no code implementations • 6 Oct 2021 • Anita L. Verő, Ann Copestake
Another motivation for this paper is the growing need for more interpretable models and for evaluating model efficiency regarding size and performance.
1 code implementation • Findings (EMNLP) 2021 • Huiyuan Xie, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu, Ann Copestake
In research on dialog systems, the ability to actively and smoothly transition to new topics is often ignored.
no code implementations • COLING 2020 • Paula Czarnowska, Sebastian Ruder, Ryan Cotterell, Ann Copestake
We propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way.
no code implementations • 19 Dec 2019 • Huiyuan Xie, Tom Sherborne, Alexander Kuhnle, Ann Copestake
Image captioning as a multimodal task has drawn much interest in recent years.
no code implementations • IJCNLP 2019 • Paula Czarnowska, Sebastian Ruder, Edouard Grave, Ryan Cotterell, Ann Copestake
Human translators routinely have to translate rare inflections of words - due to the Zipfian distribution of words in a language.
no code implementations • 17 Aug 2019 • Alexander Kuhnle, Ann Copestake
Visual question answering (VQA) comprises a variety of language capabilities.
no code implementations • WS 2019 • Alex Kuhnle, er, Ann Copestake
The correct interpretation of quantifier statements in the context of a visual scene requires non-trivial inference mechanisms.
no code implementations • WS 2019 • Paula Czarnowska, Guy Emerson, Ann Copestake
Distributional Semantic Models (DSMs) construct vector representations of word meanings based on their contexts.
no code implementations • 31 Dec 2018 • Alexander Kuhnle, Ann Copestake
The correct interpretation of quantifier statements in the context of a visual scene requires non-trivial inference mechanisms.
no code implementations • 9 Sep 2018 • Alexander Kuhnle, Huiyuan Xie, Ann Copestake
The FiLM model achieves close-to-perfect performance on the diagnostic CLEVR dataset and is distinguished from other such models by having a comparatively simple and easily transferable architecture.
no code implementations • WS 2017 • Guy Emerson, Ann Copestake
Semantic composition remains an open problem for vector space models of semantics.
no code implementations • 1 Sep 2017 • Guy Emerson, Ann Copestake
Functional Distributional Semantics is a framework that aims to learn, from text, semantic representations which can be interpreted in terms of truth.
no code implementations • WS 2017 • Ewa Muszy{\'n}ska, Ann Copestake
We propose sentence chunking as a way to reduce the time and memory costs of realization of long sentences.
no code implementations • WS 2018 • Alexander Kuhnle, Ann Copestake
We discuss problems with the standard approaches to evaluation for tasks like visual question answering, and argue that artificial data can be used to address these as a complement to current practice.
3 code implementations • 14 Apr 2017 • Alexander Kuhnle, Ann Copestake
We introduce a novel framework for evaluating multimodal deep learning models with respect to their language understanding and generalization abilities.
no code implementations • WS 2016 • Guy Emerson, Ann Copestake
Vector space models have become popular in distributional semantics, despite the challenges they face in capturing various semantic phenomena.
no code implementations • LREC 2016 • Ann Copestake, Guy Emerson, Michael Wayne Goodman, Matic Horvat, Alex Kuhnle, er, Ewa Muszy{\'n}ska
We describe resources aimed at increasing the usability of the semantic representations utilized within the DELPH-IN (Deep Linguistic Processing with HPSG) consortium.
no code implementations • LREC 2014 • Theodosia Togia, Ann Copestake
In particular, our work attempts to answer the following questions: if users were to use full descriptions, would their current tags be words present in these hypothetical sentences?
no code implementations • LREC 2012 • Carmen Dayrell, C, Arnaldo ido Jr., Gabriel Lima, Danilo Machado Jr., Ann Copestake, Val{\'e}ria Feltrim, Stella Tagnin, S Aluisio, ra
Here, we present MAZEA (Multi-label Argumentative Zoning for English Abstracts), a multi-label classifier which automatically identifies rhetorical moves in abstracts but allows for a given sentence to be assigned as many labels as appropriate.