Thomas Kober


pdf bib
Zero-shot Cross-Linguistic Learning of Event Semantics
Malihe Alikhani | Thomas Kober | Bashar Alhafni | Yue Chen | Mert Inan | Elizabeth Nielsen | Shahab Raji | Mark Steedman | Matthew Stone
Proceedings of the 15th International Conference on Natural Language Generation


pdf bib
Data Augmentation for Hypernymy Detection
Thomas Kober | Julie Weeds | Lorenzo Bertolini | David Weir
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

The automatic detection of hypernymy relationships represents a challenging problem in NLP. The successful application of state-of-the-art supervised approaches using distributed representations has generally been impeded by the limited availability of high quality training data. We have developed two novel data augmentation techniques which generate new training examples from existing ones. First, we combine the linguistic principles of hypernym transitivity and intersective modifier-noun composition to generate additional pairs of vectors, such as “small dog - dog” or “small dog - animal”, for which a hypernymy relationship can be assumed. Second, we use generative adversarial networks (GANs) to generate pairs of vectors for which the hypernymy relation can also be assumed. We furthermore present two complementary strategies for extending an existing dataset by leveraging linguistic resources such as WordNet. Using an evaluation across 3 different datasets for hypernymy detection and 2 different vector spaces, we demonstrate that both of the proposed automatic data augmentation and dataset extension strategies substantially improve classifier performance.


pdf bib
Aspectuality Across Genre: A Distributional Semantics Approach
Thomas Kober | Malihe Alikhani | Matthew Stone | Mark Steedman
Proceedings of the 28th International Conference on Computational Linguistics

The interpretation of the lexical aspect of verbs in English plays a crucial role in tasks such as recognizing textual entailment and learning discourse-level inferences. We show that two elementary dimensions of aspectual class, states vs. events, and telic vs. atelic events, can be modelled effectively with distributional semantics. We find that a verb’s local context is most indicative of its aspectual class, and we demonstrate that closed class words tend to be stronger discriminating contexts than content words. Our approach outperforms previous work on three datasets. Further, we present a new dataset of human-human conversations annotated with lexical aspects and present experiments that show the correlation of telicity with genre and discourse goals.

pdf bib
Going Beyond T-SNE: Exposing whatlies in Text Embeddings
Vincent Warmerdam | Thomas Kober | Rachael Tatman
Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)

We introduce whatlies, an open source toolkit for visually inspecting word and sentence embeddings. The project offers a unified and extensible API with current support for a range of popular embedding backends including spaCy, tfhub, huggingface transformers, gensim, fastText and BytePair embeddings. The package combines a domain specific language for vector arithmetic with visualisation tools that make exploring word embeddings more intuitive and concise. It offers support for many popular dimensionality reduction techniques as well as many interactive visualisations that can either be statically exported or shared via Jupyter notebooks. The project documentation is available from


pdf bib
Temporal and Aspectual Entailment
Thomas Kober | Sander Bijl de Vroe | Mark Steedman
Proceedings of the 13th International Conference on Computational Semantics - Long Papers

Inferences regarding “Jane’s arrival in London” from predications such as “Jane is going to London” or “Jane has gone to London” depend on tense and aspect of the predications. Tense determines the temporal location of the predication in the past, present or future of the time of utterance. The aspectual auxiliaries on the other hand specify the internal constituency of the event, i.e. whether the event of “going to London” is completed and whether its consequences hold at that time or not. While tense and aspect are among the most important factors for determining natural language inference, there has been very little work to show whether modern embedding models capture these semantic concepts. In this paper we propose a novel entailment dataset and analyse the ability of contextualised word representations to perform inference on predications across aspectual types and tenses. We show that they encode a substantial amount of information relating to tense and aspect, but fail to consistently model inferences that require reasoning with these semantic properties.


pdf bib
When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases
Julie Weeds | Thomas Kober | Jeremy Reffin | David Weir
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

Non-compositional phrases such as red herring and weakly compositional phrases such as spelling bee are an integral part of natural language (Sag, 2002). They are also the phrases that are difficult, or even impossible, for good compositional distributional models of semantics. Compositionality detection therefore provides a good testbed for compositional methods. We compare an integrated compositional distributional approach, using sparse high dimensional representations, with the ad-hoc compositional approach of applying simple composition operations to state-of-the-art neural embeddings.

pdf bib
One Representation per Word - Does it make Sense for Composition?
Thomas Kober | Julie Weeds | John Wilkie | Jeremy Reffin | David Weir
Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications

In this paper, we investigate whether an a priori disambiguation of word senses is strictly necessary or whether the meaning of a word in context can be disambiguated through composition alone. We evaluate the performance of off-the-shelf single-vector and multi-sense vector models on a benchmark phrase similarity task and a novel task for word-sense discrimination. We find that single-sense vector models perform as well or better than multi-sense vector models despite arguably less clean elementary representations. Our findings furthermore show that simple composition functions such as pointwise addition are able to recover sense specific information from a single-sense vector model remarkably well.

pdf bib
Improving Semantic Composition with Offset Inference
Thomas Kober | Julie Weeds | Jeremy Reffin | David Weir
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection. This problem is amplified for models like Anchored Packed Trees (APTs), that take the grammatical type of a co-occurrence into account. We therefore introduce a novel form of distributional inference that exploits the rich type structure in APTs and infers missing data by the same mechanism that is used for semantic composition.


pdf bib
Improving Sparse Word Representations with Distributional Inference for Semantic Composition
Thomas Kober | Julie Weeds | Jeremy Reffin | David Weir
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
A critique of word similarity as a method for evaluating distributional semantic models
Miroslav Batchkarov | Thomas Kober | Jeremy Reffin | Julie Weeds | David Weir
Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP

pdf bib
Aligning Packed Dependency Trees: A Theory of Composition for Distributional Semantics
David Weir | Julie Weeds | Jeremy Reffin | Thomas Kober
Computational Linguistics, Volume 42, Issue 4 - December 2016


pdf bib
Optimising Agile Social Media Analysis
Thomas Kober | David Weir
Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis