no code implementations • BioNLP (ACL) 2022 • Alodie Boissonnet, Marzieh Saeidi, Vassilis Plachouras, Andreas Vlachos
The healthcare domain suffers from the spread of poor quality articles on the Internet.
1 code implementation • ACL 2022 • Christine de Kock, Andreas Vlachos
Detecting biased language is useful for a variety of applications, such as identifying hyperpartisan news sources or flagging one-sided rhetoric.
no code implementations • EMNLP (FEVER) 2021 • Rami Aly, Zhijiang Guo, Michael Sejr Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal
The Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS) shared task, asks participating systems to determine whether human-authored claims are Supported or Refuted based on evidence retrieved from Wikipedia (or NotEnoughInfo if the claim cannot be verified).
no code implementations • 6 Mar 2025 • Jooyoung Lee, Xiaochen Zhu, Georgi Karadzhov, Tom Stafford, Andreas Vlachos, Dongwon Lee
In this study, we explore the potential of DeepFakeDeLiBot, a deliberation-enhancing chatbot, to support groups in detecting deepfake text.
no code implementations • 27 Feb 2025 • Zhangdie Yuan, Zifeng Ding, Andreas Vlachos
Forecasting is an important task in many domains, such as technology and economics.
1 code implementation • 16 Dec 2024 • Liang Chen, Zekun Wang, Shuhuai Ren, Lei LI, Haozhe Zhao, Yunshui Li, Zefan Cai, Hongcheng Guo, Lei Zhang, Yizhe Xiong, Yichi Zhang, Ruoyu Wu, Qingxiu Dong, Ge Zhang, Jian Yang, Lingwei Meng, Shujie Hu, Yulong Chen, Junyang Lin, Shuai Bai, Andreas Vlachos, Xu Tan, Minjia Zhang, Wen Xiao, Aaron Yee, Tianyu Liu, Baobao Chang
As Large Language Models (LLMs) have advanced to unify understanding and generation tasks within the textual modality, recent research has shown that tasks from different modalities can also be effectively encapsulated within the NTP framework, transforming the multimodal information into tokens and predict the next one given the context.
no code implementations • 15 Dec 2024 • Xiaochen Zhu, Georgi Karadzhov, Chenxi Whitehouse, Andreas Vlachos
Diffusion models have shown promise in text generation but often struggle with generating long, coherent, and contextually accurate text.
1 code implementation • 20 Nov 2024 • Rui Cao, Yuming Jiang, Michael Schlichtkrull, Andreas Vlachos
The DecompGen feedback is used to automatically construct our preference dataset, DGPref.
no code implementations • 14 Nov 2024 • Julius Cheng, Maike Züfle, Vilém Zouhar, Andreas Vlachos
Reranking a list of candidates from a machine translation system with an external scoring model and returning the highest-scoring candidate remains a simple and effective method for improving the overall output quality.
no code implementations • 8 Nov 2024 • Mubashara Akhtar, Michael Schlichtkrull, Andreas Vlachos
Current automated fact-checking (AFC) approaches commonly evaluate evidence either implicitly via the predicted verdicts or by comparing retrieved evidence with a predefined closed knowledge source, such as Wikipedia.
1 code implementation • 2 Nov 2024 • Rami Aly, Andreas Vlachos
In a few-shot setting on FEVEROUS, we achieve an accuracy of 71. 4, outperforming both fully neural and symbolic reasoning models by 3. 4 points.
1 code implementation • 31 Oct 2024 • Michael Schlichtkrull, Yulong Chen, Chenxi Whitehouse, Zhenyun Deng, Mubashara Akhtar, Rami Aly, Zhijiang Guo, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal, James Thorne, Andreas Vlachos
The Automated Verification of Textual Claims (AVeriTeC) shared task asks participants to retrieve evidence and predict veracity for real-world claims checked by fact-checkers.
no code implementations • 16 Oct 2024 • Xiaochen Zhu, Caiqi Zhang, Tom Stafford, Nigel Collier, Andreas Vlachos
Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and decision-making tasks as conversation partners to improve productivity.
no code implementations • 11 Oct 2024 • Michalis Korakakis, Andreas Vlachos, Adrian Weller
To address this issue, we propose Active Learning Via INterpolation (ALVIN), which conducts intra-class interpolations between examples from under-represented and well-represented groups to create anchors, i. e., artificial points situated between the example groups in the representation space.
