Share This Author
Stance Detection with Bidirectional Conditional Encoding
- Isabelle Augenstein, Tim Rocktäschel, Andreas Vlachos, Kalina Bontcheva
- Computer ScienceEMNLP
- 17 June 2016
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 either…
SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications
- Isabelle Augenstein, Mrinal Das, S. Riedel, Lakshmi Vikraman, A. McCallum
- Computer Science*SEMEVAL
- 10 April 2017
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 and…
A Diagnostic Study of Explainability Techniques for Text Classification
A comprehensive list of diagnostic properties for evaluating existing explainability techniques is developed and it is found that the gradient-based explanations perform best across tasks and model architectures, and further insights into the properties are presented.
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.
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.
A simple but tough-to-beat baseline for the Fake News Challenge stance detection task
- B. Riedel, Isabelle Augenstein, Georgios P. Spithourakis, S. Riedel
- Computer ScienceArXiv
- 11 July 2017
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.
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.
emoji2vec: Learning Emoji Representations from their Description
- Ben Eisner, Tim Rocktäschel, Isabelle Augenstein, Matko Bosnjak, S. Riedel
- Computer ScienceSocialNLP@EMNLP
- 27 September 2016
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.
MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims
An in-depth analysis of the largest publicly available dataset of naturally occurring factual claims, collected from 26 fact checking websites in English, paired with textual sources and rich metadata, and labelled for veracity by human expert journalists is presented.
Sluice networks: Learning what to share between loosely related tasks
- Sebastian Ruder, Joachim Bingel, Isabelle Augenstein, Anders Søgaard
- Computer ScienceArXiv
- 23 May 2017
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.