1 code implementation • COLING 2022 • Lorenzo Bertolini, Julie Weeds, David Weir
Here, we investigate whether lexical entailment (LE, i. e. hyponymy or the is a relation between words) can be generalised in a compositional manner.
no code implementations • ACL 2022 • Qiwei Peng, David Weir, Julie Weeds, Yekun Chai
Paraphrase identification involves identifying whether a pair of sentences express the same or similar meanings.
1 code implementation • COLING 2022 • Wing Yan Li, Julie Weeds, David Weir
This paper addresses a deficiency in existing cross-lingual information retrieval (CLIR) datasets and provides a robust evaluation of CLIR systems’ disambiguation ability.
no code implementations • COLING (WANLP) 2020 • Ahmed Younes, Julie Weeds
We show that embedding the information that is encoded in automatically acquired Arabic diacritics improves the performance across all datasets on both tasks.
no code implementations • ACL (RepL4NLP) 2021 • Qiwei Peng, David Weir, Julie Weeds
Recently, impressive performance on various natural language understanding tasks has been achieved by explicitly incorporating syntax and semantic information into pre-trained models, such as BERT and RoBERTa.
Natural Language Understanding Semantic Textual Similarity +4
no code implementations • 15 Mar 2023 • Nestor Prieto-Chavana, Julie Weeds, David Weir
This process requires a fact-checker to formulate a search query based on the fact and to present it to a search engine.
1 code implementation • 28 Feb 2023 • Lorenzo Bertolini, Valentina Elce, Adriana Michalak, Giulio Bernardi, Julie Weeds
In this work, we address these limitations by adopting large language models (LLMs) to study and replicate the manual annotation of dream reports, using a mixture of off-the-shelf and bespoke approaches, with a focus on references to reports' emotions.
no code implementations • COLING 2022 • Qiwei Peng, David Weir, Julie Weeds
Therefore, we here propose to combine sentence encoders with an alignment component by representing each sentence as a list of predicate-argument spans (where their span representations are derived from sentence encoders), and decomposing the sentence-level meaning comparison into the alignment between their spans for paraphrase identification tasks.
1 code implementation • Findings (ACL) 2021 • Lorenzo Bertolini, Julie Weeds, David Weir, Qiwei Peng
The exploitation of syntactic graphs (SyGs) as a word's context has been shown to be beneficial for distributional semantic models (DSMs), both at the level of individual word representations and in deriving phrasal representations via composition.
1 code implementation • EACL 2021 • Thomas Kober, Julie Weeds, Lorenzo Bertolini, David Weir
The automatic detection of hypernymy relationships represents a challenging problem in NLP.
1 code implementation • 30 Jan 2020 • Lena Schmidt, Julie Weeds, Julian P. T. Higgins
This paper contributes to solving problems related to ambiguity in PICO sentence prediction tasks, as well as highlighting how annotations for training named entity recognition systems are used to train a high-performing, but nevertheless flexible architecture for question answering in systematic review automation.
1 code implementation • ACL 2017 • Thomas Kober, Julie Weeds, Jeremy Reffin, David Weir
Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection.
no code implementations • EACL 2017 • Julie Weeds, Thomas Kober, Jeremy Reffin, David Weir
Non-compositional phrases such as \textit{red herring} and weakly compositional phrases such as \textit{spelling bee} are an integral part of natural language (Sag, 2002).
1 code implementation • WS 2017 • Thomas Kober, Julie Weeds, John Wilkie, Jeremy Reffin, David Weir
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.
no code implementations • CL 2016 • David Weir, Julie Weeds, Jeremy Reffin, Thomas Kober
We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees.
1 code implementation • EMNLP 2016 • Thomas Kober, Julie Weeds, Jeremy Reffin, David Weir
Distributional models are derived from co-occurrences in a corpus, where only a small proportion of all possible plausible co-occurrences will be observed.