Search Results for author:
Found 143 papers, 53 papers with code
SenTube: A Corpus for Sentiment Analysis on YouTube Social Media
In this paper we present SenTube -- a dataset of user-generated comments on YouTube videos annotated for information content and sentiment polarity.
When POS data sets don't add up: Combatting sample bias
We present a systematic study of several Twitter POS data sets, the problems of label and data bias, discuss their effects on model performance, and show how to overcome them to learn models that perform well on various test sets, achieving relative error reduction of up to 21{\%}.
Multilingual Projection for Parsing Truly Low-Resource Languages
We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages.
Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures
Automatic description generation from natural images is a challenging problem that has recently received a large amount of interest from the computer vision and natural language processing communities.
Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss
Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data set size, and label noise.
Ranked #4 on
Part-Of-Speech Tagging
on UD
TwiSty: A Multilingual Twitter Stylometry Corpus for Gender and Personality Profiling
Personality profiling is the task of detecting personality traits of authors based on writing style.
What to do about non-standard (or non-canonical) language in NLP
The solution is not obvious: we cannot control for all factors, and it is not clear how to best go beyond the current practice of training on homogeneous data from a single domain and language.
Semantic Tagging with Deep Residual Networks
We propose a novel semantic tagging task, sem-tagging, tailored for the purpose of multilingual semantic parsing, and present the first tagger using deep residual networks (ResNets).
Keystroke dynamics as signal for shallow syntactic parsing
Keystroke dynamics have been extensively used in psycholinguistic and writing research to gain insights into cognitive processing.
When silver glitters more than gold: Bootstrapping an Italian part-of-speech tagger for Twitter
We bootstrap a state-of-the-art part-of-speech tagger to tag Italian Twitter data, in the context of the Evalita 2016 PoSTWITA shared task.
Processing non-canonical or noisy text: fortuitous data to the rescue
on which texts can differ from the standard.
Multi-view and multi-task training of RST discourse parsers
We experiment with different ways of training LSTM networks to predict RST discourse trees.
Ranked #10 on
Discourse Parsing
on RST-DT
When is multitask learning effective? Semantic sequence prediction under varying data conditions
Multitask learning has been applied successfully to a range of tasks, mostly morphosyntactic.
Parsing Universal Dependencies without training
We propose UDP, the first training-free parser for Universal Dependencies (UD).
When Sparse Traditional Models Outperform Dense Neural Networks: the Curious Case of Discriminating between Similar Languages
We present the results of our participation in the VarDial 4 shared task on discriminating closely related languages.
Cross-lingual tagger evaluation without test data
We address the challenge of cross-lingual POS tagger evaluation in absence of manually annotated test data.
Learning to select data for transfer learning with Bayesian Optimization
Domain similarity measures can be used to gauge adaptability and select suitable data for transfer learning, but existing approaches define ad hoc measures that are deemed suitable for respective tasks.
To Normalize, or Not to Normalize: The Impact of Normalization on Part-of-Speech Tagging
Does normalization help Part-of-Speech (POS) tagging accuracy on noisy, non-canonical data?
Neural Networks and Spelling Features for Native Language Identification
We present the RUG-SU team{'}s submission at the Native Language Identification Shared Task 2017.
The Power of Character N-grams in Native Language Identification
In this paper, we explore the performance of a linear SVM trained on language independent character features for the NLI Shared Task 2017.
ALL-IN-1: Short Text Classification with One Model for All Languages
We present ALL-IN-1, a simple model for multilingual text classification that does not require any parallel data.
All-In-1 at IJCNLP-2017 Task 4: Short Text Classification with One Model for All Languages
We present All-In-1, a simple model for multilingual text classification that does not require any parallel data.
Strong Baselines for Neural Semi-supervised Learning under Domain Shift
In this paper, we re-evaluate classic general-purpose bootstrapping approaches in the context of neural networks under domain shifts vs. recent neural approaches and propose a novel multi-task tri-training method that reduces the time and space complexity of classic tri-training.
