xiongchenyan

KnowledgeIR

Knowledge graph based information retrieval

KnowledgeBasedRanking

init

CRCN

Coherence + Recurrent Neural Network + Convolutional Neural Network

PyClick

rcnn

Recurrent & convolutional neural network modules

REL

REL: Radboud Entity Linker

SPTAG

A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.

ake-datasets

Large, curated set of benchmark datasets for evaluating automatic keyphrase extraction algorithms.

alembic

⚗ A Jekyll boilerplate theme designed to be a starting point for any Jekyll website

ANCE

A novel embedding training algorithm leveraging ANN search and achieved SOTA retrieval on Trec DL 2019 and OpenQA benchmarks

bert-stable-fine-tuning

On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines

DiskANN

Graph based indices for approximate nearest neighbor search

eng-practices

Google's Engineering Practices documentation

esci-code

Open source implementation of the baselines presented in the Amazon Product Search KDD CUP 2022.

fastText

Library for fast text representation and classification.

kg4ir.github.io

SIGIR Workshop KG4IR: Knowledge Graphs and Semantics for Text Retrieval and Analysis

LeadingConversationalSearchbySuggestingUsefulQuestions

WebConf 2020 paper Leading Conversational Search by Suggesting Useful Questions

maml

Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

Megatron-LM

Ongoing research training transformer language models at scale, including: BERT & GPT-2

MS-MARCO-Web-Search

A large-scale information-rich web dataset, featuring millions of real clicked query-document labels

PaperReading

Some Interesting papers and ideas

pke

Python Keyphrase Extraction module

RAKE-tutorial

A python implementation of the Rapid Automatic Keyword Extraction

relevation

Information Retrieval Relevance Judging System

tensorflow

Computation using data flow graphs for scalable machine learning

torch-blocksparse

Block-sparse primitives for PyTorch

tSNE-Animation

Hacking sklearn's t-SNE implementation to animate embedding process

UDT-QA

Code for the paper "Open Domain Question Answering with A Unified Knowledge Interface" (ACL 2022)

website

Repo for CMU lab sites

writing-code-for-nlp-research-emnlp2018

A companion repository for the "Writing code for NLP Research" Tutorial at EMNLP 2018