• Publications
  • Influence
Stance Detection with Bidirectional Conditional Encoding
Stance detection is the task of classifying the attitude expressed in a text towards a target such as Hillary Clinton to be "positive", negative" or "neutral". Previous work has assumed that eitherExpand
SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications
We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks andExpand
LODifier: Generating Linked Data from Unstructured Text
LODifier is an approach that combines deep semantic analysis with named entity recognition, word sense disambiguation and controlled Semantic Web vocabularies in order to extract named entities and relations between them from text and to convert them into an RDF representation which is linked to DBpedia and WordNet. Expand
Turing at SemEval-2017 Task 8: Sequential Approach to Rumour Stance Classification with Branch-LSTM
A LSTM-based sequential model is proposed that, through modelling the conversational structure of tweets, achieves an accuracy of 0.784 on the RumourEval test set outperforming all other systems in Subtask A. Expand
A simple but tough-to-beat baseline for the Fake News Challenge stance detection task
This paper presents their stance detection system, which claimed third place in Stage 1 of the Fake News Challenge, and proposes it as the 'simple but tough-to-beat baseline' for the FakeNews Challenge stance detection task. Expand
Latent Multi-Task Architecture Learning
This work presents an approach that learns a latent multi-task architecture that jointly addresses (a)--(c) and consistently outperforms previous approaches to learning latent architectures for multi- task problems and achieves up to 15% average error reductions over common approaches to MTL. Expand
emoji2vec: Learning Emoji Representations from their Description
It is demonstrated, for the downstream task of sentiment analysis, that emoji embeddings learned from short descriptions outperforms a skip-gram model trained on a large collection of tweets, while avoiding the need for contexts in which emoji need to appear frequently in order to estimate a representation. Expand
Sluice networks: Learning what to share between loosely related tasks
Sluice Networks is introduced, a general framework for multi-task learning where trainable parameters control the amount of sharing and it is shown that a) label entropy is predictive of gains in sluice networks, confirming findings for hard parameter sharing and b) while slUice networks easily fit noise, they are robust across domains in practice. Expand
Discourse-aware rumour stance classification in social media using sequential classifiers
It is shown that sequential classifiers that exploit the use of discourse properties in social media conversations while using only local features, outperform non-sequential classifiers and that LSTM using a reduced set of features can outperform the other sequentialclassifiers. Expand
A Supervised Approach to Extractive Summarisation of Scientific Papers
This paper introduces a new dataset for summarisation of computer science publications by exploiting a large resource of author provided summaries and develops models on the dataset making use of both neural sentence encoding and traditionally used summarisation features. Expand