Search Results for author: Erik Velldal

Found 52 papers, 23 papers with code

Using Gender- and Polarity-Informed Models to Investigate Bias

no code implementations ACL (GeBNLP) 2021 Samia Touileb, Lilja Øvrelid, Erik Velldal

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.

Language Modelling

NARC – Norwegian Anaphora Resolution Corpus

1 code implementation COLING (CRAC) 2022 Petter Mæhlum, Dag Haug, Tollef Jørgensen, Andre Kåsen, Anders Nøklestad, Egil Rønningstad, Per Erik Solberg, Erik Velldal, Lilja Øvrelid

We present the Norwegian Anaphora Resolution Corpus (NARC), the first publicly available corpus annotated with anaphoric relations between noun phrases for Norwegian.

Relation

Occupational Biases in Norwegian and Multilingual Language Models

1 code implementation NAACL (GeBNLP) 2022 Samia Touileb, Lilja Øvrelid, Erik Velldal

In this paper we explore how a demographic distribution of occupations, along gender dimensions, is reflected in pre-trained language models.

Descriptive

Annotating evaluative sentences for sentiment analysis: a dataset for Norwegian

1 code implementation WS (NoDaLiDa) 2019 Petter Mæhlum, Jeremy Barnes, Lilja Øvrelid, Erik Velldal

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.

Sentiment Analysis

Multilingual ELMo and the Effects of Corpus Sampling

no code implementations NoDaLiDa 2021 Vinit Ravishankar, Andrey Kutuzov, Lilja Øvrelid, Erik Velldal

Multilingual pretrained language models are rapidly gaining popularity in NLP systems for non-English languages.

SemEval 2022 Task 10: Structured Sentiment Analysis

no code implementations SemEval (NAACL) 2022 Jeremy Barnes, Laura Oberlaender, Enrica Troiano, Andrey Kutuzov, Jan Buchmann, Rodrigo Agerri, Lilja Øvrelid, Erik Velldal

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.

Sentiment Analysis Test

Text-To-KG Alignment: Comparing Current Methods on Classification Tasks

no code implementations5 Jun 2023 Sondre Wold, Lilja Øvrelid, Erik Velldal

In contrast to large text corpora, knowledge graphs (KG) provide dense and structured representations of factual information.

Knowledge Graphs

NorBench -- A Benchmark for Norwegian Language Models

1 code implementation6 May 2023 David Samuel, Andrey Kutuzov, Samia Touileb, Erik Velldal, Lilja Øvrelid, Egil Rønningstad, Elina Sigdel, Anna Palatkina

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

1 code implementation COLING 2022 Egil Rønningstad, Erik Velldal, Lilja Øvrelid

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.

coreference-resolution Sentence +1

Measuring Normative and Descriptive Biases in Language Models Using Census Data

no code implementations12 Apr 2023 Samia Touileb, Lilja Øvrelid, Erik Velldal

We investigate in this paper how distributions of occupations with respect to gender is reflected in pre-trained language models.

Descriptive

Trained on 100 million words and still in shape: BERT meets British National Corpus

2 code implementations17 Mar 2023 David Samuel, Andrey Kutuzov, Lilja Øvrelid, Erik Velldal

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.

Language Modelling

Contextualized language models for semantic change detection: lessons learned

1 code implementation31 Aug 2022 Andrey Kutuzov, Erik Velldal, Lilja Øvrelid

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).

Change Detection

Direct parsing to sentiment graphs

1 code implementation ACL 2022 David Samuel, Jeremy Barnes, Robin Kurtz, Stephan Oepen, Lilja Øvrelid, Erik Velldal

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.

Sentiment Analysis

Structured Sentiment Analysis as Dependency Graph Parsing

2 code implementations ACL 2021 Jeremy Barnes, Robin Kurtz, Stephan Oepen, Lilja Øvrelid, Erik Velldal

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.

Sentiment Analysis

Large-Scale Contextualised Language Modelling for Norwegian

2 code implementations NoDaLiDa 2021 Andrey Kutuzov, Jeremy Barnes, Erik Velldal, Lilja Øvrelid, Stephan Oepen

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.

Language Modelling

If you've got it, flaunt it: Making the most of fine-grained sentiment annotations

no code implementations EACL 2021 Jeremy Barnes, Lilja Øvrelid, Erik Velldal

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.

