Search Results for author:
Found 98 papers, 38 papers with code
Explainable Assessment of Healthcare Articles with QA
The healthcare domain suffers from the spread of poor quality articles on the Internet.
Leveraging Wikipedia article evolution for promotional tone detection
Detecting biased language is useful for a variety of applications, such as identifying hyperpartisan news sources or flagging one-sided rhetoric.
The Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS) Shared Task
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).
The Future Outcome Reasoning and Confidence Assessment Benchmark
Forecasting is an important task in many domains, such as technology and economics.
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey
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.
Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language Models
Diffusion models have shown promise in text generation but often struggle with generating long, coherent, and contextually accurate text.
Decompose and Leverage Preferences from Expert Models for Improving Trustworthiness of MLLMs
The DecompGen feedback is used to automatically construct our preference dataset, DGPref.
A Bayesian Optimization Approach to Machine Translation Reranking
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.
Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking
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.
TabVer: Tabular Fact Verification with Natural Logic
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.
The Automated Verification of Textual Claims (AVeriTeC) Shared Task
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.
Conformity in Large Language Models
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.
ALVIN: Active Learning Via INterpolation
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.
Zero-Shot Fact Verification via Natural Logic and Large Language Models
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.
An LLM Feature-based Framework for Dialogue Constructiveness Assessment
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.
Causal Estimation of Memorisation Profiles
Understanding memorisation in language models has practical and societal implications, e. g., studying models' training dynamics or preventing copyright infringements.
Document-level Claim Extraction and Decontextualisation for Fact-Checking
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.
Automated Focused Feedback Generation for Scientific Writing Assistance
In this paper, we propose a novel task: automated focused feedback generation for scientific writing assistance.
AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets
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.
PRobELM: Plausibility Ranking Evaluation for Language Models
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.
The effect of diversity on group decision-making
We explore different aspects of cognitive diversity and its effect on the success of group deliberation.
Do We Need Language-Specific Fact-Checking Models? The Case of Chinese
This paper investigates the potential benefits of language-specific fact-checking models, focusing on the case of Chinese.
Zero-Shot Fact-Checking with Semantic Triples and Knowledge Graphs
Despite progress in automated fact-checking, most systems require a significant amount of labeled training data, which is expensive.
Faster Minimum Bayes Risk Decoding with Confidence-based Pruning
Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function.
Automated Fact-Checking in Dialogue: Are Specialized Models Needed?
Prior research has shown that typical fact-checking models for stand-alone claims struggle with claims made in dialogues.
QA-NatVer: Question Answering for Natural Logic-based Fact Verification
Fact verification systems assess a claim's veracity based on evidence.
AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web
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.
Multimodal Automated Fact-Checking: A Survey
In this survey, we conceptualise a framework for AFC including subtasks unique to multimodal misinformation.
The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who
Automated fact-checking is often presented as an epistemic tool that fact-checkers, social media consumers, and other stakeholders can use to fight misinformation.
Opening up Minds with Argumentative Dialogues
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.
How to disagree well: Investigating the dispute tactics used on Wikipedia
Disagreements are frequently studied from the perspective of either detecting toxicity or analysing argument structure.
Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verification
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.
Varifocal Question Generation for Fact-checking
Our method outperforms previous work on a fact-checking question generation dataset on a wide range of automatic evaluation metrics.
What makes you change your mind? An empirical investigation in online group decision-making conversations
People leverage group discussions to collaborate in order to solve complex tasks, e. g. in project meetings or hiring panels.
Policy Compliance Detection via Expression Tree Inference
In this work, we learn how to infer expression trees automatically from policy texts.
Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation
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.
Cross-Policy Compliance Detection via Question Answering
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).
A Survey on Automated Fact-Checking
Fact-checking has become increasingly important due to the speed with which both information and misinformation can spread in the modern media ecosystem.
ProoFVer: Natural Logic Theorem Proving for Fact Verification
Fact verification systems typically rely on neural network classifiers for veracity prediction which lack explainability.
Ranked #1 on
Fact Verification
on FEVER
DeliData: A dataset for deliberation in multi-party problem solving
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
Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification
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.
FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information
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.
Evidence-based Factual Error Correction
This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence.
AmbiFC: Fact-Checking Ambiguous Claims with Evidence
Automated fact-checking systems verify claims against evidence to predict their veracity.
Web Mining for Estimating Regulatory Blockchain Readiness
In this work, a computational model is proposed for quantitatively estimating the regulatory stance of countries with respect to cryptocurrencies.
Trajectory-Based Meta-Learning for Out-Of-Vocabulary Word Embedding Learning
Word embedding learning methods require a large number of occurrences of a word to accurately learn its embedding.
Incremental Beam Manipulation for Natural Language Generation
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.
I Beg to Differ: A study of constructive disagreement in online conversations
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.
A Robust Blockchain Readiness Index Model
As the blockchain ecosystem gets more mature many businesses, investors, and entrepreneurs are seeking opportunities on working with blockchain systems and cryptocurrencies.
Evidence-based Factual Error Correction
This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence.
Generating Fact Checking Briefs
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.
Elastic weight consolidation for better bias inoculation
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.
Evaluating adversarial attacks against multiple fact verification systems
Automated fact verification has been progressing owing to advancements in modeling and availability of large datasets.
The FEVER2.0 Shared Task
We present the results of the second Fact Extraction and VERification (FEVER2. 0) Shared Task.
Incorporating Label Dependencies in Multilabel Stance Detection
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.
Byte-Pair Encoding for Text-to-SQL Generation
In this work, we adapt BPE for text-to-SQL generation.
Neural Generative Rhetorical Structure Parsing
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.
Meta-Learning Improves Lifelong Relation Extraction
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.
Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision
In this paper we frame the task of supervised relation classification as an instance of meta-learning.
Merge and Label: A novel neural network architecture for nested NER
Named entity recognition (NER) is one of the best studied tasks in natural language processing.
Ranked #4 on
Nested Mention Recognition
on ACE 2005
HighRES: Highlight-based Reference-less Evaluation of Summarization
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.
Generating Token-Level Explanations for Natural Language Inference
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.
Strong Baselines for Complex Word Identification across Multiple Languages
Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience.
Automated Fact Checking in the News Room
Fact checking is an essential task in journalism; its importance has been highlighted due to recently increased concerns and efforts in combating misinformation.
Adversarial attacks against Fact Extraction and VERification
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.
The Fact Extraction and VERification (FEVER) Shared Task
We present the results of the first Fact Extraction and VERification (FEVER) Shared Task.
Zero-shot Relation Classification as Textual Entailment
We consider the task of relation classification, and pose this task as one of textual entailment.
Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation
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
Topic or Style? Exploring the Most Useful Features for Authorship Attribution
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.
Automated Fact Checking: Task formulations, methods and future directions
The recently increased focus on misinformation has stimulated research in fact checking, the task of assessing the truthfulness of a claim.
FEVER: a large-scale dataset for Fact Extraction and VERification
Thus we believe that FEVER is a challenging testbed that will help stimulate progress on claim verification against textual sources.
Fake news stance detection using stacked ensemble of classifiers
Fake news has become a hotly debated topic in journalism.
Sheffield at SemEval-2017 Task 9: Transition-based language generation from AMR.
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).
An Extensible Framework for Verification of Numerical Claims
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.
The SUMMA Platform Prototype
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Continuous N-gram Representations for Authorship Attribution
This paper presents work on using continuous representations for authorship attribution.
Imitation learning for structured prediction in natural language processing
Imitation learning is a learning paradigm originally developed to learn robotic controllers from demonstrations by humans, e. g. autonomous flight from pilot demonstrations.
Imitation learning for language generation from unaligned data
Natural language generation (NLG) is the task of generating natural language from a meaning representation.
Stance Detection with Bidirectional Conditional Encoding
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".
Dependency Recurrent Neural Language Models for Sentence Completion
Recent work on language modelling has shifted focus from count-based models to neural models.
A New Corpus and Imitation Learning Framework for Context-Dependent Semantic Parsing
Semantic parsing is the task of translating natural language utterances into a machine-interpretable meaning representation.
