Knowledge Base Completion: Baselines Strike Back

Kadlec, Rudolf; Bajgar, Ondřej; Kleindienst, Jan

doi:10.18653/v1/w17-2609

Cited by 125 publications

(132 citation statements)

References 28 publications

(18 reference statements)

Supporting

Mentioning

120

Contrasting

Order By: Relevance

“…Any KBE model can be used for learning M. For evaluation, we adopt DistMult (Yang et al, 2014) for its state-of-the art performance over many other KBE models (Kadlec et al, 2017). The scoring function of DistMult is defined as follows:…”

Section: Inference Modelmentioning

confidence: 99%

Lifelong and Interactive Learning of Factual Knowledge in Dialogues

Mazumder¹,

Liu²,

Wang³

et al. 2019

Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue

View full text Add to dashboard Cite

Dialogue systems are increasingly using knowledge bases (KBs) storing real-world facts to help generate quality responses. However, as the KBs are inherently incomplete and remain fixed during conversation, it limits dialogue systems' ability to answer questions and to handle questions involving entities or relations that are not in the KB. In this paper, we make an attempt to propose an engine for Continuous and Interactive Learning of Knowledge (CILK) for dialogue systems to give them the ability to continuously and interactively learn and infer new knowledge during conversations. With more knowledge accumulated over time, they will be able to learn better and answer more questions. Our empirical evaluation shows that CILK is promising.

show abstract

Section: Inference Modelmentioning

confidence: 99%

Lifelong and Interactive Learning of Factual Knowledge in Dialogues

Mazumder¹,

Liu²,

Wang³

et al. 2019

Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue

View full text Add to dashboard Cite

show abstract

“…Knolwedge Graph Embeddings: To obtain the embedding from this graph, we use state-ofthe-art DistMult model (Bishan Yang and Deng, 2015). The choice is inspired by Kadlec et al (2017), which reports that an appropriately tuned DistMult model can produce similar or better performance while compared with the competing knowledge graph embedding models. Dist-Mult model embeds entities (nodes) and relations (edges) as vectors.…”

Section: Proposed Approachmentioning

confidence: 99%

Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs

Sharma¹,

Santra²,

Jana³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Recently, biomedical version of embeddings obtained from language models such as BioELMo have shown state-of-the-art results for the textual inference task in the medical domain. In this paper, we explore how to incorporate structured domain knowledge, available in the form of a knowledge graph (UMLS), for the Medical NLI task. Specifically, we experiment with fusing embeddings obtained from knowledge graph with the state-of-theart approaches for NLI task, which mainly rely on contextual word embeddings. We also experiment with fusing the domain-specific sentiment information for the task. Experiments conducted on MedNLI dataset clearly show that this strategy improves the baseline BioELMo architecture for the Medical NLI task 1 .

show abstract

“…It has also been shown that the presence of relations between candidate pairs can be an extremely strong signal in some cases [31]. Moreover, recent works showed that a hyperparameter tuning has been overlooked and that a simple method, such as DistMult, can achieve state-of-the-art performance when well tuned [10].…”

Section: Related Workmentioning

confidence: 99%

Detection of Relation Assertion Errors in Knowledge Graphs

Melo

Paulheim

2017

Proceedings of the Knowledge Capture Conference

View full text Add to dashboard Cite

Although the link prediction problem, where missing relation assertions are predicted, has been widely researched, error detection did not receive as much attention. In this paper, we investigate the problem of error detection in relation assertions of knowledge graphs, and we propose an error detection method which relies on path and type features used by a classifier for every relation in the graph exploiting local feature selection. We perform an extensive evaluation on a variety of datasets, backed by a manual evaluation on DBpedia and NELL, and we propose and evaluate heuristics for the selection of relevant graph paths to be used as features in our method.

show abstract

Knowledge Base Completion: Baselines Strike Back

Cited by 125 publications

References 28 publications

Lifelong and Interactive Learning of Factual Knowledge in Dialogues

Lifelong and Interactive Learning of Factual Knowledge in Dialogues

Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs

Detection of Relation Assertion Errors in Knowledge Graphs

Contact Info

Product

Resources

About