andy-wagner Goto Github PK

gpt-embeddings

Fast Text Embeddings retrofitted using the Google Product Taxonomy (GPT) Tree

granne

Graph-based Approximate Nearest Neighbor Search

graph_based_recommendation_engine_for_tags

Search for a term/tag in the graph and return the sorted (based on edge weights) list of tags which are related to the search query

graphjet

GraphJet is a real-time graph processing library.

grobid-quantities

GROBID extension for identifying and normalizing physical quantities.

gru4rec

GRU4Rec is the cleaned & simplified implementation of the algorithm of the "Session-based Recommendations with Recurrent Neural Networks" paper, published at ICLR 2016. The code is stripped of features that we had found to be unhelpful in increasing accuracy.

gtnw-guessthenextword

Efficient word co-occurrence statistics computation software

hesml

HESML Java software library of ontology-based semantic similarity measures and information content models

hierarchical-embedding-model-for-personalized-product-search

An implementation of the Hierarchical Embedding Model (HEM) for personalized product search

hnswlib

Java library for approximate nearest neighbors search using Hierarchical Navigable Small World graphs

hnswlib-jna

Native-Like Performance for Nearest Neighbor Search in Java Applications using Hnswlib and Java Native Access

homonym

A mini web crawler to get hundreds of websites' content based on a list of keywords.

hyperscan-java

Match tens of thousands of regular expressions within milliseconds - Java bindings for Intel's hyperscan 5

ice

ICE: Item Concept Embedding

ieturk

Intuitive Annotation Tool for Information Extraction / Named Entity Recognition using localturk / Amazon Mechanical Turk

image-similarity

Library to find most similar items based on images

image-similarity-deep-ranking

image_search_engine

Image search engine

implicit

Fast Python Collaborative Filtering for Implicit Datasets

improving-semantic-topic-clustering-for-search-queries-with-word-co-occurrence

Uncovering common themes from a large number of unor- ganized search queries is a primary step to mine insights about aggregated user interests. Common topic model- ing techniques for document modeling often face sparsity problems with search query data as these are much shorter than documents. We present two novel techniques that can discover semantically meaningful topics in search queries: i) word co-occurrence clustering generates topics from words frequently occurring together; ii) weighted bigraph cluster- ing uses URLs from Google search results to induce query similarity and generate topics. We exemplify our proposed methods on a set of Lipton brand as well as make-up & cos- metics queries. A comparison to standard LDA clustering demonstrates the usefulness and improved performance of the two proposed methods. keywords: search queries, topic clustering, word co- occurrence, bipartite graph, co-clustering.

in-memory-cooccurrence

Analyze for significant cooccurrence using Mahout sparse matrices

indexer4j

Simple full text indexing and searching library for Java

instatrie

Trie-Based Prefix Index for Java

interactive-dictionary

In this program, the user interacts with a dictionary. The user can input a word, part of speech, and filter the dictionary by part of speech. The Java program interacts with an enum to pull data from. There are still a bit of fixes to make, but the program overall works.

interactive-elastic-analyzer

Interactive Elasticsearch Analyzer

interactive-search-engine

Based on a web crawler, stored term/document frequency matrix from collected logs, implemented cosine similarity against the query, returned document URLs ordered by similarity.

ip-nsw

Implementation of ip-nsw from Non-metric Similarity Graphs for Maximum Inner Product Search

ipa-dict

Monolingual wordlists with pronunciation information in IPA

ipredict

Sequence Prediction Framework

ir-project

Project for the Information Retrieval course at the University of Padova: "GRAS Stemmer".