Search Results for author: Carl Allen

Found 12 papers, 6 papers with code

Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs

no code implementations26 Sep 2022 Đorđe Miladinović, Kumar Shridhar, Kushal Jain, Max B. Paulus, Joachim M. Buhmann, Carl Allen

In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning.

Representation Learning

Towards a Theoretical Understanding of Word and Relation Representation

no code implementations1 Feb 2022 Carl Allen

To address this: 1. we theoretically justify the empirical observation that particular geometric relationships between word embeddings learned by algorithms such as word2vec and GloVe correspond to semantic relations between words; and 2. we extend this correspondence between semantics and geometry to the entities and relations of knowledge graphs, providing a model for the latent structure of knowledge graph representation linked to that of word embeddings.

Knowledge Graphs Word Embeddings +1

Learning the Prediction Distribution for Semi-Supervised Learning with Normalising Flows

1 code implementation6 Jul 2020 Ivana Balažević, Carl Allen, Timothy Hospedales

In this work, we propose a probabilistically principled general approach to SSL that considers the distribution over label predictions, for labels of different complexity, from "one-hot" vectors to binary vectors and images.

General Classification Image Classification +3

A Probabilistic Model for Discriminative and Neuro-Symbolic Semi-Supervised Learning

no code implementations10 Jun 2020 Carl Allen, Ivana Balažević, Timothy Hospedales

Much progress has been made in semi-supervised learning (SSL) by combining methods that exploit different aspects of the data distribution, e. g. consistency regularisation relies on properties of $p(x)$, whereas entropy minimisation pertains to the label distribution $p(y|x)$.

Image Augmentation Logical Reasoning

Multi-scale Attributed Node Embedding

4 code implementations28 Sep 2019 Benedek Rozemberczki, Carl Allen, Rik Sarkar

We present network embedding algorithms that capture information about a node from the local distribution over node attributes around it, as observed over random walks following an approach similar to Skip-gram.

Network Embedding

Interpreting Knowledge Graph Relation Representation from Word Embeddings

no code implementations ICLR 2021 Carl Allen, Ivana Balažević, Timothy Hospedales

Many models learn representations of knowledge graph data by exploiting its low-rank latent structure, encoding known relations between entities and enabling unknown facts to be inferred.

Link Prediction Word Embeddings

Multi-relational Poincaré Graph Embeddings

1 code implementation NeurIPS 2019 Ivana Balažević, Carl Allen, Timothy Hospedales

Hyperbolic embeddings have recently gained attention in machine learning due to their ability to represent hierarchical data more accurately and succinctly than their Euclidean analogues.

Entity Embeddings Knowledge Graphs +1

Analogies Explained: Towards Understanding Word Embeddings

no code implementations28 Jan 2019 Carl Allen, Timothy Hospedales

Word embeddings generated by neural network methods such as word2vec (W2V) are well known to exhibit seemingly linear behaviour, e. g. the embeddings of analogy "woman is to queen as man is to king" approximately describe a parallelogram.

Word Embeddings

Hypernetwork Knowledge Graph Embeddings

1 code implementation21 Aug 2018 Ivana Balažević, Carl Allen, Timothy M. Hospedales

Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness.

Knowledge Graph Embeddings Knowledge Graphs +1

What the Vec? Towards Probabilistically Grounded Embeddings

no code implementations NeurIPS 2019 Carl Allen, Ivana Balažević, Timothy Hospedales

We show that different interactions between PMI vectors reflect semantic word relationships, such as similarity and paraphrasing, that are encoded in low dimensional word embeddings under a suitable projection, theoretically explaining why embeddings of W2V and GloVe work.

Graph Embedding Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.