Ranked #3 on
Sentiment Analysis
on Multi-Domain Sentiment Dataset
Bleaching Text: Abstract Features for Cross-lingual Gender Prediction
Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent.
Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models
We present our submission to the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM).
Predicting Authorship and Author Traits from Keystroke Dynamics
Written text transmits a good deal of nonverbal information related to the author{'}s identity and social factors, such as age, gender and personality.
Character-level Supervision for Low-resource POS Tagging
Neural part-of-speech (POS) taggers are known to not perform well with little training data.
When Simple n-gram Models Outperform Syntactic Approaches: Discriminating between Dutch and Flemish
In this paper we present the results of our participation in the Discriminating between Dutch and Flemish in Subtitles VarDial 2018 shared task.
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging
We introduce DsDs: a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource languages.
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat
We compare our approach to an alternative system which extends the baseline with reinforcement learning.
The Best of Both Worlds: Lexical Resources To Improve Low-Resource Part-of-Speech Tagging
In natural language processing, the deep learning revolution has shifted the focus from conventional hand-crafted symbolic representations to dense inputs, which are adequate representations learned automatically from corpora.
Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering
We study the issue of catastrophic forgetting in the context of neural multimodal approaches to Visual Question Answering (VQA).
MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding
Word embeddings have undoubtedly revolutionized NLP.
At a Glance: The Impact of Gaze Aggregation Views on Syntactic Tagging
Hence, caution is warranted when using gaze data as signal for NLP, as no single view is robust over tasks, modeling choice and gaze corpus.
Neural Cross-Lingual Transfer and Limited Annotated Data for Named Entity Recognition in Danish
Named Entity Recognition (NER) has greatly advanced by the introduction of deep neural architectures.
Cross-Domain Evaluation of Edge Detection for Biomedical Event Extraction
Biomedical event extraction is a crucial task in order to automatically extract information from the increasingly growing body of biomedical literature.
FT Speech: Danish Parliament Speech Corpus
A combination of FT Speech with in-domain language data provides comparable results to models trained specifically on Spr\r{a}kbanken, showing that FT Speech transfers well to this data set.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP
In this paper we present MaChAmp, a toolkit for easy fine-tuning of contextualized embeddings in multi-task settings.
Neural Unsupervised Domain Adaptation in NLP---A Survey
We also revisit the notion of domain, and we uncover a bias in the type of Natural Language Processing tasks which received most attention.
Out-of-Distribution Generalization
Unsupervised Domain Adaptation
Team DiSaster at SemEval-2020 Task 11: Combining BERT and Hand-crafted Features for Identifying Propaganda Techniques in News
We present an ablation study which shows that even though BERT representations are very powerful also for this task, BERT still benefits from being combined with carefully designed task-specific features.
Buhscitu at SemEval-2020 Task 7: Assessing Humour in Edited News Headlines Using Hand-Crafted Features and Online Knowledge Bases
This paper describes a system that aims at assessing humour intensity in edited news headlines as part of the 7th task of SemEval-2020 on {``}Humor, Emphasis and Sentiment{''}.
Longitudinal Citation Prediction using Temporal Graph Neural Networks
Citation count prediction is the task of predicting the number of citations a paper has gained after a period of time.
On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions
However, it remains unclear in which situations these dataset embeddings are most effective, because they are used in a large variety of settings, languages and tasks.
From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding
To tackle the challenge, we propose a joint learning approach, with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer.
DaN+: Danish Nested Named Entities and Lexical Normalization
We examine language-specific versus multilingual BERT, and study the effect of lexical normalization on NER.
De-identification of Privacy-related Entities in Job Postings
We present JobStack, a new corpus for de-identification of personal data in job vacancies on Stackoverflow.
Beyond Black \& White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning
Supervised learning assumes that a ground truth label exists.
Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)
Welcome to WeaSuL 2021, the First Workshop on Weakly Supervised Learning, co-located with ICLR 2021.
