A Summary of Recent SDA Contributions towards improving Entity Disambiguation, Linking and Prediction

Improvement of State of the Art on different Tasks.
Figure 1: Overall Approach: Φrefers to the ordered set of triples from the KG for a candidate entity while Φ max ⊆ Φ, is the maximum number of triples that fits in the sequence length. For brevity: N→”National”, H→”Highway”, desc→”description.
Figure 2: The red and green dots represent entity candidate vectors for the given question. The green vectors are the correct entity vectors. Although they belong to the same entity they are not the same dots because they come from different n-grams. At each time step the Pointer Network points to one of the input candidate entities as the linked entity, or to the END symbol to indicate nochoice.
Figure 3: Proposed Approach Arjun: Arjun consists of three tasks. First task identifies the surface forms using an attentive neural network. Second task induces background knowledge from the Local KG and associates each surface form with potential entity candidates. Third task links the potential entity candidates to the correct entity labels.
Figure 4: The mechanism in which STARE encodes a hyper-relational fact from Fig. 1.B. Qualifier pairs are passed through a composition functionφq, summed and transformed by Wq. The resulting vector is then merged viaγ, andφrwith the relation and object vector, respectively. Finally, nodeQ937aggregates mes-sages from this and other hyper-relational edges.
Figure 5: Geometric illustration of the translation terms considered in MDE.
Figure 6: illustration of the means and (diagonal) variances of entities and relations in a temporal Gaussian Embedding Space. The labels indicate their position. In the representations, we might infer that Bill ClintonwaspresidentOf USAi n 1998 and Barack Obama was president of USA in 2010

--

--

--

The Smart Data Analytics (SDA) research group at the University of Bonn working on #semantics, #machinelearning and #bigdata.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Hate speech detection with machine learning

How do you think your model will React  : Comparison between RTX 3070, M1 chip, Google Colab GPU

Why Kaggle Kernels is the Best Way to Run and Share Your Jupyter Notebook

PointPillars — 3D point clouds bounding box detection and tracking (PointNet, PointNet++, LaserNet…

Trajectory tracking for UAV with neural network Post 2/3

How to detect dog breeds from images using CNN?

What is Gradient Descent? How does it work?

Machine learning is much more than a good model

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
SDA Research

SDA Research

The Smart Data Analytics (SDA) research group at the University of Bonn working on #semantics, #machinelearning and #bigdata.

More from Medium

College Students are Left Out of Government Benefits Programs Because of Misconceptions of Who They…

Yield360

Greetings Yarn Lander🐱‍👓🐱‍🚀🐱‍👤🌈

You can use SketchUp to effortlessly STAND OUT