1 code implementation • 4 Oct 2024 • Marek Strong, Rami Aly, Andreas Vlachos
To comprehensively assess the zero-shot capabilities of our method and other fact verification systems, we evaluate all models on both artificial and real-world claims, including multilingual datasets.
1 code implementation • 20 Jun 2024 • Lexin Zhou, Youmna Farag, Andreas Vlachos
In this paper we propose an LLM feature-based framework for dialogue constructiveness assessment that combines the strengths of feature-based and neural approaches, while mitigating their downsides.
1 code implementation • 6 Jun 2024 • Pietro Lesci, Clara Meister, Thomas Hofmann, Andreas Vlachos, Tiago Pimentel
Understanding memorisation in language models has practical and societal implications, e. g., studying models' training dynamics or preventing copyright infringements.
1 code implementation • 5 Jun 2024 • Zhenyun Deng, Michael Schlichtkrull, Andreas Vlachos
Selecting which claims to check is a time-consuming task for human fact-checkers, especially from documents consisting of multiple sentences and containing multiple claims.
1 code implementation • 30 May 2024 • Eric Chamoun, Michael Schlichktrull, Andreas Vlachos
In this paper, we propose a novel task: automated focused feedback generation for scientific writing assistance.
2 code implementations • 8 Apr 2024 • Pietro Lesci, Andreas Vlachos
By dynamically selecting different anchors at each iteration it promotes class balance and prevents overfitting the initial decision boundary, thus promoting the discovery of new clusters of minority instances.
no code implementations • 4 Apr 2024 • Zhangdie Yuan, Eric Chamoun, Rami Aly, Chenxi Whitehouse, Andreas Vlachos
This paper introduces PRobELM (Plausibility Ranking Evaluation for Language Models), a benchmark designed to assess language models' ability to discern more plausible from less plausible scenarios through their parametric knowledge.
1 code implementation • 2 Feb 2024 • Georgi Karadzhov, Andreas Vlachos, Tom Stafford
We explore different aspects of cognitive diversity and its effect on the success of group deliberation.
no code implementations • 27 Jan 2024 • Caiqi Zhang, Zhijiang Guo, Andreas Vlachos
This paper investigates the potential benefits of language-specific fact-checking models, focusing on the case of Chinese.
no code implementations • 19 Dec 2023 • Zhangdie Yuan, Andreas Vlachos
Despite progress in automated fact-checking, most systems require a significant amount of labeled training data, which is expensive.
1 code implementation • 25 Nov 2023 • Julius Cheng, Andreas Vlachos
Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function.
no code implementations • 14 Nov 2023 • Eric Chamoun, Marzieh Saeidi, Andreas Vlachos
Prior research has shown that typical fact-checking models for stand-alone claims struggle with claims made in dialogues.
1 code implementation • 22 Oct 2023 • Rami Aly, Marek Strong, Andreas Vlachos
Fact verification systems assess a claim's veracity based on evidence.
3 code implementations • NeurIPS 2023 • Michael Schlichtkrull, Zhijiang Guo, Andreas Vlachos
Existing datasets for automated fact-checking have substantial limitations, such as relying on artificial claims, lacking annotations for evidence and intermediate reasoning, or including evidence published after the claim.
1 code implementation • 22 May 2023 • Mubashara Akhtar, Michael Schlichtkrull, Zhijiang Guo, Oana Cocarascu, Elena Simperl, Andreas Vlachos
In this survey, we conceptualise a framework for AFC including subtasks unique to multimodal misinformation.
1 code implementation • 27 Apr 2023 • Michael Schlichtkrull, Nedjma Ousidhoum, Andreas Vlachos
Automated fact-checking is often presented as an epistemic tool that fact-checkers, social media consumers, and other stakeholders can use to fight misinformation.
no code implementations • 16 Jan 2023 • Youmna Farag, Charlotte O. Brand, Jacopo Amidei, Paul Piwek, Tom Stafford, Svetlana Stoyanchev, Andreas Vlachos
We show that while both models perform closely in terms of opening up minds, the argument-based model is significantly better on other dialogue properties such as engagement and clarity.
