Adrian Flanagan


2022

pdf
SeqL at SemEval-2022 Task 11: An Ensemble of Transformer Based Models for Complex Named Entity Recognition Task
Fadi Hassan | Wondimagegnhue Tufa | Guillem Collell | Piek Vossen | Lisa Beinborn | Adrian Flanagan | Kuan Eeik Tan
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper presents our system used to participate in task 11 (MultiCONER) of the SemEval 2022 competition. Our system ranked fourth place in track 12 (Multilingual) and fifth place in track 13 (Code-Mixed). The goal of track 12 is to detect complex named entities in a multilingual setting, while track 13 is dedicated to detecting complex named entities in a code-mixed setting. Both systems were developed using transformer-based language models. We used an ensemble of XLM-RoBERTa-large and Microsoft/infoxlm-large with a Conditional Random Field (CRF) layer. In addition, we describe the algorithms employed to train our models and our hyper-parameter selection. We furthermore study the impact of different methods to aggregate the outputs of the individual models that compose our ensemble. Finally, we present an extensive analysis of the results and errors.

2020

pdf
A little goes a long way: Improving toxic language classification despite data scarcity
Mika Juuti | Tommi Gröndahl | Adrian Flanagan | N. Asokan
Findings of the Association for Computational Linguistics: EMNLP 2020

Detection of some types of toxic language is hampered by extreme scarcity of labeled training data. Data augmentation – generating new synthetic data from a labeled seed dataset – can help. The efficacy of data augmentation on toxic language classification has not been fully explored. We present the first systematic study on how data augmentation techniques impact performance across toxic language classifiers, ranging from shallow logistic regression architectures to BERT – a state-of-the-art pretrained Transformer network. We compare the performance of eight techniques on very scarce seed datasets. We show that while BERT performed the best, shallow classifiers performed comparably when trained on data augmented with a combination of three techniques, including GPT-2-generated sentences. We discuss the interplay of performance and computational overhead, which can inform the choice of techniques under different constraints.