Knowledge Graphs @ AAAI 2020

  1. KG-Augmented Language Models: in different flavours
  2. Entity Matching in Heterogeneous KGs: finally no manual mappings
  3. KG Completion and Link Prediction: neuro-symbolic and temporal KGs
  4. KG-based Conversational AI and Question Answering: going big
  5. Conclusion

KG-Augmented Language Models In Different Flavours

We first noted the trend of infusing some structured knowledge into LMs in the review of EMNLP 2019, and 2020 is officially (declared by me 😊) a year of KG-Augmented LMs: more large-scale training corpora appears together with pre-trained models (and multilingual, too! 🌍).

Source: Hayashi et al
Source: Liu et al

Entity Matching in Heterogeneous KGs

Different KGs have their own schema for modelling their entities, i.e., different set of properties that might only partially overlap, or totally different URIs. For instance, the city of Berlin in Wikidata has URI while in DBpedia it is . If you have a KG comprised of such heterogeneous URIs (that in fact describe one real-world Berlin) you either will consider those entities as independent or need to write/find custom mappings that will explicitly pair those URIs as same (e.g., with owl:sameAs predicate often used in open domain KGs). Maintaining mappings for large-scale evolving graphs is quite a cumbersome task 🤯 . Previously, ontology-based alignment tools relied only on such mappings to identify similar entities. Today, we have GNNs to learn such mappings automatically with just a small training set!

Source: Sun et al

Knowledge Graph Completion and Link Prediction

AAAI’20 marks and outlines two growing trends: neuro-symbolic computation is back and shiny; temporal KGs are getting more traction.

Source: Minervini et al
Source: Hildebrandt et al
Visualization of embeddings from WN18RR. Source: Zhang et al

KG-based Conversational AI and Question Answering

AAAI’20 hosted the Dialogue State Tracking Workshop (DSTC8). The event brought together the experts in Conversational AI including folks from Google Assistant, Amazon Alexa, and DeepPavlov 🎅.

Source: Rastogi et al.
A model for Visual Storytelling. Source: Hsu et al


We had a brief look on KGs applied in rather NLP-related tasks. Surely, there are applications in other domains like structuring scene graphs in Computer vision or Bioinformatics where graphs, for instance, help to study molecules. I hope now your backlog increased just a little bit 😉.



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Michael Galkin

Michael Galkin

Postdoc @ Mila & McGill University. Working on Knowledge Graphs, Graph ML, and NLP