SemEval-2021 Task 12: Learning with Disagreements
Disagreement between coders is ubiquitous in virtually all datasets annotated with human judgements in both natural language processing and computer vision.
Cartography Active Learning
We propose Cartography Active Learning (CAL), a novel Active Learning (AL) algorithm that exploits the behavior of the model on individual instances during training as a proxy to find the most informative instances for labeling.
Genre as Weak Supervision for Cross-lingual Dependency Parsing
Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection.
How Universal is Genre in Universal Dependencies?
This work provides the first in-depth analysis of genre in Universal Dependencies (UD).
Probing for Labeled Dependency Trees
Probing has become an important tool for analyzing representations in Natural Language Processing (NLP).
Experimental Standards for Deep Learning in Natural Language Processing Research
The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well.
SkillSpan: Hard and Soft Skill Extraction from English Job Postings
We introduce a BERT baseline (Devlin et al., 2019).
What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification
Over the last five years, research on Relation Extraction (RE) witnessed extensive progress with many new dataset releases.
Kompetencer: Fine-grained Skill Classification in Danish Job Postings via Distant Supervision and Transfer Learning
Skill Classification (SC) is the task of classifying job competences from job postings.
Sort by Structure: Language Model Ranking as Dependency Probing
Making an informed choice of pre-trained language model (LM) is critical for performance, yet environmentally costly, and as such widely underexplored.
Skill Extraction from Job Postings using Weak Supervision
Aggregated data obtained from job postings provide powerful insights into labor market demands, and emerging skills, and aid job matching.
An Interdisciplinary Perspective on Evaluation and Experimental Design for Visual Text Analytics: Position Paper
We identify four key groups of challenges for evaluating visual text analytics approaches (data ambiguity, experimental design, user trust, and "big picture" concerns) and provide suggestions for research opportunities from an interdisciplinary perspective.
CrossRE: A Cross-Domain Dataset for Relation Extraction
Relation Extraction (RE) has attracted increasing attention, but current RE evaluation is limited to in-domain evaluation setups.
Evidence > Intuition: Transferability Estimation for Encoder Selection
With the increase in availability of large pre-trained language models (LMs) in Natural Language Processing (NLP), it becomes critical to assess their fit for a specific target task a priori - as fine-tuning the entire space of available LMs is computationally prohibitive and unsustainable.
Stop Measuring Calibration When Humans Disagree
Calibration is a popular framework to evaluate whether a classifier knows when it does not know - i. e., its predictive probabilities are a good indication of how likely a prediction is to be correct.
The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation
Human variation in labeling is often considered noise.
A Survey of Corpora for Germanic Low-Resource Languages and Dialects
In this work, we instead focus on low-resource languages and in particular non-standardized low-resource languages.
Low-resource Bilingual Dialect Lexicon Induction with Large Language Models
Bilingual word lexicons are crucial tools for multilingual natural language understanding and machine translation tasks, as they facilitate the mapping of words in one language to their synonyms in another language.
Bilingual Lexicon Induction
Natural Language Understanding
+4
Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages
This can for instance be observed when finetuning PLMs on one language and evaluating them on data in a closely related language variety with no standardized orthography.
SemEval-2023 Task 11: Learning With Disagreements (LeWiDi)
We report on the second LeWiDi shared task, which differs from the first edition in three crucial respects: (i) it focuses entirely on NLP, instead of both NLP and computer vision tasks in its first edition; (ii) it focuses on subjective tasks, instead of covering different types of disagreements-as training with aggregated labels for subjective NLP tasks is a particularly obvious misrepresentation of the data; and (iii) for the evaluation, we concentrate on soft approaches to evaluation.
Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched Data
Transferring information retrieval (IR) models from a high-resource language (typically English) to other languages in a zero-shot fashion has become a widely adopted approach.
