch implementation of the position-aware attention model for relation extraction
Stars: ✭ 271 (-23.23%)