Browsing Høstingsarkiver by Author "Øvrelid, Lilja"

Now showing items 1-20 of 31

  • A Diagnostic Dataset for Sentiment and Negation Modeling for Norwegian 
    Mæhlum, Petter; Velldal, Erik; Øvrelid, Lilja (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2023)
    Negation constitutes a challenging phenomenon for many natural language processing tasks, such as sentiment analysis (SA). In this paper we investigate the relationship between negation and sentiment in the context of ...
  • A GPT among Annotators: LLM-based Entity-Level Sentiment Annotation 
    Rønningstad, Egil; Velldal, Erik; Øvrelid, Lilja (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2024)
    We investigate annotator variation for the novel task of Entity-Level Sentiment Analysis (ELSA) which annotates the aggregated sentiment directed towards volitional entities in a text. More specifically, we analyze the ...
  • A tale of four parsers: methodological reflections on diagnostic evaluation and in-depth error analysis for meaning representation parsing 
    Buljan, Maja; Nivre, Joakim; Oepen, Stephan; Øvrelid, Lilja (Journal article / Tidsskriftartikkel / PublishedVersion; Peer reviewed, 2022)
    Abstract We discuss methodological choices in diagnostic evaluation and error analysis in meaning representation parsing (MRP), i.e. mapping from natural language utterances to graph-based encodings of semantic structure. ...
  • A tale of three parsers: Towards diagnostic evaluation for meaning representation parsing. 
    Buljan, Maja; Nivre, Joakim; Oepen, Stephan; Øvrelid, Lilja (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2020)
    We discuss methodological choices in contrastive and diagnostic evaluation in meaning representation parsing, i.e. mapping from natural language utterances to graph-based encodings of its semantic structure. Drawing ...
  • Annotating evaluative sentences for sentiment analysis: a dataset for Norwegian 
    Mæhlum, Petter; Barnes, Jeremy Claude; Øvrelid, Lilja; Velldal, Erik (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2019)
    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 ...
  • Diachronic word embeddings and semantic shifts: a survey 
    Kutuzov, Andrei; Øvrelid, Lilja; Szymanski, Terrence; Velldal, Erik (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2018)
    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. However, this vein of research ...
  • Emotion Analysis of Tweets Banning Education in Afghanistan 
    Hussiny, Mohammad Ali; Øvrelid, Lilja (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2023)
    This paper introduces the first emotion-annotated dataset for the Dari variant of Persian spoken in Afghanistan. The LetHerLearn dataset contains 7,600 tweets posted in reaction to the Taliban’s ban of women’s rights to ...
  • Entity-Level Sentiment Analysis (ELSA): An Exploratory Task Survey 
    Rønningstad, Egil; Øvrelid, Lilja; Velldal, Erik (Journal article / Tidsskriftartikkel / PublishedVersion; Peer reviewed, 2022)
    This paper explores the task of identifying the overall sentiment expressed towards volitional entities (persons and organizations) in a document - what we refer to as Entity-Level Sentiment Analysis (ELSA). While identifying ...
  • Improving cross-domain dependency parsing with dependency-derived clusters 
    Lien, Jostein; Velldal, Erik; Øvrelid, Lilja (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2015)
    This paper describes a semi-supervised approach to improving statistical dependency parsing using dependency-based word clusters. After applying a baseline parser to unlabeled text, clusters are induced using K-means with ...
  • Joint UD Parsing of Norwegian Bokmål and Nynorsk 
    Velldal, Erik; Øvrelid, Lilja; Hohle, Petter (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2017)
    This paper investigates interactions in parser performance for the two official standards for written Norwegian: Bokmål and Nynorsk. We demonstrate that while applying models across standards yields poor performance, ...
  • JSEEGraph: Joint Structured Event Extraction as Graph Parsing 
    You, Huiling; Touileb, Samia; Øvrelid, Lilja (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2023)
    We propose a graph-based event extraction framework JSEEGraph that approaches the task of event extraction as general graph parsing in the tradition of Meaning Representation Parsing. It explicitly encodes entities and ...
