Search Results for author:
Found 78 papers, 25 papers with code
An IDR Framework of Opportunities and Barriers between HCI and NLP
The framework is constructed by following an interdisciplinary research-model (IDR), combining field-specific knowledge with existing work in the two fields.
DanFEVER: claim verification dataset for Danish
We present a dataset, DanFEVER, intended for multilingual misinformation research.
Ranked #1 on
Fact Verification
on DanFEVER
The Lacunae of Danish Natural Language Processing
Danish is a North Germanic language spoken principally in Denmark, a country with a long tradition of technological and scientific innovation.
Bornholmsk Natural Language Processing: Resources and Tools
This paper introduces language processing resources and tools for Bornholmsk, a language spoken on the island of Bornholm, with roots in Danish and closely related to Scanian.
Joint Rumour Stance and Veracity Prediction
In our experiments, monolinugal scores reach stance-based veracity accuracy of 0. 83 (F1 0. 68); applying the model across languages predicts veracity of claims with an accuracy of 0. 82 (F1 0. 67).
Political Stance in Danish
Furthermore, three models based on an LSTM architecture are designed, implemented and optimized to perform the task of stance detection for the generated dataset.
Hyperparameter Power Impact in Transformer Language Model Training
Training large language models can consume a large amount of energy.
Nemotron-4 340B Technical Report
We release the Nemotron-4 340B model family, including Nemotron-4-340B-Base, Nemotron-4-340B-Instruct, and Nemotron-4-340B-Reward.
garak: A Framework for Security Probing Large Language Models
As Large Language Models (LLMs) are deployed and integrated into thousands of applications, the need for scalable evaluation of how models respond to adversarial attacks grows rapidly.
Introducing v0.5 of the AI Safety Benchmark from MLCommons
We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0. 5 benchmark.
Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming in the Wild
As a result, this paper presents a grounded theory of how and why people attack large language models: LLM red teaming in the wild.
Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research
Many recent improvements in NLP stem from the development and use of large pre-trained language models (PLMs) with billions of parameters.
Assessing Language Model Deployment with Risk Cards
However, there is no risk-centric framework for documenting the complexity of a landscape in which some risks are shared across models and contexts, while others are specific, and where certain conditions may be required for risks to manifest as harms.
Efficient Methods for Natural Language Processing: A Survey
Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows.
Training a T5 Using Lab-sized Resources
Training large neural language models on large datasets is resource- and time-intensive.
Sparse Probability of Agreement
Measuring inter-annotator agreement is important for annotation tasks, but many metrics require a fully-annotated set of data, where all annotators annotate all samples.
The ITU Faroese Pairs Dataset
This article documents a dataset of sentence pairs between Faroese and Danish, produced at ITU Copenhagen.
Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction
The task of learning to map an input set onto a permuted sequence of its elements is challenging for neural networks.
Bridging the Domain Gap for Stance Detection for the Zulu language
This allows us to rapidly achieve similar results for stance detection for the Zulu language, the target language in this work, as are found for English.
Annotating Online Misogyny
Online misogyny, a category of online abusive language, has serious and harmful social consequences.
Ranked #1 on
Hate Speech Detection
on bajer_danish_misogyny
Detecting Abusive Albanian
The ever growing usage of social media in the recent years has had a direct impact on the increased presence of hate speech and offensive speech in online platforms.
Ranked #1 on
Hate Speech Detection
on SHAJ
Optimal Size-Performance Tradeoffs: Weighing PoS Tagger Models
Improvement in machine learning-based NLP performance are often presented with bigger models and more complex code.
Discriminating Between Similar Nordic Languages
Automatic language identification is a challenging problem.
Detection and Resolution of Rumors and Misinformation with NLP
Detecting and grounding false and misleading claims on the web has grown to form a substantial sub-field of NLP.
Maintaining Quality in FEVER Annotation
We propose two measures for measuring the quality of constructed claims in the FEVER task.
SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)
We present the results and main findings of SemEval-2020 Task 12 on Multilingual Offensive Language Identification in Social Media (OffensEval 2020).
Power Consumption Variation over Activation Functions
The power that machine learning models consume when making predictions can be affected by a model's architecture.
Accelerated High-Quality Mutual-Information Based Word Clustering
We present efficient implementations of Brown clustering and the alternative Exchange clustering as well as a number of methods to accelerate the computation of both hierarchical and flat clusters.
Directions in Abusive Language Training Data: Garbage In, Garbage Out
Data-driven analysis and detection of abusive online content covers many different tasks, phenomena, contexts, and methodologies.
The Rumour Mill: Making the Spread of Misinformation Explicit and Tangible
Misinformation spread presents a technological and social threat to society.
