research
∙
09/11/2023
Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models
Readability metrics and standards such as Flesch Kincaid Grade Level (FK...
share
research
∙
09/04/2023
Are Emergent Abilities in Large Language Models just In-Context Learning?
Large language models have exhibited emergent abilities, demonstrating e...
research
∙
08/25/2023
Construction Grammar and Language Models
Recent progress in deep learning and natural language processing has giv...
research
∙
10/31/2022
Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5
We compare sequential fine-tuning with a model for multi-task learning i...
research
∙
06/08/2022
Abstraction not Memory: BERT and the English Article System
Article prediction is a task that has long defied accurate linguistic de...
research
∙
05/23/2022
Sample Efficient Approaches for Idiomaticity Detection
Deep neural models, in particular Transformer-based pre-trained language...
research
∙
04/21/2022
SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding
This paper presents the shared task on Multilingual Idiomaticity Detecti...
research
∙
04/08/2022
Improving Tokenisation by Alternative Treatment of Spaces
Tokenisation is the first step in almost all NLP tasks, and state-of-the...
research
∙
10/12/2021
Learned Construction Grammars Converge Across Registers Given Increased Exposure
This paper measures the impact of increased exposure on whether learned ...
research
∙
10/07/2021
UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction
Toxicity is pervasive in social media and poses a major threat to the he...
research
∙
09/09/2021
AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models
Despite their success in a variety of NLP tasks, pre-trained language mo...
research
∙
11/09/2020
CxGBERT: BERT meets Construction Grammar
While lexico-semantic elements no doubt capture a large amount of lingui...
research
∙
10/18/2020
Incorporating Count-Based Features into Pre-Trained Models for Improved Stance Detection
The explosive growth and popularity of Social Media has revolutionised t...
research
∙
10/18/2020
UoB at SemEval-2020 Task 1: Automatic Identification of Novel Word Senses
Much as the social landscape in which languages are spoken shifts, langu...
research
∙
10/15/2020
CXP949 at WNUT-2020 Task 2: Extracting Informative COVID-19 Tweets – RoBERTa Ensembles and The Continued Relevance of Handcrafted Features
This paper presents our submission to Task 2 of the Workshop on Noisy Us...
research
∙
08/19/2020
UoB at SemEval-2020 Task 12: Boosting BERT with Corpus Level Information
Pre-trained language model word representation, such as BERT, have been ...
research
∙
06/08/2020
CS-Embed-francesita at SemEval-2020 Task 9: The effectiveness of code-switched word embeddings for sentiment analysis
The growing popularity and applications of sentiment analysis of social ...
research
∙
03/16/2020
Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data
The automatic identification of propaganda has gained significance in re...
research
∙
03/08/2020
Keeping it simple: Implementation and performance of the proto-principle of adaptation and learning in the language sciences
In this paper we present the Widrow-Hoff rule and its applications to la...
research
∙
08/15/2019