  • Lexicon information in neural sentiment analysis: a multi-task learning approach 
    Barnes, Jeremy Claude; Touileb, Samia; Øvrelid, Lilja; Velldal, Erik (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2019)
    This paper explores the use of multi-task learning (MTL) for incorporating external knowledge in neural models. Specifically, we show how MTL can enable a BiLSTM sentiment classifier to incorporate information from sentiment ...
  • Measuring normative and descriptive biases in language models using census data 
    Touileb, Samia; Øvrelid, Lilja; Velldal, Erik (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2023)
    We investigate in this paper how distributions of occupations with respect to gender is reflected in pre-trained language models. Such distributions are not always aligned to normative ideals, nor do they necessarily reflect ...
  • NARC – Norwegian Anaphora Resolution Corpus 
    Mæhlum, Petter; Haug, Dag Trygve Truslew; Jørgensen, Tollef Emil; Kåsen, Andre; Nøklestad, Anders; Rønningstad, Egil; Solberg, Per Erik; Velldal, Erik; Øvrelid, Lilja (Journal article / Tidsskriftartikkel / AcceptedVersion; Peer reviewed, 2022)
    Published in: Proceedings of the Fifth Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC): https://aclanthology.org/venues/coling/. We present the Norwegian Anaphora Resolution Corpus (NARC), ...
  • Neural classification of Norwegian radiology reports: using NLP to detect findings in CT-scans of children 
    Dahl, Fredrik A.; Rama, Taraka; Hurlen, Petter; Brekke, Pål H.; Husby, Haldor; Gundersen, Tore; Nytrø, Øystein; Øvrelid, Lilja (Journal article / Tidsskriftartikkel / PublishedVersion; Peer reviewed, 2021)
    Background With a motivation of quality assurance, machine learning techniques were trained to classify Norwegian radiology reports of paediatric CT examinations according to their description of abnormal ...
  • NorBench – A Benchmark for Norwegian Language Models 
    Samuel, David; Kutuzov, Andrei; Touileb, Samia; Velldal, Erik; Øvrelid, Lilja; Rønningstad, Egil; Sigdel, Elina; Palatkina, Anna (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2023)
    We present NorBench: a streamlined suite of NLP tasks and probes for evaluating Norwegian language models (LMs) on standardized data splits and evaluation metrics. We also introduce a range of new Norwegian language models ...
  • NoReC: The Norwegian Review Corpus 
    Velldal, Erik; Øvrelid, Lilja; Bergem, Eivind Alexander; Stadsnes, Cathrine; Touileb, Samia; Jørgensen, Fredrik (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2018)
    This paper presents the Norwegian Review Corpus (NoReC), created for training and evaluating models for document-level sentiment analysis. The full-text reviews have been collected from major Norwegian news sources and ...
  • The Norwegian Dependency Treebank 
    Solberg, Per Erik; Skjærholt, Arne; Øvrelid, Lilja; Hagen, Kristin; Johannessen, Janne Bondi (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2014)
    The Norwegian Dependency Treebank is a new syntactic treebank for Norwegian Bokmål and Nynorsk with manual syntactic and morphological annotation, developed at the National Library of Norway in collaboration with the ...
  • On Different Approaches to Syntactic Analysis Into Bi-Lexical Dependencies. An Empirical Comparison of Direct, PCFG-Based, and HPSG-Based Parsers 
    Ivanova, Angelina; Oepen, Stephan; Dridan, Rebecca; Flickinger, Dan; Øvrelid, Lilja (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2013)
    We compare three different approaches to parsing into syntactic, bi-lexical dependencies for English: a ‘direct’ data-driven dependency parser, a statistical phrase structure parser, and a hybrid, ‘deep’ grammar-driven ...
  • One-to-X Analogical Reasoning on Word Embeddings: a Case for Diachronic Armed Conflict Prediction from News Texts 
    Kutuzov, Andrei; Velldal, Erik; Øvrelid, Lilja (Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2019)
    We extend the well-known word analogy task to a one-to-X formulation, including one-to-none cases, when no correct answer exists. The task is cast as a relation discovery problem and applied to historical armed conflicts ...