Search

In this paper, we address government and opposition speeches made by the Danish Parliament’s members from 2014 to 2022. We use the linguistic annotations and metadata in ParlaMint-DK, one of the ParlaMint corpora, to investigate some characteristics of the transcribed speeches made by government and opposition and test how well classifiers can identify the speeches delivered by these groups. Our analyses confirm that there are differences in the speeches made by government and opposition e.g., in the frequency of some modality expressions. In our study, we also include parties, which do not directly support or are against the government, the “other” group. The best performing classifier for identifying speeches made by parties in government, in opposition or in “other” is a transformer with a pre-trained Danish BERT model which gave an F1-score of 0.64. The same classifier obtained an F1-score of 0.77 on the binary identification of speeches made by government or opposition parties.

This paper investigates how two policy areas, Environment and Energy were dealt with by seven Danish left and right wing parties in their electoral manifestos (2007-2019) and parliamentary debates between 2009 and 2020. We analyse the two datasets both quantitatively and contentwise using BERTopic (Grootendorst, 2022) to generate subtopics about the two policy areas from the debates, and comparing the results with the content of the manifestos. BERTopic is trained with both multilingual and Danish word embeddings (https://certainly.io/blog/danish-bert-model/). BERTopic generated useful subtopics with both word embeddings, but the multimodal ones produced the largest number of relevant subtopics. Our study shows that only few parties have a consistent behavior in their electoral manifestos and parliamentary debates with respect to the topics that they address. This can be explained in terms of issue and party competition as well as coalition and role of the parties as proposed by political science researchers.

This paper addresses the semi-automatic annotation of subjects, also called policy areas, in the Danish Parliament Corpus (2009-2017) v.2. Recently, the corpus has been made available through the CLARIN-DK repository, the Danish node of the European CLARIN infrastructure. The paper also contains an analysis of the subjects in the corpus, and a description of multi-label classification experiments act to verify the consistency of the subject annotation and the utility of the corpus for training classifiers on this type of data. The analysis of the corpus comprises an investigation of how often the parliament members addressed each subject and the relation between subjects and gender of the speaker. The classification experiments show that classifiers can determine the two co-occurring subjects of the speeches from the agenda titles with a performance similar to that of human annotators. Moreover, a multilayer perceptron achieved an F1-score of 0.68 on the same task when trained on bag of words vectors obtained from the speeches’ lemmas. This is an improvement of more than 0.6 with respect to the baseline, a majority classifier that accounts for the frequency of the classes. The result is promising given the high number of subject combinations (186) and the skewness of the data.

The paper presents a study of how seven Danish left and right wing parties addressed immigration in their 2011, 2015 and 2019 manifestos and in their speeches in the Danish Parliament from 2009 to 2020. The annotated manifestos are produced by the Comparative Manifesto Project, while the parliamentary speeches annotated with policy areas (subjects) have been recently released under CLARIN-DK. In the paper, we investigate how often the seven parties addressed immigration in the manifestos and parliamentary debates, and we analyse both datasets after having applied NLP tools to them. A sentiment analysis tool was run on the manifestos and its results were compared with the manifestos’ annotations, while topic modeling was applied to the parliamentary speeches in order to outline central themes in the immigration debates. Many of the resulting topic groups are related to cultural, religious and integration aspects which were heavily debated by politicians and media when discussing immigration policy during the past decade. Our analyses also show differences and similarities between parties and indicate how the 2015 immigrant crisis is reflected in the two types of data. Finally, we discuss advantages and limitations of our quantitative and tool-based analyses.

In this paper we describe the Danish CLARIN resources, corpora, tools and workflow, which we used and enhanced in order to build the Danish ParlaMint corpus, as part of the CLARIN founded ParlaMint project. More specifically, the article accounts for the manual and automatic processes involved in the preparation of the Danish Parliamentary speeches with focus on the CLARIN-DK tools and Text Tonsorium workflow management. The tools annotated the speeches with metadata and linguistic information in compliance with the common ParlaMint TEI P5 format. As a spin-off of the project, the CLARIN-DK sen-tence tokenizer and the CST Named Entity Recognizer were improved. These tools, to-gether with the CST-lemmatiser, Danish UD-Pipe software and several data transformation utilities, produced all the linguistic annotations in the correct format. We conclude the pa-per with a report of a pilot evaluation of the quality of some of the linguistic annotations in the Danish ParlaMint corpus.

