WebBrain: Joint Neural Learning of Large-Scale Commonsense Knowledge

Chen, Jiaqiang; Tandon, Niket; Hariman, Charles Darwis; Melo, Gerard de

doi:10.1007/978-3-319-46523-4_7

Cited by 8 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…WebChild 2.0 has already been effective in providing background knowledge to applications such as visual question answering (Wang et al, 2016) and neural relation prediction (Chen et al, 2016). The WebChild 2.0 data is freely downloadable at http://www.mpi-inf.mpg.…”

Section: Discussionmentioning

confidence: 99%

WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation

Tandon¹,

Melo²,

Weikum

2017

Proceedings of ACL 2017, System Demonstrations

Self Cite

View full text Add to dashboard Cite

Despite important progress in the area of intelligent systems, most such systems still lack commonsense knowledge that appears crucial for enabling smarter, more human-like decisions. In this paper, we present a system based on a series of algorithms to distill fine-grained disambiguated commonsense knowledge from massive amounts of text. Our WebChild 2.0 knowledge base is one of the largest commonsense knowledge bases available, describing over 2 million disambiguated concepts and activities, connected by over 18 million assertions.

show abstract

Section: Discussionmentioning

confidence: 99%

WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation

Tandon¹,

Melo²,

Weikum

2017

Proceedings of ACL 2017, System Demonstrations

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sev-eral authors have tried to improve word embeddings by incorporating external knowledge bases. For example, some authors have proposed models which combine the loss function of a word embedding model, to ensure that word vectors are predictive of their context words, with the loss function of a knowledge graph embedding model, to encourage the word vectors to additionally be predictive of a given set of relational facts (Xu et al, 2014;Celikyilmaz et al, 2015;Chen et al, 2016). Other authors have used knowledge bases in a more restricted way, by taking the fact that two words are linked to each other in a given knowledge graph as evidence that their word vectors should be similar Speer et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

“…First, rather than relying on an external knowledge base, or other forms of supervision, as in e.g. (Chen et al, 2016), our method is completely unsupervised, as our only input consists of a text corpus. Second, whereas existing work has focused on methods for improving word embeddings, our aim is to learn vector representations that are complementary to standard word embeddings.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Relational Word Embeddings

Camacho-Collados¹,

Espinosa-Anke²,

Schockaert³

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

While word embeddings have been shown to implicitly encode various forms of attributional knowledge, the extent to which they capture relational information is far more limited. In previous work, this limitation has been addressed by incorporating relational knowledge from external knowledge bases when learning the word embedding. Such strategies may not be optimal, however, as they are limited by the coverage of available resources and conflate similarity with other forms of relatedness. As an alternative, in this paper we propose to encode relational knowledge in a separate word embedding, which is aimed to be complementary to a given standard word embedding. This relational word embedding is still learned from co-occurrence statistics, and can thus be used even when no external knowledge base is available. Our analysis shows that relational word vectors do indeed capture information that is complementary to what is encoded in standard word embeddings.

show abstract

“…Similarly, Chen et al [31] presented an approach for harvesting commonsense knowledge that relies on joint learning model from web-scale data. The model learn vector representations of commonsensical words and relations jointly using large-scale web information extractions and general corpus co-occurrences.…”

Section: Arxiv:180904708v2 [Csai] 27 Sep 2018mentioning

confidence: 99%

Semantically Enhanced Models for Commonsense Knowledge Acquisition

Alhussien

Wang

NengSheng

2018

2018 IEEE International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

Commonsense knowledge is paramount to enable intelligent systems. Typically, it is characterized as being implicit and ambiguous, hindering thereby the automation of its acquisition. To address these challenges, this paper presents semantically enhanced models to enable reasoning through resolving part of commonsense ambiguity. The proposed models enhance in a knowledge graph embedding framework for knowledge base completion. Experimental results show the effectiveness of the new semantic models in commonsense reasoning.

show abstract

WebBrain: Joint Neural Learning of Large-Scale Commonsense Knowledge

Cited by 8 publications

References 25 publications

WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation

WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation

Relational Word Embeddings

Semantically Enhanced Models for Commonsense Knowledge Acquisition

Contact Info

Product

Resources

About