Code for hyperboloid embeddings for knowledge graph entities

Related tags

Text Data & NLP hyperbolic-embeddings
Overview

Implementation for the papers:

Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs, Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian and Chandan Reddy, WWW 2021.

Code directory: hype_kg/codes/

ANTHEM: Attentive Hyperbolic Entity Model for Product Search, Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian and Chandan Reddy, WSDM 2022.

Code directory: product_matching/

Please refer these works if you find the code useful:

@inproceedings{10.1145/3442381.3449974,
author = {Choudhary, Nurendra and Rao, Nikhil and Katariya, Sumeet and Subbian, Karthik and Reddy, Chandan K.},
title = {Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs},
year = {2021},
isbn = {9781450383127},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3442381.3449974},
doi = {10.1145/3442381.3449974},
booktitle = {Proceedings of the Web Conference 2021},
pages = {1373–1384},
numpages = {12},
keywords = {knowledge graphs, hyperbolic space, Representation learning, reasoning queries},
location = {Ljubljana, Slovenia},
series = {WWW '21}
}

@inproceedings{choudhary2022anthem,
author = {Choudhary, Nurendra and Rao, Nikhil and Katariya, Sumeet and Subbian, Karthik and Reddy, Chandan K.},
title = {ANTHEM: Attentive Hyperbolic Entity Model for Product Search},
year = {2022},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
booktitle = {{WSDM} '22: The Fifteenth {ACM} International Conference on Web Search
               and Data Mining, Phoenix, AZ, USA, February 21-25, 2022},
location = {Phoenix, AZ, USA},
series = {WSDM '22}
}
Comments
  • Cannot Reproduce Results on hyper_kg

    Cannot Reproduce Results on hyper_kg

    Hi @Akirato @nikrao ,

    Thanks for your great work on HypE! However, I have been trying to reproduce your excellent results on FB15k-237, but to find the hyper-parameters you have provided in example_hype.sh to be the same for all default datasets. The consequent results are much poorer than your report.

    Could you please provide the reproducible hyper-parameters in the example_hype.sh? Thanks again for your help.

    opened by Xiao9905 19
  • The warehouse lacks core code？

    The warehouse lacks core code？

    Hello, from the README, I find that the model.py file should exist under the manifolders folder, the dataloader.py file should exist under the codes folder, and the hyperbolicity.py file should exist under the utils folder, but I don't find these files in the code repository. Looking forward to your reply.

    opened by zhiweihu1103 6
  • Changed a redundant dependency from tensorflow_manopt to tensorflow_riemopt

    Changed a redundant dependency from tensorflow_manopt to tensorflow_riemopt

    Issue #, if available:

    Description of changes:

    By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

    opened by Akirato 1
  • Changed the dependency from tensorflow-manopt to tensorflow-riemopt

    Changed the dependency from tensorflow-manopt to tensorflow-riemopt

    Issue #, if available:

    Description of changes:

    By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

    opened by Akirato 0
  • Updated README with resolution to issues.

    Updated README with resolution to issues.

    Issue #, if available:

    Description of changes:

    By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

    opened by Akirato 0
  • Update README.md

    Update README.md

    Issue #, if available:

    Description of changes:

    By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

    opened by Akirato 0
  • Reorganized the repository, so we add other hyperbolic works in the future.

    Reorganized the repository, so we add other hyperbolic works in the future.

    Issue #, if available:

    Description of changes:

    By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

    opened by Akirato 0
  • How to deal with DBpedia dataset?

    How to deal with DBpedia dataset?

    Hi, thanks for the excellent work, recently, i am reproducing the result on the DBpedia dataset. I download the dataset on the kaggle dataset, but I dont know how to construrt the triples. As you mentioned, it contains 34575 entities and 240942 edges. The download training set contains 240942 edges, but i do not quite understand how is 34575 entities are obtained. Can you provide some more details about the dbpedia dataset.

    opened by chandeler 0
  • attention in hype directly uses torch.mm

    attention in hype directly uses torch.mm

    hi,thanks for the wonderful work! when reproducing the code,I am wondering is it reasonable to directly uses torch.mm to calculate the attention value in the hyperbolic space?

    opened by chandeler 0
Owner
null
GitHub
Index different CKAN entities in Solr, not just datasets

ckanext-sitesearch Index different CKAN entities in Solr, not just datasets Requirements This extension requires CKAN 2.9 or higher and Python 3 Featu

Open Knowledge Foundation 3 Dec 2, 2022
Shared code for training sentence embeddings with Flax / JAX

flax-sentence-embeddings This repository will be used to share code for the Flax / JAX community event to train sentence embeddings on 1B+ training pa