1 code implementation • 16 Dec 2022 • Christine de Kock, Tom Stafford, Andreas Vlachos
Disagreements are frequently studied from the perspective of either detecting toxicity or analysing argument structure.
no code implementations • 10 Dec 2022 • Rami Aly, Andreas Vlachos
We propose a novel retrieve-and-rerank method for multi-hop retrieval, that consists of a retriever that jointly scores documents in the knowledge source and sentences from previously retrieved documents using an autoregressive formulation and is guided by a proof system based on natural logic that dynamically terminates the retrieval process if the evidence is deemed sufficient.
1 code implementation • 22 Oct 2022 • Nedjma Ousidhoum, Zhangdie Yuan, Andreas Vlachos
Our method outperforms previous work on a fact-checking question generation dataset on a wide range of automatic evaluation metrics.
no code implementations • SIGDIAL (ACL) 2022 • Georgi Karadzhov, Tom Stafford, Andreas Vlachos
People leverage group discussions to collaborate in order to solve complex tasks, e. g. in project meetings or hiring panels.
no code implementations • 24 May 2022 • Neema Kotonya, Andreas Vlachos, Majid Yazdani, Lambert Mathias, Marzieh Saeidi
In this work, we learn how to infer expression trees automatically from policy texts.
no code implementations • 13 Sep 2021 • Michalis Korakakis, Andreas Vlachos
In this paper, we conduct systematic experiments and find that scheduled sampling, while it ameliorates exposure bias by increasing model reliance on the input sequence, worsens performance when the prefix at inference time is correct, a form of catastrophic forgetting.
no code implementations • EMNLP 2021 • Marzieh Saeidi, Majid Yazdani, Andreas Vlachos
Policy compliance detection is the task of ensuring that a scenario conforms to a policy (e. g. a claim is valid according to government rules or a post in an online platform conforms to community guidelines).
1 code implementation • 26 Aug 2021 • Zhijiang Guo, Michael Schlichtkrull, Andreas Vlachos
Fact-checking has become increasingly important due to the speed with which both information and misinformation can spread in the modern media ecosystem.
1 code implementation • 25 Aug 2021 • Amrith Krishna, Sebastian Riedel, Andreas Vlachos
Fact verification systems typically rely on neural network classifiers for veracity prediction which lack explainability.
Ranked #1 on
Fact Verification
on FEVER
no code implementations • 11 Aug 2021 • Georgi Karadzhov, Tom Stafford, Andreas Vlachos
Group deliberation enables people to collaborate and solve problems, however, it is understudied due to a lack of resources.
Ranked #1 on
Problem-Solving Deliberation
on DeliData
no code implementations • ACL 2021 • Rami Aly, Andreas Vlachos, Ryan Mcdonald
We address the zero-shot NERC specific challenge that the not-an-entity class is not well defined as different entity classes are considered in training and testing.
1 code implementation • 10 Jun 2021 • Rami Aly, Zhijiang Guo, Michael Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal
Fact verification has attracted a lot of attention in the machine learning and natural language processing communities, as it is one of the key methods for detecting misinformation.
1 code implementation • ACL 2021 • James Thorne, Andreas Vlachos
This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence.
2 code implementations • 1 Apr 2021 • Max Glockner, Ieva Staliūnaitė, James Thorne, Gisela Vallejo, Andreas Vlachos, Iryna Gurevych
Automated fact-checking systems verify claims against evidence to predict their veracity.
no code implementations • 24 Mar 2021 • Elias Iosif, Klitos Christodoulou, Andreas Vlachos
In this work, a computational model is proposed for quantitatively estimating the regulatory stance of countries with respect to cryptocurrencies.
no code implementations • EACL (AdaptNLP) 2021 • Gordon Buck, Andreas Vlachos
Word embedding learning methods require a large number of occurrences of a word to accurately learn its embedding.
1 code implementation • EACL 2021 • James Hargreaves, Andreas Vlachos, Guy Emerson
For this reason, it is common to rerank the output of beam search, but this relies on beam search to produce a good set of hypotheses, which limits the potential gains.