Offensive Language and Hate Speech Detection for Danish
It contains user generated comments from various social media platforms, and to our knowledge, it is the first of its kind.
Ranked #1 on
Hate Speech Detection
on DKhate
Simple Natural Language Processing Tools for Danish
This technical note describes a set of baseline tools for automatic processing of Danish text.
Quantifying the morphosyntactic content of Brown Clusters
We show that increases in Average Mutual Information, the clustering algorithms{'} optimization goal, are highly correlated with improvements in encoding of morphosyntactic information.
SemEval-2019 Task 7: RumourEval, Determining Rumour Veracity and Support for Rumours
Rumour verification is characterised by the need to consider evolving conversations and news updates to reach a verdict on a rumour{'}s veracity.
RumourEval 2019: Determining Rumour Veracity and Support for Rumours
This is the proposal for RumourEval-2019, which will run in early 2019 as part of that year's SemEval event.
Stance Prediction for Russian: Data and Analysis
As well as presenting this openly-available dataset, the first of its kind for Russian, the paper presents a baseline for stance prediction in the language.
Ranked #1 on
Stance Detection
on RuStance
IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source
This paper describes the IUCM entry at SemEval-2018 Task 11, on machine comprehension using commonsense knowledge.
Helping Crisis Responders Find the Informative Needle in the Tweet Haystack
Messages are filtered for informativeness based on a definition of the concept drawn from prior research and crisis response experts.
Tracking the Diffusion of Named Entities
Existing studies of how information diffuses across social networks have thus far concentrated on analysing and recovering the spread of deterministic innovations such as URLs, hashtags, and group membership.
Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition
This shared task focuses on identifying unusual, previously-unseen entities in the context of emerging discussions.
Simple Open Stance Classification for Rumour Analysis
Stance classification determines the attitude, or stance, in a (typically short) text.
SemEval-2017 Task 8: RumourEval: Determining rumour veracity and support for rumours
Media is full of false claims.
Generalisation in Named Entity Recognition: A Quantitative Analysis
Unseen NEs, in particular, play an important role, which have a higher incidence in diverse genres such as social media than in more regular genres such as newswire.
Twitter Geolocation Prediction Shared Task of the 2016 Workshop on Noisy User-generated Text
This paper presents the shared task for English Twitter geolocation prediction in WNUT 2016.
Broad Twitter Corpus: A Diverse Named Entity Recognition Resource
One of the main obstacles, hampering method development and comparative evaluation of named entity recognition in social media, is the lack of a sizeable, diverse, high quality annotated corpus, analogous to the CoNLL{'}2003 news dataset.
Representation and Learning of Temporal Relations
Determining the relative order of events and times described in text is an important problem in natural language processing.
Desiderata for Vector-Space Word Representations
A plethora of vector-space representations for words is currently available, which is growing.
Complementarity, F-score, and NLP Evaluation
This paper addresses the problem of quantifying the differences between entity extraction systems, where in general only a small proportion a document should be selected.
GATE-Time: Extraction of Temporal Expressions and Events
GATE is a widely used open-source solution for text processing with a large user community.
USFD: Twitter NER with Drift Compensation and Linked Data
This paper describes a pilot NER system for Twitter, comprising the USFD system entry to the W-NUT 2015 NER shared task.
Analysis of Named Entity Recognition and Linking for Tweets
Applying natural language processing for mining and intelligent information access to tweets (a form of microblog) is a challenging, emerging research area.
Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines
Crowdsourcing is an emerging collaborative approach that can be used for the acquisition of annotated corpora and a wide range of other linguistic resources.
Clinical TempEval
We describe the Clinical TempEval task which is currently in preparation for the SemEval-2015 evaluation exercise.
TimeML-strict: clarifying temporal annotation
To unify the state of current resources, and to make progress toward easy adoption of its current incarnation ISO-TimeML, this paper introduces TimeML-strict: a valid, unambiguous, and easy-to-process subset of TimeML.
Question Answering Against Very-Large Text Collections
Question answering involves developing methods to extract useful information from large collections of documents.
TempEval-3: Evaluating Events, Time Expressions, and Temporal Relations
We describe the TempEval-3 task which is currently in preparation for the SemEval-2013 evaluation exercise.
TIMEN: An Open Temporal Expression Normalisation Resource
In this paper, we present TIMEN, a community-driven tool for temporal expression normalisation.
Ranked #1 on
Timex normalization
on TimeBank
Massively Increasing TIMEX3 Resources: A Transduction Approach
Automatic annotation of temporal expressions is a research challenge of great interest in the field of information extraction.