This paper addresses differences in the word use of two left-winged and two right-winged Danish parties, and how these differences, which reflect some of the basic stances of the parties, can be used to automatically identify the party of politicians from their speeches. In the first study, the most frequent and characteristic lemmas in the manifestos of the political parties as well as their language complexity are analysed. The analysis shows inter alia that the most frequently occurring lemmas in the manifestos reflect either the ideology or the position of the parties towards specific subjects, confirming for Danish preceding studies of English and German manifestos. Successively, we scaled our analysis applying NLP methods to the transcribed speeches by members of the same parties in the Parliament (Hansards) and trained machine learning algorithms in order to determine to what extent it is possible to predict the party of the politicians from the speeches. The speeches are a subset of the Danish Parliament corpus 2009–2017. The best results of the classification experiments gave a weighted F1-score of 0.57. These results are significantly better than the results obtained by the majority classifier (weighted F1-score = 0.11) and by chance results. They show that the party of the politicians can be distinguished from their speeches in nearly 60% of the cases, even if they debate about the same subjects and thus often use the same terminology. In the future, we will include the subject of the speeches in the prediction experiments.

We describe an anonymization tool that was commissioned by and specified together with Schultz, a publishing company specialized in Danish law related publications. Unavailability of training data and the need to guarantee compliance with pre-existing anonymization guidelines forced us to implement a tool using manually crafted rules. We used Bracmat, a programming language that is specialized in transforming tree data structures, to meet the requirement to pass the XML structure of the input document unscathed through the whole workflow. The tool attains a reassuringly good recall, makes almost no chunk errors and reduces the found entity designators to a nearly correct set of entities that the input text refers to, minimizing the time needed for manual check and post-editing.

This paper presents the challenges and issues encountered in the conversion of TEI header metadata into the CMDI format. The work is carried out in the Danish research infrastructure, CLARIN-DK, in order to enable the exchange of language resources nationally as well as internationally, in particular with other partners of CLARIN ERIC. The paper describes the task of converting an existing TEI specification applied to all the text resources deposited in DK-CLARIN. During the task we have tried to reuse and share CMDI profiles and components in the CLARIN Component Registry, as well as linking the CMDI components and elements to the relevant data categories in the ISOcat Data Category Registry. The conversion of the existing metadata into the CMDI format turned out not to be a trivial task and the experience and insights gained from this work have resulted in a proposal for a work flow for future use. We also present a core TEI header metadata set.

The initiative CLARIN-DK (starting as a Danish preparatory DK-CLARIN project) is a part of the Danish research infrastructure initiative, DIGHUMLAB. In this paper the aims, status, and the current challenges for CLARIN-DK are presented. CLARIN-DK focuses on written and spoken language resources, multimodal resources and tools, and involving users is a core issue. Users involved in a preparatory project gave input that led to the current user interface of the resource repository website, clarin.dk. Clarin.dk is now in the transition phase from a repository to a research infrastructure, where researchers and students can be supported in their research, education and studies. Clarin.dk works with a Service-Oriented Architecture (SOA), uses eSciDoc and Fedora Commons, and is primarily based on open source solutions. A key issue in CLARIN-DK is using standards such as TEIP5, IMDI, OLAC, and CMDI for resource metadata. Optional metadata fields suggested by users have been included when it could comply with the standards, allowing for the diversity needed when describing the research material. Current work includes normalising metadata naming in the search pages, and making search more user-friendly by adding selectable pick-lists for query values. Also a consolidation of metadata quality is currently performed by changing some metadata values to a more harmonized set of values. All deposited metadata are maintained. Clarin.dk will apply for assessment as a CLARIN ERIC B centre in 2013 enforcing the sustainability and persistency of the infrastructure. Clarin.dk has already joined the national identity federation WAYF, implemented SSL-certificates, and offers harvesting of metadata via OAI-PMH as part of the CLARIN centre requirements.

In this paper, we present the architecture of a distributed resource repository developed for collecting training data for building customized statistical machine translation systems. The repository is designed for the cloud-based translation service integrated in the Let'sMT! platform which is about to be launched to the public. The system includes important features such as automatic import and alignment of textual documents in a variety of formats, a flexible database for meta-information using modern key-value stores and a grid-based backend for running off-line processes. The entire system is very modular and supports highly distributed setups to enable a maximum of flexibility and scalability. The system uses secure connections and includes an effective permission management to ensure data integrity. In this paper, we also take a closer look at the task of sentence alignment. The process of alignment is extremely important for the success of translation models trained on the platform. Alignment decisions significantly influence the quality of SMT engines.

vidensystemer, terminologi, sprogteknologi

Knowledge organisation system, language, engineering

Named Entity Recognition, NER, navnegenkendelse, Sprogteknologi

Ontology, Question-answering

navnegenkendelse, Named Entity Recognition, NER, NE