hkazuakey

ABSA-BERT-pair

Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence (NAACL 2019)

bert-japanese

BERT with SentencePiece for Japanese text.

chatbot_production

cibook

clucene

Mirror of CLucene 2.3.2's development master branch. CLucene is a C++ port of Lucene: the high-performance, full-featured text search engine written in Java. CLucene is faster than lucene as it is written in C++. Read more at http://clucene.sourceforge.net/.

darts-java

Java porting of Darts (Double ARray Trie System)

delayed-memory-update-entnet

Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis, published at NAACL 2018

dl4s

source code accompanying "Deep Learning for Search" book

elyzer

"Stop worrying about Elasticsearch analyzers", my therapist says

glance

🔎 All-in-one Quick Look plugin

hkazuakey

evaluation_book

janome

Japanese morphological analysis engine written in pure Python

kuromoji

Kuromoji is a self-contained and very easy to use Japanese morphological analyzer designed for search

llm-book

「大規模言語モデル入門」（技術評論社, 2023）のGitHubリポジトリ

lucene-gosen

Japanese analysis for Apache Lucene/Solr

lucene-solr

Mirror of Apache Lucene + Solr

luke

This is mavenised Luke: Lucene Toolbox Project

marple

Browser-driven explorer for lucene indexes

mecab

Yet another Japanese morphological analyzer

meval

形態素解析器性能評価システム MevAL

Named-Entity-Recognition-BidirectionalLSTM-CNN-CoNLL

Keras implementation of Chiu and Nichols (2016)

NSC

Neural Sentiment Classification

pyStatParser

Simple Python Statistical Parser

search-benchmark-game

tantivy

Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust

tf_ner

Simple and Efficient Tensorflow implementations of NER models with tf.estimator and tf.data

universal-sentence-encoder-fine-tune

yoin

A Japanese Morphological Analyzer written in pure Rust

zotero-scholar-citations

Zotero plugin for auto-fetching numbers of citations from Google Scholar