General Classification Sentiment Analysis

A Systematic Comparison of Architectures for Document-Level Sentiment Classification

1 code implementation19 Feb 2020 Jeremy Barnes, Vinit Ravishankar, Lilja Øvrelid, Erik Velldal

Documents are composed of smaller pieces - paragraphs, sentences, and tokens - that have complex relationships between one another.

Classification Document Classification +5

A Fine-Grained Sentiment Dataset for Norwegian

1 code implementation LREC 2020 Lilja Øvrelid, Petter Mæhlum, Jeremy Barnes, Erik Velldal

We introduce NoReC_fine, a dataset for fine-grained sentiment analysis in Norwegian, annotated with respect to polar expressions, targets and holders of opinion.

Sentiment Analysis

NorNE: Annotating Named Entities for Norwegian

1 code implementation LREC 2020 Fredrik Jørgensen, Tobias Aasmoe, Anne-Stine Ruud Husevåg, Lilja Øvrelid, Erik Velldal

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

no code implementations WS 2019 Vinit Ravishankar, Memduh G{\"o}k{\i}rmak, Lilja {\O}vrelid, Erik Velldal

Encoders that generate representations based on context have, in recent years, benefited from adaptations that allow for pre-training on large text corpora.

Sentence

Improving Sentiment Analysis with Multi-task Learning of Negation

1 code implementation18 Jun 2019 Jeremy Barnes, Erik Velldal, Lilja Øvrelid

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.

Multi-Task Learning Negation +1

Sentiment analysis is not solved! Assessing and probing sentiment classification

1 code implementation WS 2019 Jeremy Barnes, Lilja Øvrelid, Erik Velldal

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.

Classification General Classification +3

Probing Multilingual Sentence Representations With X-Probe

no code implementations WS 2019 Vinit Ravishankar, Lilja Øvrelid, Erik Velldal

This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain.

Natural Language Inference Sentence

Transfer and Multi-Task Learning for Noun--Noun Compound Interpretation

no code implementations EMNLP 2018 Murhaf Fares, Stephan Oepen, Erik Velldal

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.

General Classification Information Retrieval +3

Transfer and Multi-Task Learning for Noun-Noun Compound Interpretation

1 code implementation18 Sep 2018 Murhaf Fares, Stephan Oepen, Erik Velldal

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.

Classification General Classification +1

Diachronic word embeddings and semantic shifts: a survey

no code implementations COLING 2018 Andrey Kutuzov, Lilja Øvrelid, Terrence Szymanski, Erik Velldal

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.

Diachronic Word Embeddings Word Embeddings

NoReC: The Norwegian Review Corpus

1 code implementation LREC 2018 Erik Velldal, Lilja Øvrelid, Eivind Alexander Bergem, Cathrine Stadsnes, Samia Touileb, Fredrik Jørgensen

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.

Opinion Mining Sentiment Analysis

Tracing armed conflicts with diachronic word embedding models

no code implementations WS 2017 Andrey Kutuzov, Erik Velldal, Lilja {\O}vrelid

Recent studies have shown that word embedding models can be used to trace time-related (diachronic) semantic shifts in particular words.

Word Embeddings

Representation and Interchange of Linguistic Annotation. An In-Depth, Side-by-Side Comparison of Three Designs

no code implementations WS 2017 Richard Eckart de Castilho, Nancy Ide, Emanuele Lapponi, Stephan Oepen, Keith Suderman, Erik Velldal, Marc Verhagen

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.

Redefining part-of-speech classes with distributional semantic models

no code implementations CONLL 2016 Andrey Kutuzov, Erik Velldal, Lilja Øvrelid

This paper studies how word embeddings trained on the British National Corpus interact with part of speech boundaries.

POS TAG +1

A Corpus of Clinical Practice Guidelines Annotated with the Importance of Recommendations

no code implementations LREC 2016 Jonathon Read, Erik Velldal, Marc Cavazza, Gersende Georg

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

no code implementations LREC 2014 Emanuele Lapponi, Erik Velldal, Stephan Oepen, Rune Lain Knudsen

The Linguistic Annotation Framework (LAF) provides an abstract data model for specifying interchange representations to ensure interoperability among different annotation formats.

Part-Of-Speech Tagging

Cannot find the paper you are looking for? You can Submit a new open access paper.