• Publications
  • Influence
Graph-to-Sequence Learning using Gated Graph Neural Networks
TLDR
This work proposes a new model that encodes the full structural information contained in the graph, couples the recently proposed Gated Graph Neural Networks with an input transformation that allows nodes and edges to have their own hidden representations, while tackling the parameter explosion problem present in previous work.
DyNet: The Dynamic Neural Network Toolkit
TLDR
DyNet is a toolkit for implementing neural network models based on dynamic declaration of network structure that has an optimized C++ backend and lightweight graph representation and is designed to allow users to implement their models in a way that is idiomatic in their preferred programming language.
A Discriminative Latent Variable Model for Statistical Machine Translation
TLDR
A translation model is presented which models derivations as a latent variable, in both training and decoding, and is fully discriminative and globally optimised, and results show that accounting for multiple derivations does indeed improve performance.
Learning how to Active Learn: A Deep Reinforcement Learning Approach
TLDR
A novel formulation of active learning is introduced by reframing the active learning as a reinforcement learning problem and explicitly learning a data selection policy, where the policy takes the role of the activelearning heuristic.
Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning
TLDR
It is found that word embeddings capture a surprising amount of information, and that, under suitable supervised training, vector subtraction generalises well to a broad range of relations, including over unseen lexical items.
QuEst - A translation quality estimation framework
TLDR
quest, an open source framework for machine translation quality estimation that allows the extraction of several quality indicators from source segments, their translations, external resources, as well as language tools, and provides machine learning algorithms to build quality estimation models.
Constructing Corpora for the Development and Evaluation of Paraphrase Systems
TLDR
A definition of paraphrase based on word alignments is adopted and it is shown that it yields high inter-annotator agreement, and an alternative agreement statistic is employed which is appropriate for structured alignment tasks.
Semi-supervised User Geolocation via Graph Convolutional Networks
TLDR
GCN, a multiview geolocation model based on Graph Convolutional Networks, that uses both text and network context is proposed, and it is found that highway network gates are essential for controlling the amount of useful neighbourhood expansion in GCN.
Incorporating Structural Alignment Biases into an Attentional Neural Translation Model
TLDR
The attentional neural translation model is extended to include structural biases from word based alignment models, including positional bias, Markov conditioning, fertility and agreement over translation directions.
Massively Multilingual Transfer for NER
TLDR
Evaluating on named entity recognition, it is shown that the proposed techniques for modulating the transfer are much more effective than strong baselines, including standard ensembling, and the unsupervised method rivals oracle selection of the single best individual model.
...
...