@conference{Samuel2023,

title = {NorBench – A Benchmark for Norwegian Language Models},

author = {David Samuel and Andrey Kutuzov and Samia Touileb and Erik Velldal and Lilja Øvrelid and Egil Rønningstad and Elina Sigdel and Anna Palatkina},

url = {https://mediafutures.no/2023_nodalida-1_61/},

year  = {2023},

date = {2023-05-24},

urldate = {2023-05-24},

abstract = {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 (both encoder and encoder-decoder based). Finally, we compare and analyze their performance, along with other existing LMs, across the different benchmark tests of NorBench.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Touileb2023,

title = {Measuring Normative and Descriptive Biases in Language Models Using Census Data},

author = {Samia Touileb and Lilja Øvrelid and Erik Velldal},

url = {https://mediafutures.no/2023_eacl-main_164/},

year  = {2023},

date = {2023-05-02},

abstract = {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 a descriptive assessment of reality. In this paper, we introduce an approach for measuring to what degree pre-trained language models are aligned to normative and descriptive occupational distributions. To this end, we use official demographic information about gender–occupation distributions provided by the national statistics agencies of France, Norway, United Kingdom, and the United States. We manually generate template-based sentences combining gendered pronouns and nouns with occupations,

and subsequently probe a selection of ten language models covering the English, French, and Norwegian languages. The scoring system we introduce in this work is language independent, and can be used on any combination of

template-based sentences, occupations, and languages. The approach could also be extended to other dimensions of national census data and other demographic variables.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Barnes2019,

title = {Lexicon information in neural sentiment analysis: a multi-task learning approach},

author = {Jeremy Barnes and Samia Touileb and Lilja Øvrelid and Erik Velldal},

url = {https://www.aclweb.org/anthology/W19-6119.pdf},

year  = {2019},

date = {2019-10-01},

journal = {Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa)},

pages = {175–186},

publisher = {Linköping University Electronic Press},

abstract = {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 lexicons. Our MTL set-up is shown to improve model performance (compared to a single-task set-up) on both English and Norwegian sentence-level sentiment datasets. The paper also introduces a new sentiment lexicon for Norwegian.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}