• Stars
    star
    66
  • Rank 468,167 (Top 10 %)
  • Language
    Scala
  • License
    Apache License 2.0
  • Created over 7 years ago
  • Updated over 5 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Algorithms and evaluation tools for extreme clustering

More Repositories

1

dilated-cnn-ner

Dilated CNNs for NER in TensorFlow
Python
244
star
2

box-embeddings

Box Embeddings as Modules
Python
100
star
3

diora

Deep Inside-Outside Recursive Autoencoder
Python
87
star
4

TypeNet

A Hierarchical Type system for fine grained entity typing
Python
51
star
5

metanlp

Meta-learning for NLP
Python
45
star
6

learned-string-alignments

Learning String Alignments for Entity Aliases
Python
38
star
7

stance

Learned string similarity for entity names using optimal transport.
Python
34
star
8

word2box

Capturing Set-Theoretic Semantics of Words using Box Embeddings
Python
33
star
9

watr-works

Scala
33
star
10

protoqa-data

Dataset for protoqa ("family feud") data
30
star
11

leopard

24
star
12

grinch

Scalable Hierarchical Clustering with Tree Grafting
Python
23
star
13

interactive_LM

Python
20
star
14

CSFCube

A Test Collection of Computer Science Papers for Faceted Query by Example
Python
18
star
15

inventor-disambiguation

Scala
16
star
16

Distributional-Inclusion-Vector-Embedding

Jupyter Notebook
15
star
17

geometric-graph-embedding

Python
12
star
18

conll2012-preprocess-parsing

Scripts for pre-processing the CoNLL-2012 dataset for syntactic dependency parsing.
Shell
12
star
19

fair-matching

Fair paper matching
Python
11
star
20

CE2ERE

Constrained learning using boxes for event-event relation extraction
Jupyter Notebook
11
star
21

gumbel-box-embeddings

Jupyter Notebook
11
star
22

box-mlc-iclr-2022

Official repository for the paper "Modeling Label Space Interactions in Multi-label Classification using Box Embeddings".
Jupyter Notebook
11
star
23

s-diora

Python
10
star
24

expLinkage

Supervised hierarchical clustering
Python
9
star
25

Softmax-CPR

Better output softmax alternatives for natural language generation
Python
8
star
26

anncur

Approximate Nearest Neighbor search using CUR Decomposition
Python
8
star
27

ProtoQA_GPT2

This is the GPT2 baseline for ProtoQA
Python
8
star
28

softmax_CPR_recommend

The code repository for "To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders"
Python
7
star
29

rexa1-metatagger

Java
5
star
30

author_coref

Author Disambiguation
Scala
5
star
31

knnlm-retrieval-quality

Python
4
star
32

protoqa-evaluator

Evaluation functions for ProtoQA dataset
Python
4
star
33

rexa1-pstotext

C
3
star
34

paper-header

Scala
3
star
35

institution_hierarchies

Python
3
star
36

iesl-sbt-base

SBT plugin providing lots of boilerplate dependencies, IESL repos, etc., to provide simple and consistent configuration of IESL SBT projects.
Scala
3
star
37

bibie

Research paper header and references field extraction
Scala
3
star
38

pdf2meta

Scala
3
star
39

namejuggler

Parsing, rearranging, and compatibility testing of person names (mostly in Western cultures). The problem is in general unsolvable due to cultural ambiguities, so we just make a simple heuristic attempt.
Scala
3
star
40

Boxes_for_Joint_hierarchy_AKBC_2020

Python
2
star
41

seal-neurips-2022

🦭 This is the official implementation for the paper [Structured Energy Network As a Loss](https://openreview.net/pdf?id=F0DowhX7_x).
Python
2
star
42

structured_prediction_baselines

Structure Prediction Baselines Using AllenNLP. Implements baselines for tasks like POS tagging, NER and SRL.
Jsonnet
2
star
43

rpp

Research Paper Processor
Scala
2
star
44

distantly-supervised-diora

Python
2
star
45

Multi_facet_recommendation

Jupyter Notebook
1
star
46

paper_coref

Paper/Citation Coreference
Scala
1
star
47

neural_relation_extraction

Python
1
star
48

bibmogrify

High-volume format translation and processing of scholarly citations and patents.
Scala
1
star
49

fuse_ttl

Technical Term List Generation for Fuse
Scala
1
star
50

paper-header-annotator-2

a paper header annotation tool based on Fabric.js and Play Framework
JavaScript
1
star
51

paper-header-annotator

An tool for annotating the headers of academic papers
JavaScript
1
star
52

score-paper-segmentation

A small utility which uses Jaccard Similarity of Bigrams to measure coarse paper segmentation
Python
1
star
53

iesl-pdf-to-text

JavaScript
1
star