1 code implementation • EACL 2021 • Christine de Kock, Andreas Vlachos
We develop a variety of neural models and show that taking into account the structure of the conversation improves predictive accuracy, exceeding that of feature-based models.
no code implementations • 20 Jan 2021 • Elias Iosif, Klitos Christodoulou, Andreas Vlachos
As the blockchain ecosystem gets more mature many businesses, investors, and entrepreneurs are seeking opportunities on working with blockchain systems and cryptocurrencies.
3 code implementations • 31 Dec 2020 • James Thorne, Andreas Vlachos
This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence.
no code implementations • EMNLP 2020 • Angela Fan, Aleksandra Piktus, Fabio Petroni, Guillaume Wenzek, Marzieh Saeidi, Andreas Vlachos, Antoine Bordes, Sebastian Riedel
Fact checking at scale is difficult -- while the number of active fact checking websites is growing, it remains too small for the needs of the contemporary media ecosystem.
1 code implementation • EACL 2021 • James Thorne, Andreas Vlachos
The biases present in training datasets have been shown to affect models for sentence pair classification tasks such as natural language inference (NLI) and fact verification.
no code implementations • IJCNLP 2019 • James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Arpit Mittal
Automated fact verification has been progressing owing to advancements in modeling and availability of large datasets.
no code implementations • WS 2019 • James Thorne, Andreas Vlachos, Oana Cocarascu, Christos Christodoulopoulos, Arpit Mittal
We present the results of the second Fact Extraction and VERification (FEVER2. 0) Shared Task.
1 code implementation • IJCNLP 2019 • William Ferreira, Andreas Vlachos
We propose a method that explicitly incorporates label dependencies in the training objective and compare it against a variety of baselines, as well as a reduction of multilabel to multiclass learning.
1 code implementation • 20 Oct 2019 • Samuel Müller, Andreas Vlachos
In this work, we adapt BPE for text-to-SQL generation.
no code implementations • IJCNLP 2019 • Amandla Mabona, Laura Rimell, Stephen Clark, Andreas Vlachos
We show that, for our parser's traversal order, previous beam search algorithms for RNNGs have a left-branching bias which is ill-suited for RST parsing.
no code implementations • WS 2019 • Abiola Obamuyide, Andreas Vlachos
Most existing relation extraction models assume a fixed set of relations and are unable to adapt to exploit newly available supervision data to extract new relations.
no code implementations • ACL 2019 • Abiola Obamuyide, Andreas Vlachos
In this paper we frame the task of supervised relation classification as an instance of meta-learning.
1 code implementation • ACL 2019 • Joseph Fisher, Andreas Vlachos
Named entity recognition (NER) is one of the best studied tasks in natural language processing.
Ranked #4 on
Nested Mention Recognition
on ACE 2005
1 code implementation • ACL 2019 • Hardy, Shashi Narayan, Andreas Vlachos
There has been substantial progress in summarization research enabled by the availability of novel, often large-scale, datasets and recent advances on neural network-based approaches.
no code implementations • NAACL 2019 • James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Arpit Mittal
In this paper, we show that it is possible to generate token-level explanations for NLI without the need for training data explicitly annotated for this purpose.
1 code implementation • NAACL 2019 • Pierre Finnimore, Elisabeth Fritzsch, Daniel King, Alison Sneyd, Aneeq Ur Rehman, Fernando Alva-Manchego, Andreas Vlachos
Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience.
no code implementations • 3 Apr 2019 • Sebastião Miranda, David Nogueira, Afonso Mendes, Andreas Vlachos, Andrew Secker, Rebecca Garrett, Jeff Mitchel, Zita Marinho
Fact checking is an essential task in journalism; its importance has been highlighted due to recently increased concerns and efforts in combating misinformation.
no code implementations • 13 Mar 2019 • James Thorne, Andreas Vlachos
This paper describes a baseline for the second iteration of the Fact Extraction and VERification shared task (FEVER2. 0) which explores the resilience of systems through adversarial evaluation.
no code implementations • WS 2018 • James Thorne, Andreas Vlachos, Oana Cocarascu, Christos Christodoulopoulos, Arpit Mittal
We present the results of the first Fact Extraction and VERification (FEVER) Shared Task.
no code implementations • WS 2018 • Abiola Obamuyide, Andreas Vlachos
We consider the task of relation classification, and pose this task as one of textual entailment.
