1 code implementation • 2 Apr 2024 • Ivo Verhoeven, Pushkar Mishra, Rahel Beloch, Helen Yannakoudakis, Ekaterina Shutova
This mismatch can be partially attributed to the limitations of current evaluation setups that neglect the rapid evolution of online content and the underlying social graph.
no code implementations • 15 Jan 2024 • Christopher Davis, Andrew Caines, Øistein Andersen, Shiva Taslimipoor, Helen Yannakoudakis, Zheng Yuan, Christopher Bryant, Marek Rei, Paula Buttery
Thanks to recent advances in generative AI, we are able to prompt large language models (LLMs) to produce texts which are fluent and grammatical.
no code implementations • 17 Jul 2023 • Andrew Caines, Luca Benedetto, Shiva Taslimipoor, Christopher Davis, Yuan Gao, Oeistein Andersen, Zheng Yuan, Mark Elliott, Russell Moore, Christopher Bryant, Marek Rei, Helen Yannakoudakis, Andrew Mullooly, Diane Nicholls, Paula Buttery
The recent release of very large language models such as PaLM and GPT-4 has made an unprecedented impact in the popular media and public consciousness, giving rise to a mixture of excitement and fear as to their capabilities and potential uses, and shining a light on natural language processing research which had not previously received so much attention.
no code implementations • 14 Mar 2023 • Kamil Bujel, Andrew Caines, Helen Yannakoudakis, Marek Rei
Long-sequence transformers are designed to improve the representation of longer texts by language models and their performance on downstream document-level tasks.
1 code implementation • 17 Feb 2023 • Zhi Zhang, Helen Yannakoudakis, XianTong Zhen, Ekaterina Shutova
The task of multimodal referring expression comprehension (REC), aiming at localizing an image region described by a natural language expression, has recently received increasing attention within the research comminity.
no code implementations • 25 Jan 2023 • Niels van der Heijden, Ekaterina Shutova, Helen Yannakoudakis
We present FewShotTextGCN, a novel method designed to effectively utilize the properties of word-document graphs for improved learning in low-resource settings.
1 code implementation • 28 Nov 2022 • Tamara Czinczoll, Helen Yannakoudakis, Pushkar Mishra, Ekaterina Shutova
This paper examines the encoding of analogy in large-scale pretrained language models, such as BERT and GPT-2.
1 code implementation • 31 Oct 2022 • Avyav Kumar Singh, Ekaterina Shutova, Helen Yannakoudakis
Existing approaches to few-shot learning in NLP rely on large language models and fine-tuning of these to generalise on out-of-distribution data.
1 code implementation • ACL 2021 • Rishav Hada, Sohi Sudhir, Pushkar Mishra, Helen Yannakoudakis, Saif M. Mohammad, Ekaterina Shutova
On social media platforms, hateful and offensive language negatively impact the mental well-being of users and the participation of people from diverse backgrounds.
1 code implementation • ACL 2022 • Anna Langedijk, Verna Dankers, Phillip Lippe, Sander Bos, Bryan Cardenas Guevara, Helen Yannakoudakis, Ekaterina Shutova
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks.
no code implementations • Findings (EMNLP) 2021 • Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
Specifically, we review and analyze the state of the art methods that leverage user or community information to enhance the understanding and detection of abusive language.
1 code implementation • ACL (RepL4NLP) 2021 • Kamil Bujel, Helen Yannakoudakis, Marek Rei
We investigate how sentence-level transformers can be modified into effective sequence labelers at the token level without any direct supervision.
1 code implementation • EACL 2021 • Niels van der Heijden, Helen Yannakoudakis, Pushkar Mishra, Ekaterina Shutova
The great majority of languages in the world are considered under-resourced for the successful application of deep learning methods.
Cross-Lingual Document Classification Document Classification +2
1 code implementation • 23 Dec 2020 • Phillip Lippe, Nithin Holla, Shantanu Chandra, Santhosh Rajamanickam, Georgios Antoniou, Ekaterina Shutova, Helen Yannakoudakis
An increasingly common expression of online hate speech is multimodal in nature and comes in the form of memes.
no code implementations • NLP4CALL (COLING) 2020 • Andrew Caines, Helen Yannakoudakis, Helena Edmondson, Helen Allen, Pascual Pérez-Paredes, Bill Byrne, Paula Buttery
The Teacher-Student Chatroom Corpus (TSCC) is a collection of written conversations captured during one-to-one lessons between teachers and learners of English.
1 code implementation • EMNLP (CODI) 2020 • Youmna Farag, Josef Valvoda, Helen Yannakoudakis, Ted Briscoe
In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation.
no code implementations • EMNLP 2020 • Simon Flachs, Ophélie Lacroix, Helen Yannakoudakis, Marek Rei, Anders Søgaard
Evaluation of grammatical error correction (GEC) systems has primarily focused on essays written by non-native learners of English, which however is only part of the full spectrum of GEC applications.
1 code implementation • 10 Sep 2020 • Nithin Holla, Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions.