Silver Syntax Pre-training for Cross-Domain Relation Extraction
One of the main reasons for this is the limited training size of current RE datasets: obtaining high-quality (manually annotated) data is extremely expensive and cannot realistically be repeated for each new domain.
Multi-CrossRE A Multi-Lingual Multi-Domain Dataset for Relation Extraction
Most research in Relation Extraction (RE) involves the English language, mainly due to the lack of multi-lingual resources.
What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability
In Natural Language Generation (NLG) tasks, for any input, multiple communicative goals are plausible, and any goal can be put into words, or produced, in multiple ways.
ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain
The increasing number of benchmarks for Natural Language Processing (NLP) tasks in the computational job market domain highlights the demand for methods that can handle job-related tasks such as skill extraction, skill classification, job title classification, and de-identification.
How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives
To the best of our knowledge, this is the first work comprehensively evaluating distillation objectives in both settings.
Findings of the VarDial Evaluation Campaign 2023
This report presents the results of the shared tasks organized as part of the VarDial Evaluation Campaign 2023.
ActiveAED: A Human in the Loop Improves Annotation Error Detection
This problem has been addressed with Annotation Error Detection (AED) models, which can flag such errors for human re-annotation.
Uncertainty in Natural Language Generation: From Theory to Applications
Recent advances of powerful Language Models have allowed Natural Language Generation (NLG) to emerge as an important technology that can not only perform traditional tasks like summarisation or translation, but also serve as a natural language interface to a variety of applications.
Donkii: Can Annotation Error Detection Methods Find Errors in Instruction-Tuning Datasets?
Our results show that the choice of the right AED method and model size is indeed crucial and derive practical recommendations for how to use AED methods to clean instruction-tuning data.
Establishing Trustworthiness: Rethinking Tasks and Model Evaluation
Language understanding is a multi-faceted cognitive capability, which the Natural Language Processing (NLP) community has striven to model computationally for decades.
From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification
Overall, our case study reveals hitherto underappreciated complexities in creating benchmark datasets in legal NLP that revolve around identifying aspects of a case's facts supposedly relevant to its outcome.
LoHoRavens: A Long-Horizon Language-Conditioned Benchmark for Robotic Tabletop Manipulation
The convergence of embodied agents and large language models (LLMs) has brought significant advancements to embodied instruction following.
ACTOR: Active Learning with Annotator-specific Classification Heads to Embrace Human Label Variation
We show that in the active learning setting, a multi-head model performs significantly better than a single-head model in terms of uncertainty estimation.
Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training
We identify critical learning phases across tasks and time, during which subspaces emerge, share information, and later disentangle to specialize.
Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark
We introduce Universal NER (UNER), an open, community-driven project to develop gold-standard NER benchmarks in many languages.
Ranked #1 on
Named Entity Recognition (NER)
on UNER v1 (Danish)
NNOSE: Nearest Neighbor Occupational Skill Extraction
The labor market is changing rapidly, prompting increased interest in the automatic extraction of occupational skills from text.
Entity Linking in the Job Market Domain
In this work, we are the first to explore EL in this domain, specifically targeting the linkage of occupational skills to the ESCO taxonomy (le Vrang et al., 2014).
Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations
Named Entity Recognition (NER) is a key information extraction task with a long-standing tradition.
Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties
Inspired by prior work on English varieties, we craft and manually evaluate perturbation rules that transform German sentences into colloquial forms and use them to synthesize test sets in four ToD datasets.
EEVEE: An Easy Annotation Tool for Natural Language Processing
Annotation tools are the starting point for creating Natural Language Processing (NLP) datasets.
Deep Learning-based Computational Job Market Analysis: A Survey on Skill Extraction and Classification from Job Postings
Recent years have brought significant advances to Natural Language Processing (NLP), which enabled fast progress in the field of computational job market analysis.
Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification
We observe limited alignment with the judge vote distribution.
What Do Dialect Speakers Want? A Survey of Attitudes Towards Language Technology for German Dialects
Natural language processing (NLP) has largely focused on modelling standardized languages.
Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning
Deductive reasoning plays a pivotal role in the formulation of sound and cohesive arguments.
"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging.
Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?
With the rise of increasingly powerful and user-facing NLP systems, there is growing interest in assessing whether they have a good representation of uncertainty by evaluating the quality of their predictive distribution over outcomes.
VariErr NLI: Separating Annotation Error from Human Label Variation
To fill this gap, we introduce a systematic methodology and a new dataset, VariErr (variation versus error), focusing on the NLI task in English.
MaiBaam Annotation Guidelines
This document provides the annotation guidelines for MaiBaam, a Bavarian corpus annotated with part-of-speech (POS) tags and syntactic dependencies.
MaiBaam: A Multi-Dialectal Bavarian Universal Dependency Treebank
Despite the success of the Universal Dependencies (UD) project exemplified by its impressive language breadth, there is still a lack in `within-language breadth': most treebanks focus on standard languages.
Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Data
Named Entity Recognition (NER) is a fundamental task to extract key information from texts, but annotated resources are scarce for dialects.
Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
Large language models (LLMs) have recently shown impressive performance on tasks involving reasoning, leading to a lively debate on whether these models possess reasoning capabilities similar to humans.
MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness
This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR), on Track C: Cross-lingual.
Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
We show that the text answers are more robust to question perturbations than the first token probabilities, when the first token answers mismatch the text answers.
How to Encode Domain Information in Relation Classification
Current language models require a lot of training data to obtain high performance.
“I’ll be there for you”: The One with Understanding Indirect Answers
In this paper, we introduce a new English corpus to study the problem of understanding indirect answers.
Sliced at SemEval-2022 Task 11: Bigger, Better? Massively Multilingual LMs for Multilingual Complex NER on an Academic GPU Budget
Our submission of a single model for 11 languages on the SemEval Task 11 MultiCoNER shows that a vanilla transformer-CRF with XLM-R_{large} outperforms the more recent RemBERT, ranking 9th from 26 submissions in the multilingual track.
MultiLexNorm: A Shared Task on Multilingual Lexical Normalization
This task is beneficial for downstream analysis, as it provides a way to harmonize (often spontaneous) linguistic variation.
Biomedical Event Extraction as Sequence Labeling
We introduce Biomedical Event Extraction as Sequence Labeling (BeeSL), a joint end-to-end neural information extraction model.
From back to the roots into the gated woods: Deep learning for NLP
Deep neural networks have revolutionized many fields, including Natural Language Processing.
Lexical Resources for Low-Resource PoS Tagging in Neural Times
More and more evidence is appearing that integrating symbolic lexical knowledge into neural models aids learning.
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.
Fine-tuning vs From Scratch: Do Vision & Language Models Have Similar Capabilities on Out-of-Distribution Visual Question Answering?
Fine-tuning general-purpose pre-trained models has become a de-facto standard, also for Vision and Language tasks such as Visual Question Answering (VQA).
Frustratingly Easy Performance Improvements for Low-resource Setups: A Tale on BERT and Segment Embeddings
For low-resource syntactic tasks, we observe impacts of segment embedding and multilingual BERT choice.
NLP North at WNUT-2020 Task 2: Pre-training versus Ensembling for Detection of Informative COVID-19 English Tweets
With the COVID-19 pandemic raging world-wide since the beginning of the 2020 decade, the need for monitoring systems to track relevant information on social media is vitally important.
We Need to Consider Disagreement in Evaluation
Instead, we suggest that we need to better capture the sources of disagreement to improve today’s evaluation practice.
Resources and Evaluations for Danish Entity Resolution
Automatic coreference resolution is understudied in Danish even though most of the Danish Dependency Treebank (Buch-Kromann, 2003) is annotated with coreference relations.
Finding the needle in a haystack: Extraction of Informative COVID-19 Danish Tweets
In this work, we introduce a new dataset of 5, 000 tweets for finding informative COVID-19 tweets for Danish.
