AllAcronyms
30 May 2020
AllAcronyms
Labels:
big data
,
data science
,
linked data
,
natural language processing
,
semantic web
,
text analytics
SimFin
Labels:
big data
,
data science
,
deep learning
,
finance
,
machine learning
,
natural language processing
,
text analytics
24 May 2020
Magenta
Labels:
big data
,
data science
,
deep learning
,
machine learning
,
music
,
natural language processing
23 May 2020
22 May 2020
20 May 2020
GNN Datasets and Implementations
Citation Networks:
Biochemical:
Social Networks:
Knowledge Graphs:
Repos:
Implementations:
GNN Models:
- PubMed
- Cora
- Citeseer
- DBLP
Biochemical:
- MUTAG
- NCI-1
- PPI
- D&D
- PROTEIN
Social Networks:
- BlogCatalog
Knowledge Graphs:
- FB13
- FB15K
- FB15K237
- WN11
- WN18
- WN18RR
Repos:
- Network Repository
- Graph Kernel Datasets
- Relational Dataset Repository
- Stanford Large Network Dataset Collection
- Open Graph Benchmark
Implementations:
GNN Models:
- GGNN
- Neural FPs
- ChebNet
- DNGR
- SDNE
- GAE
- DRNE
- Structured RNN
- DCNN
- GCN
- CayleyNet
- GraphSage
- GAT
- CLN
- ECC
- MPNN
- MoNet
- JK-Net
- SSE
- LGCN
- FastGCN
- DiffPool
- GraphRNN
- MolGAN
- NetGAN
- DCRNN
- ST-GCN
- RGCN
- AS-GCN
- DGCN
- GaAN
- DGI
- GraphWaveNet
- HAN
Labels:
big data
,
data science
,
deep learning
,
linked data
,
natural language processing
,
semantic web
,
text analytics
Deep Fact Checking
In general, a fact verification attempts to obtain supported evidence from text in order to verify claims. The labels can contain "supported", "refuted", or "not enough info" to classify a claim. In many respects, this is a natural language interpretation process of entailments. Some methods in this process may incorporate evidence concatenation or individual evidence-claim pairs. Unfortunately, such methods are limited in sufficiently identifying relational and logical attributes of information from the evidence. In order to integrate and reason over several evidences, one has to utilize a graph network for aggregation and reasoning to enable a connected evidence graph with a means of identifying information propagation. A deep workflow process using deep learning with graphs is one approach. The first step in the process is to use a sentence encoder with Bert. The second step is to combine evidence reasoning with aggregation in a modified graph attention network. DAGs can further be utilized for relation and event extraction representations and linkage.
Labels:
big data
,
data science
,
deep learning
,
linked data
,
natural language processing
,
semantic web
,
text analytics
12 May 2020
Text Production Datasets
Data-to-Text Generation
- WikiBio
- WikiNLG
- SBNation
- RotoWire
- SR'18
- E2E
- Summarization (DUC2001-2005)
- CNN
- DailyMail
- NYTimes
- NewsRoom
- XSum
- Simplification
- PWKP
- WikiLarge
- Newsela
- Compression
- Gigaword
- Automatic Creation of Extractive Sentence/Compression
- MASC
- Multi-Reference Corpus for Abstractive Compression
- Cohn and Lapata's Corpus
- Paraphrasing
- MSRP
- PIT-2015
- Twitter News URL Corpus
- ParaNMT-80
- ParaNMT-50
- MTC
- PPDB
7 May 2020
6 May 2020
5 May 2020
Moogsoft
Labels:
artificial intelligence
,
big data
,
data science
,
devops
,
event-driven
,
events
,
machine learning
4 May 2020
Social Mixed Reality
In times of social distancing, people still want to be able to connect. Bars are empty. Parks are relatively empty. Seems like the linear social networking sites have become a bit of a trite concept. The next phase of socializing on the web is likely to be in the form of mixed reality - combining some sort of augmented reality with virtual reality concepts. This concept of virtual connection will enable people to meet in all sorts of different ways and maintain a safe distance if they need. It will also help people that are medically ill in hospital or busy at work to be able to connect as well without physically leaving their place of location. It will also enable people to connect across the globe which means reduced need for frequent travelling. Communications is likely to take on new forms of medium as people live more complicated lives with socially unique circumstances. In fact, enabling people with children to socially connect consciously as well within safe environment controls. Such virtual environments may also extend into remote support work to customer service and sales/marketing interactions. Similarly, it can also be extended towards socially connecting collective religious prayer such as for churches, synagogues, mosques, and temples allowing people to not have to physically visit such places while still making their regular rituals of worship remotely. In many respects, non-muslims, may want to visit mecca, where mixed reality could allow them to have a near real-time experience. On other hand, people may want to visit jerusalem from the convenience of their home. On other hand, an individual might want to join a global network of virtually connected prayer gatherings, even a social party scene like a wedding, concert or a festival.
3 May 2020
Subscribe to:
Posts
(
Atom
)