ScdvText classification with Sparse Composite Document Vectors.
Stars: ✭ 54 (-75%)
bert in a flaskA dockerized flask API, serving ALBERT and BERT predictions using TensorFlow 2.0.
Stars: ✭ 32 (-85.19%)
kexKex is a python library for unsupervised keyword extraction from a document, providing an easy interface and benchmarks on 15 public datasets.
Stars: ✭ 46 (-78.7%)
T3[EMNLP 2020] "T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack" by Boxin Wang, Hengzhi Pei, Boyuan Pan, Qian Chen, Shuohang Wang, Bo Li
Stars: ✭ 25 (-88.43%)
HdltexHDLTex: Hierarchical Deep Learning for Text Classification
Stars: ✭ 191 (-11.57%)
PIEFast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D19-1435.pdf (EMNLP-IJCNLP 2019)
Stars: ✭ 164 (-24.07%)
MixGCFMixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems, KDD2021
Stars: ✭ 73 (-66.2%)
iamQA中文wiki百科QA阅读理解问答系统,使用了CCKS2016数据的NER模型和CMRC2018的阅读理解模型,还有W2V词向量搜索,使用torchserve部署
Stars: ✭ 46 (-78.7%)
NprfNPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval
Stars: ✭ 31 (-85.65%)
bert-as-a-service TFXEnd-to-end pipeline with TFX to train and deploy a BERT model for sentiment analysis.
Stars: ✭ 32 (-85.19%)
patzillaPatZilla is a modular patent information research platform and data integration toolkit with a modern user interface and access to multiple data sources.
Stars: ✭ 71 (-67.13%)
KoBERT-nsmcNaver movie review sentiment classification with KoBERT
Stars: ✭ 57 (-73.61%)
ProQAProgressively Pretrained Dense Corpus Index for Open-Domain QA and Information Retrieval
Stars: ✭ 44 (-79.63%)
knowledge-graph-nlp-in-action从模型训练到部署,实战知识图谱(Knowledge Graph)&自然语言处理(NLP)。涉及 Tensorflow, Bert+Bi-LSTM+CRF,Neo4j等 涵盖 Named Entity Recognition,Text Classify,Information Extraction,Relation Extraction 等任务。
Stars: ✭ 58 (-73.15%)
Knowledge GraphsA collection of research on knowledge graphs
Stars: ✭ 845 (+291.2%)
Filipino-Text-BenchmarksOpen-source benchmark datasets and pretrained transformer models in the Filipino language.
Stars: ✭ 22 (-89.81%)
COVID19-IRQANo description or website provided.
Stars: ✭ 32 (-85.19%)
MengziMengzi Pretrained Models
Stars: ✭ 238 (+10.19%)
OpenmatchAn Open-Source Package for Information Retrieval.
Stars: ✭ 186 (-13.89%)
semantic-document-relationsImplementation, trained models and result data for the paper "Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles"
Stars: ✭ 21 (-90.28%)
Drl4nlp.scratchpadNotes on Deep Reinforcement Learning for Natural Language Processing papers
Stars: ✭ 26 (-87.96%)
learning2hash.github.ioWebsite for "A survey of learning to hash for Computer Vision" https://learning2hash.github.io
Stars: ✭ 14 (-93.52%)
deepconsensusDeepConsensus uses gap-aware sequence transformers to correct errors in Pacific Biosciences (PacBio) Circular Consensus Sequencing (CCS) data.
Stars: ✭ 124 (-42.59%)
KLUE📖 Korean NLU Benchmark
Stars: ✭ 420 (+94.44%)
LuceneTutorialA simple tutorial of Lucene for LIS 501 Introduction to Text Mining students at the University of Wisconsin-Madison (Fall 2021).
Stars: ✭ 62 (-71.3%)
NER-FunTool本NER项目包含多个中文数据集,模型采用BiLSTM+CRF、BERT+Softmax、BERT+Cascade、BERT+WOL等,最后用TFServing进行模型部署,线上推理和线下推理。
Stars: ✭ 56 (-74.07%)
IR-exercisesSolutions of the various test exams of the Information Retrieval course
Stars: ✭ 28 (-87.04%)
bert sabert sentiment analysis tensorflow serving with RESTful API
Stars: ✭ 35 (-83.8%)
NSP-BERTThe code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"
Stars: ✭ 166 (-23.15%)
RelevancyfeedbackDice.com's relevancy feedback solr plugin created by Simon Hughes (Dice). Contains request handlers for doing MLT style recommendations, conceptual search, semantic search and personalized search
Stars: ✭ 19 (-91.2%)
textgoText preprocessing, representation, similarity calculation, text search and classification. Let's go and play with text!
Stars: ✭ 33 (-84.72%)
perkeA keyphrase extractor for Persian
Stars: ✭ 60 (-72.22%)
ALBERT-PytorchPytorch Implementation of ALBERT(A Lite BERT for Self-supervised Learning of Language Representations)
Stars: ✭ 214 (-0.93%)
NeuralqaNeuralQA: A Usable Library for Question Answering on Large Datasets with BERT
Stars: ✭ 185 (-14.35%)
query-wellformedness25,100 queries from the Paralex corpus (Fader et al., 2013) annotated with human ratings of whether they are well-formed natural language questions.
Stars: ✭ 80 (-62.96%)
TalismanStraightforward fuzzy matching, information retrieval and NLP building blocks for JavaScript.
Stars: ✭ 584 (+170.37%)
VtextSimple NLP in Rust with Python bindings
Stars: ✭ 108 (-50%)
luceneApache Lucene open-source search software
Stars: ✭ 1,009 (+367.13%)
bernA neural named entity recognition and multi-type normalization tool for biomedical text mining
Stars: ✭ 151 (-30.09%)
Fengshenbang-LMFengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系,成为中文AIGC和认知智能的基础设施。
Stars: ✭ 1,813 (+739.35%)
DocProductMedical Q&A with Deep Language Models
Stars: ✭ 527 (+143.98%)
Dalle PytorchImplementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
Stars: ✭ 3,661 (+1594.91%)
ark-nlpA private nlp coding package, which quickly implements the SOTA solutions.
Stars: ✭ 232 (+7.41%)
ResinHardware-accelerated vector-based search engine. Available as a HTTP service or as an embedded library.
Stars: ✭ 529 (+144.91%)
Information-RetrievalInformation Retrieval algorithms developed in python. To follow the blog posts, click on the link:
Stars: ✭ 103 (-52.31%)
RankingLearning to Rank in TensorFlow
Stars: ✭ 2,362 (+993.52%)
transformers-interpretModel explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.
Stars: ✭ 861 (+298.61%)
py-lingualyticsA text analytics library with support for codemixed data
Stars: ✭ 36 (-83.33%)
pykaleKnowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem
Stars: ✭ 381 (+76.39%)
pytorch-revgradA minimal pytorch package implementing a gradient reversal layer.
Stars: ✭ 142 (-34.26%)
Ds2iA library of inverted index data structures
Stars: ✭ 104 (-51.85%)
JPQCIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.
Stars: ✭ 39 (-81.94%)
elastic transformersMaking BERT stretchy. Semantic Elasticsearch with Sentence Transformers
Stars: ✭ 153 (-29.17%)