Timothy Hospedales


2019

pdf bib
TuckER: Tensor Factorization for Knowledge Graph Completion
Ivana Balazevic | Carl Allen | Timothy Hospedales
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Knowledge graphs are structured representations of real world facts. However, they typically contain only a small subset of all possible facts. Link prediction is a task of inferring missing facts based on existing ones. We propose TuckER, a relatively straightforward but powerful linear model based on Tucker decomposition of the binary tensor representation of knowledge graph triples. TuckER outperforms previous state-of-the-art models across standard link prediction datasets, acting as a strong baseline for more elaborate models. We show that TuckER is a fully expressive model, derive sufficient bounds on its embedding dimensionalities and demonstrate that several previously introduced linear models can be viewed as special cases of TuckER.

2018

pdf bib
Learning Unsupervised Word Translations Without Adversaries
Tanmoy Mukherjee | Makoto Yamada | Timothy Hospedales
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Word translation, or bilingual dictionary induction, is an important capability that impacts many multilingual language processing tasks. Recent research has shown that word translation can be achieved in an unsupervised manner, without parallel seed dictionaries or aligned corpora. However, state of the art methods unsupervised bilingual dictionary induction are based on generative adversarial models, and as such suffer from their well known problems of instability and hyper-parameter sensitivity. We present a statistical dependency-based approach to bilingual dictionary induction that is unsupervised – no seed dictionary or parallel corpora required; and introduces no adversary – therefore being much easier to train. Our method performs comparably to adversarial alternatives and outperforms prior non-adversarial methods.

2016

pdf bib
Gaussian Visual-Linguistic Embedding for Zero-Shot Recognition
Tanmoy Mukherjee | Timothy Hospedales
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing