Search Results for author:
Found 61 papers, 25 papers with code
Negation in Norwegian: an annotated dataset
This paper introduces NorecNeg – the first annotated dataset of negation for Norwegian.
Multilingual ELMo and the Effects of Corpus Sampling
Multilingual pretrained language models are rapidly gaining popularity in NLP systems for non-English languages.
Gender and sentiment, critics and authors: a dataset of Norwegian book reviews
We also explore the differences in how this is done by male and female critics.
Lexicon information in neural sentiment analysis: a multi-task learning approach
This paper explores the use of multi-task learning (MTL) for incorporating external knowledge in neural models.
Annotating evaluative sentences for sentiment analysis: a dataset for Norwegian
This paper documents the creation of a large-scale dataset of evaluative sentences – i. e. both subjective and objective sentences that are found to be sentiment-bearing – based on mixed-domain professional reviews from various news-sources.
Using Gender- and Polarity-Informed Models to Investigate Bias
More specifically, we add information about the gender of critics and book authors when classifying the polarity of book reviews, and the polarity of the reviews when classifying the genders of authors and critics.
NARC – Norwegian Anaphora Resolution Corpus
We present the Norwegian Anaphora Resolution Corpus (NARC), the first publicly available corpus annotated with anaphoric relations between noun phrases for Norwegian.
SemEval 2022 Task 10: Structured Sentiment Analysis
In this paper, we introduce the first SemEval shared task on Structured Sentiment Analysis, for which participants are required to predict all sentiment graphs in a text, where a single sentiment graph is composed of a sentiment holder, target, expression and polarity.
Occupational Biases in Norwegian and Multilingual Language Models
In this paper we explore how a demographic distribution of occupations, along gender dimensions, is reflected in pre-trained language models.
NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark
We describe the NorEval design and present the results of benchmarking 19 open-source pre-trained and instruction-tuned LMs for Norwegian in various scenarios.
Mixed Feelings: Cross-Domain Sentiment Classification of Patient Feedback
Sentiment analysis of patient feedback from the public health domain can aid decision makers in evaluating the provided services.
A Collection of Question Answering Datasets for Norwegian
This paper introduces a new suite of question answering datasets for Norwegian; NorOpenBookQA, NorCommonSenseQA, NorTruthfulQA, and NRK-Quiz-QA.
Benchmarking Abstractive Summarisation: A Dataset of Human-authored Summaries of Norwegian News Articles
We introduce a dataset of high-quality human-authored summaries of news articles in Norwegian.
The Impact of Copyrighted Material on Large Language Models: A Norwegian Perspective
The use of copyrighted materials in training language models raises critical legal and ethical questions.
Small Languages, Big Models: A Study of Continual Training on Languages of Norway
Training large language models requires vast amounts of data, posing a challenge for less widely spoken languages like Norwegian and even more so for truly low-resource languages like Northern S\'ami.
Entity-Level Sentiment: More than the Sum of Its Parts
In order to better understand how sentiment regarding persons and organizations (each entity in our scope) is expressed in longer texts, we have collected a dataset of expert annotations where the overall sentiment regarding each entity is identified, together with the sentence-level sentiment for these entities separately.
Compositional Generalization with Grounded Language Models
Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training.
It's Difficult to be Neutral -- Human and LLM-based Sentiment Annotation of Patient Comments
Sentiment analysis is an important tool for aggregating patient voices, in order to provide targeted improvements in healthcare services.
Text-To-KG Alignment: Comparing Current Methods on Classification Tasks
In contrast to large text corpora, knowledge graphs (KG) provide dense and structured representations of factual information.
NorBench -- A Benchmark for Norwegian Language Models
We present NorBench: a streamlined suite of NLP tasks and probes for evaluating Norwegian language models (LMs) on standardized data splits and evaluation metrics.
Entity-Level Sentiment Analysis (ELSA): An exploratory task survey
We show that sentiment in our dataset is expressed not only with an entity mention as target, but also towards targets with a sentiment-relevant relation to a volitional entity.
Measuring Normative and Descriptive Biases in Language Models Using Census Data
We investigate in this paper how distributions of occupations with respect to gender is reflected in pre-trained language models.
Trained on 100 million words and still in shape: BERT meets British National Corpus
While modern masked language models (LMs) are trained on ever larger corpora, we here explore the effects of down-scaling training to a modestly-sized but representative, well-balanced, and publicly available English text source -- the British National Corpus.
Contextualized language models for semantic change detection: lessons learned
Our findings show that contextualized methods can often predict high change scores for words which are not undergoing any real diachronic semantic shift in the lexicographic sense of the term (or at least the status of these shifts is questionable).
Direct parsing to sentiment graphs
This paper demonstrates how a graph-based semantic parser can be applied to the task of structured sentiment analysis, directly predicting sentiment graphs from text.
Structured Sentiment Analysis as Dependency Graph Parsing
Structured sentiment analysis attempts to extract full opinion tuples from a text, but over time this task has been subdivided into smaller and smaller sub-tasks, e, g,, target extraction or targeted polarity classification.
Large-Scale Contextualised Language Modelling for Norwegian
We present the ongoing NorLM initiative to support the creation and use of very large contextualised language models for Norwegian (and in principle other Nordic languages), including a ready-to-use software environment, as well as an experience report for data preparation and training.
If you've got it, flaunt it: Making the most of fine-grained sentiment annotations
Fine-grained sentiment analysis attempts to extract sentiment holders, targets and polar expressions and resolve the relationship between them, but progress has been hampered by the difficulty of annotation.
A Systematic Comparison of Architectures for Document-Level Sentiment Classification
Documents are composed of smaller pieces - paragraphs, sentences, and tokens - that have complex relationships between one another.
A Fine-Grained Sentiment Dataset for Norwegian
We introduce NoReC_fine, a dataset for fine-grained sentiment analysis in Norwegian, annotated with respect to polar expressions, targets and holders of opinion.
NorNE: Annotating Named Entities for Norwegian
This paper presents NorNE, a manually annotated corpus of named entities which extends the annotation of the existing Norwegian Dependency Treebank.
Multilingual Probing of Deep Pre-Trained Contextual Encoders
Encoders that generate representations based on context have, in recent years, benefited from adaptations that allow for pre-training on large text corpora.
Measuring Diachronic Evolution of Evaluative Adjectives with Word Embeddings: the Case for English, Norwegian, and Russian
We measure the intensity of diachronic semantic shifts in adjectives in English, Norwegian and Russian across 5 decades.
One-to-X analogical reasoning on word embeddings: a case for diachronic armed conflict prediction from news texts
We extend the well-known word analogy task to a one-to-X formulation, including one-to-none cases, when no correct answer exists.
Improving Sentiment Analysis with Multi-task Learning of Negation
Sentiment analysis is directly affected by compositional phenomena in language that act on the prior polarity of the words and phrases found in the text.
Sentiment analysis is not solved! Assessing and probing sentiment classification
Finally, we provide a case study that demonstrates the usefulness of the dataset to probe the performance of a given sentiment classifier with respect to linguistic phenomena.
Probing Multilingual Sentence Representations With X-Probe
This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain.
Transfer and Multi-Task Learning for Noun--Noun Compound Interpretation
In this paper, we empirically evaluate the utility of transfer and multi-task learning on a challenging semantic classification task: semantic interpretation of noun{--}noun compounds.
Transfer and Multi-Task Learning for Noun-Noun Compound Interpretation
In this paper, we empirically evaluate the utility of transfer and multi-task learning on a challenging semantic classification task: semantic interpretation of noun--noun compounds.
Diachronic word embeddings and semantic shifts: a survey
Recent years have witnessed a surge of publications aimed at tracing temporal changes in lexical semantics using distributional methods, particularly prediction-based word embedding models.
NoReC: The Norwegian Review Corpus
As resources for sentiment analysis have so far been unavailable for Norwegian, NoReC represents a highly valuable and sought-after addition to Norwegian language technology.
Tracing armed conflicts with diachronic word embedding models
Recent studies have shown that word embedding models can be used to trace time-related (diachronic) semantic shifts in particular words.
Temporal dynamics of semantic relations in word embeddings: an application to predicting armed conflict participants
This paper deals with using word embedding models to trace the temporal dynamics of semantic relations between pairs of words.
Representation and Interchange of Linguistic Annotation. An In-Depth, Side-by-Side Comparison of Three Designs
We expect that a more in-depth understanding of these choices across designs may led to increased harmonization, or at least to more informed design of future representations.
An open-source tool for negation detection: a maximum-margin approach
This paper presents an open-source toolkit for negation detection.
A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations
In this paper we present the Corpus of REcommendation STrength (CREST), a collection of HTML-formatted clinical guidelines annotated with the location of recommendations.
Off-Road LAF: Encoding and Processing Annotations in NLP Workflows
The Linguistic Annotation Framework (LAF) provides an abstract data model for specifying interchange representations to ensure interoperability among different annotation formats.