1 code implementation • EMNLP 2018 • Hardy, Andreas Vlachos
In this paper, we extend previous work on abstractive summarization using Abstract Meaning Representation (AMR) with a neural language generation stage which we guide using the source document.
Abstractive Text Summarization
Abstract Meaning Representation
+2
1 code implementation • COLING 2018 • Yunita Sari, Mark Stevenson, Andreas Vlachos
Approaches to authorship attribution, the task of identifying the author of a document, are based on analysis of individuals{'} writing style and/or preferred topics.
no code implementations • COLING 2018 • James Thorne, Andreas Vlachos
The recently increased focus on misinformation has stimulated research in fact checking, the task of assessing the truthfulness of a claim.
5 code implementations • NAACL 2018 • James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Arpit Mittal
Thus we believe that FEVER is a challenging testbed that will help stimulate progress on claim verification against textual sources.
no code implementations • WS 2017 • James Thorne, Mingjie Chen, Giorgos Myrianthous, Jiashu Pu, Xiaoxuan Wang, Andreas Vlachos
Fake news has become a hotly debated topic in journalism.
no code implementations • SEMEVAL 2017 • Gerasimos Lampouras, Andreas Vlachos
This paper describes the submission by the University of Sheffield to the SemEval 2017 Abstract Meaning Representation Parsing and Generation task (SemEval 2017 Task 9, Subtask 2).
no code implementations • EACL 2017 • James Thorne, Andreas Vlachos
In this paper we present our automated fact checking system demonstration which we developed in order to participate in the Fast and Furious Fact Check challenge.
no code implementations • EACL 2017 • Renars Liepins, Ulrich Germann, Guntis Barzdins, Alex Birch, ra, Steve Renals, Susanne Weber, Peggy van der Kreeft, Herv{\'e} Bourlard, Jo{\~a}o Prieto, Ond{\v{r}}ej Klejch, Peter Bell, Alex Lazaridis, ros, Alfonso Mendes, Sebastian Riedel, Mariana S. C. Almeida, Pedro Balage, Shay B. Cohen, Tomasz Dwojak, Philip N. Garner, Andreas Giefer, Marcin Junczys-Dowmunt, Hina Imran, David Nogueira, Ahmed Ali, Mir, Sebasti{\~a}o a, Andrei Popescu-Belis, Lesly Miculicich Werlen, Nikos Papasarantopoulos, Abiola Obamuyide, Clive Jones, Fahim Dalvi, Andreas Vlachos, Yang Wang, Sibo Tong, Rico Sennrich, Nikolaos Pappas, Shashi Narayan, Marco Damonte, Nadir Durrani, Sameer Khurana, Ahmed Abdelali, Hassan Sajjad, Stephan Vogel, David Sheppey, Chris Hernon, Jeff Mitchell
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
no code implementations • EACL 2017 • Yunita Sari, Andreas Vlachos, Mark Stevenson
This paper presents work on using continuous representations for authorship attribution.
no code implementations • EACL 2017 • Andreas Vlachos, Gerasimos Lampouras, Sebastian Riedel
Imitation learning is a learning paradigm originally developed to learn robotic controllers from demonstrations by humans, e. g. autonomous flight from pilot demonstrations.
no code implementations • COLING 2016 • Gerasimos Lampouras, Andreas Vlachos
Natural language generation (NLG) is the task of generating natural language from a meaning representation.
1 code implementation • EMNLP 2016 • Isabelle Augenstein, Tim Rocktäschel, Andreas Vlachos, Kalina Bontcheva
Stance detection is the task of classifying the attitude expressed in a text towards a target such as Hillary Clinton to be "positive", negative" or "neutral".
1 code implementation • IJCNLP 2015 • Piotr Mirowski, Andreas Vlachos
Recent work on language modelling has shifted focus from count-based models to neural models.
no code implementations • TACL 2014 • Andreas Vlachos, Stephen Clark
Semantic parsing is the task of translating natural language utterances into a machine-interpretable meaning representation.