Nils Reimers 23 Dec 30, 2022
Knowledge Graph,Question Answering System，基于知识图谱和向量检索的医疗诊断问答系统

Knowledge Graph,Question Answering System，基于知识图谱和向量检索的医疗诊断问答系统

wangle 823 Dec 28, 2022
open-information-extraction-system, build open-knowledge-graph(SPO, subject-predicate-object) by pyltp(version==3.4.0)

中文开放信息抽取系统, open-information-extraction-system, build open-knowledge-graph(SPO, subject-predicate-object) by pyltp(version==3.4.0)

null 7 Nov 2, 2022
Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge. Proceedings of EMNLP 2021

AAGCN-ACSA EMNLP 2021 Introduction This repository was used in our paper: Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment An

Akuchi 36 Dec 18, 2022
A framework for evaluating Knowledge Graph Embedding Models in a fine-grained manner.

A framework for evaluating Knowledge Graph Embedding Models in a fine-grained manner.

NEC Laboratories Europe 13 Sep 8, 2022
Large-scale Knowledge Graph Construction with Prompting

Large-scale Knowledge Graph Construction with Prompting across tasks (predictive and generative), and modalities (language, image, vision + language, etc.)

ZJUNLP 161 Dec 28, 2022
Sentence Embeddings with BERT & XLNet

Sentence Transformers: Multilingual Sentence Embeddings using BERT / RoBERTa / XLM-RoBERTa & Co. with PyTorch This framework provides an easy method t

Ubiquitous Knowledge Processing Lab 9.1k Jan 2, 2023
Sentence Embeddings with BERT & XLNet

Sentence Transformers: Multilingual Sentence Embeddings using BERT / RoBERTa / XLM-RoBERTa & Co. with PyTorch This framework provides an easy method t

Ubiquitous Knowledge Processing Lab 4.2k Feb 18, 2021
SimCSE: Simple Contrastive Learning of Sentence Embeddings

SimCSE: Simple Contrastive Learning of Sentence Embeddings This repository contains the code and pre-trained models for our paper SimCSE: Simple Contr

Princeton Natural Language Processing 2.5k Jan 7, 2023
A library for Multilingual Unsupervised or Supervised word Embeddings

MUSE: Multilingual Unsupervised and Supervised Embeddings MUSE is a Python library for multilingual word embeddings, whose goal is to provide the comm

Facebook Research 3k Jan 6, 2023
InferSent sentence embeddings

InferSent InferSent is a sentence embeddings method that provides semantic representations for English sentences. It is trained on natural language in

Facebook Research 2.2k Dec 27, 2022
Cải thiện Elasticsearch trong bài toán semantic search sử dụng phương pháp Sentence Embeddings

Cải thiện Elasticsearch trong bài toán semantic search sử dụng phương pháp Sentence Embeddings Trong bài viết này mình sẽ sử dụng pretrain model SimCS

Vo Van Phuc 18 Nov 25, 2022
PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

Poincaré Embeddings for Learning Hierarchical Representations PyTorch implementation of Poincaré Embeddings for Learning Hierarchical Representations

Facebook Research 1.6k Dec 29, 2022
Korean Simple Contrastive Learning of Sentence Embeddings using SKT KoBERT and kakaobrain KorNLU dataset

KoSimCSE Korean Simple Contrastive Learning of Sentence Embeddings implementation using pytorch SimCSE Installation git clone https://github.com/BM-K/

null 34 Nov 24, 2022
Original implementation of the pooling method introduced in "Speaker embeddings by modeling channel-wise correlations"

Speaker-Embeddings-Correlation-Pooling This is the original implementation of the pooling method introduced in "Speaker embeddings by modeling channel

Themos Stafylakis 10 Apr 30, 2022
An easy-to-use Python module that helps you to extract the BERT embeddings for a large text dataset (Bengali/English) efficiently.

An easy-to-use Python module that helps you to extract the BERT embeddings for a large text dataset (Bengali/English) efficiently.

Khalid Saifullah 37 Sep 5, 2022
BPEmb is a collection of pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) and trained on Wikipedia.

BPEmb is a collection of pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) and trained on Wikipedia. Its intended use is as input for neural models in natural language processing.

Benjamin Heinzerling 1.1k Jan 3, 2023
🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy

floret: fastText + Bloom embeddings for compact, full-coverage vectors with spaCy floret is an extended version of fastText that can produce word repr

Explosion 222 Dec 16, 2022