1 code implementation • 14 Aug 2020 • Shantanu Chandra, Pushkar Mishra, Helen Yannakoudakis, Madhav Nimishakavi, Marzieh Saeidi, Ekaterina Shutova
Existing research has modeled the structure, style, content, and patterns in dissemination of online posts, as well as the demographic traits of users who interact with them.
no code implementations • ACL 2020 • Hannah Craighead, Andrew Caines, Paula Buttery, Helen Yannakoudakis
We address the task of automatically grading the language proficiency of spontaneous speech based on textual features from automatic speech recognition transcripts.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • ACL 2020 • Santhosh Rajamanickam, Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
The rise of online communication platforms has been accompanied by some undesirable effects, such as the proliferation of aggressive and abusive behaviour online.
2 code implementations • Findings of the Association for Computational Linguistics 2020 • Nithin Holla, Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
Meta-learning aims to solve this problem by training a model on a large number of few-shot tasks, with an objective to learn new tasks quickly from a small number of examples.
no code implementations • 13 Aug 2019 • Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
Abuse on the Internet represents an important societal problem of our time.
no code implementations • WS 2019 • Zheng Yuan, Felix Stahlberg, Marek Rei, Bill Byrne, Helen Yannakoudakis
In this paper, we describe our submission to the BEA 2019 shared task on grammatical error correction.
1 code implementation • ACL 2019 • Youmna Farag, Helen Yannakoudakis
We address the task of assessing discourse coherence, an aspect of text quality that is essential for many NLP tasks, such as summarization and language assessment.
1 code implementation • WS 2019 • Samuel Bell, Helen Yannakoudakis, Marek Rei
Grammatical error detection (GED) in non-native writing requires systems to identify a wide range of errors in text written by language learners.
no code implementations • SEMEVAL 2019 • Guy Aglionby, Chris Davis, Pushkar Mishra, Andrew Caines, Helen Yannakoudakis, Marek Rei, Ekaterina Shutova, Paula Buttery
We describe the CAMsterdam team entry to the SemEval-2019 Shared Task 6 on offensive language identification in Twitter data.
no code implementations • NAACL 2019 • Simon Flachs, Oph{\'e}lie Lacroix, Marek Rei, Helen Yannakoudakis, Anders S{\o}gaard
While rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit their training data.
no code implementations • NAACL 2019 • Pushkar Mishra, Marco del Tredici, Helen Yannakoudakis, Ekaterina Shutova
Abuse on the Internet represents a significant societal problem of our time.
1 code implementation • NAACL 2019 • Jesse Mu, Helen Yannakoudakis, Ekaterina Shutova
Most current approaches to metaphor identification use restricted linguistic contexts, e. g. by considering only a verb's arguments or the sentence containing a phrase.
no code implementations • 14 Feb 2019 • Pushkar Mishra, Marco del Tredici, Helen Yannakoudakis, Ekaterina Shutova
The rapid growth of social media in recent years has fed into some highly undesirable phenomena such as proliferation of abusive and offensive language on the Internet.
no code implementations • WS 2018 • Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
The current state of the art approaches to abusive language detection, based on recurrent neural networks, do not explicitly address this problem and resort to a generic OOV (out of vocabulary) embedding for unseen words.
1 code implementation • COLING 2018 • Pushkar Mishra, Marco del Tredici, Helen Yannakoudakis, Ekaterina Shutova
The rapid growth of social media in recent years has fed into some highly undesirable phenomena such as proliferation of hateful and offensive language on the Internet.
1 code implementation • NAACL 2018 • Youmna Farag, Helen Yannakoudakis, Ted Briscoe
We demonstrate that current state-of-the-art approaches to Automated Essay Scoring (AES) are not well-suited to capturing adversarially crafted input of grammatical but incoherent sequences of sentences.
no code implementations • EMNLP 2017 • Helen Yannakoudakis, Marek Rei, {\O}istein E. Andersen, Zheng Yuan
We propose an approach to N-best list reranking using neural sequence-labelling models.
no code implementations • SEMEVAL 2017 • Ekaterina Shutova, Andreas Wundsam, Helen Yannakoudakis
Frame-semantic parsing and semantic role labelling, that aim to automatically assign semantic roles to arguments of verbs in a sentence, have become an active strand of research in NLP.
no code implementations • WS 2017 • Marek Rei, Helen Yannakoudakis
We investigate the utility of different auxiliary objectives and training strategies within a neural sequence labeling approach to error detection in learner writing.
Ranked #2 on Grammatical Error Detection on CoNLL-2014 A1
no code implementations • ACL 2016 • Marek Rei, Helen Yannakoudakis
In this paper, we present the first experiments using neural network models for the task of error detection in learner writing.
Ranked #3 on Grammatical Error Detection on CoNLL-2014 A1
3 code implementations • ACL 2016 • Dimitrios Alikaniotis, Helen Yannakoudakis, Marek Rei
Automated Text Scoring (ATS) provides a cost-effective and consistent alternative to human marking.