@article{Touileb2020,

title = {Gender and sentiment, critics and authors: a dataset of Norwegian book reviews},

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

url = {https://www.aclweb.org/anthology/2020.gebnlp-1.11.pdf},

year  = {2020},

date = {2020-12-01},

journal = {Gender Bias in Natural Language Processing. Association for Computational Linguistics},

abstract = {Gender bias in models and datasets is widely studied in NLP. The focus has usually been on analysing how females and males express themselves, or how females and males are described. However, a less studied aspect is the combination of these two perspectives, how female and male describe the same or opposite gender. In this paper, we present a new gender annotated sentiment dataset of critics reviewing the works of female and male authors. We investigate if this newly annotated dataset contains differences in how the works of male and female authors are critiqued, in particular in terms of positive and negative sentiment. We also explore the differences in how this is done by male and female critics. We show that there are differences in how critics assess the works of authors of the same or opposite gender. For example, male critics rate crime novels written by females, and romantic and sentimental works written by males, more negatively.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Barnes2020,

title = {Improving sentiment analysis with multi-task learning of negation},

author = {J Barnes and Erik Velldal and Lilja Øvrelid},

url = {https://www.cambridge.org/core/journals/natural-language-engineering/article/abs/improving-sentiment-analysis-with-multitask-learning-of-negation/14EF2B829EC4B8EC29E7C0C5C77B95B0},

year  = {2020},

date = {2020-11-11},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Lison2020,

title = {Named Entity Recognition without Labelled Data: A Weak Supervision Approach},

author = {Pierre Lison and Aliaksandr Hubin and Jeremy Barnes and Samia Touileb},

url = {https://arxiv.org/pdf/2004.14723.pdf},

year  = {2020},

date = {2020-04-30},

journal = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},

pages = {1518–1533},

abstract = {Named Entity Recognition (NER) performance often degrades rapidly when applied to target domains that differ from the texts observed during training. When in-domain labelled data is available, transfer learning techniques can be used to adapt existing NER models to the target domain. But what should one do when there is no hand-labelled data for the target domain? This paper presents a simple but powerful approach to learn NER models in the absence of labelled data through weak supervision. The approach relies on a broad spectrum of labelling functions to automatically annotate texts from the target domain. These annotations are then merged together using a hidden Markov model which captures the varying accuracies and confusions of the labelling functions. A sequence labelling model can finally be trained on the basis of this unified annotation. We evaluate the approach on two English datasets (CoNLL 2003 and news articles from Reuters and Bloomberg) and demonstrate an improvement of about 7 percentage points in entity-level F1 scores compared to an out-of-domain neural NER model.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{deSmedt2020,

title = {FAIR Digital Objects for Science: From Data Pieces to Actionable Knowledge Units},

author = {Koenraad de Smedt and D Koureas and P Wittenberg},

url = {https://ideas.repec.org/a/gam/jpubli/v8y2020i2p21-d344422.html},

year  = {2020},

date = {2020-04-01},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Touileb2017,

title = {Automatic identification of unknown names with specific roles},

author = {Samia Touileb and Truls Pedersen and Helle Sjøvaag},

url = {https://www.aclweb.org/anthology/W18-4517.pdf},

year  = {2017},

date = {2017-08-01},

journal = {Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature},

pages = {150-158},

abstract = {Automatically identifying persons in a particular role within a large corpus can be a difficult task, especially if you don’t know who you are actually looking for. Resources compiling names of persons can be available, but no exhaustive lists exist. However, such lists usually contain known names that are “visible” in the national public sphere, and tend to ignore the marginal and international ones. In this article we propose a method for automatically generating suggestions of names found in a corpus of Norwegian news articles, and which “naturally” belong to a given initial list of members, and that were not known (compiled in a list) beforehand. The approach is based, in part, on the assumption that surface level syntactic features reveal parts of the underlying semantic content and can help uncover the structure of the language.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rosén2016,

title = {The enrichment of lexical resources through incremental parsebanking},

author = {V Rosén and M Thunes and P Haugereid and GS Losnegaard and H Dyvik and P Meurer and G Lyse and Koenraad De Smedt},

url = {https://bora.uib.no/bora-xmlui/handle/1956/15680},

year  = {2016},

date = {2016-06-01},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Velldal2012,

title = {Speculation and negation: Rules, rankers, and the role of syntax},

author = {Erik Velldal and Lilja Øvrelid and J Read and S Oepen},

url = {https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00126},

year  = {2012},

date = {2012-01-01},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Touileb2020,

title = {Gender and sentiment, critics and authors: a dataset of Norwegian book reviews},

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

url = {https://www.aclweb.org/anthology/2020.gebnlp-1.11.pdf},

year  = {2020},

date = {2020-12-01},

journal = {Gender Bias in Natural Language Processing. Association for Computational Linguistics},

abstract = {Gender bias in models and datasets is widely studied in NLP. The focus has usually been on analysing how females and males express themselves, or how females and males are described. However, a less studied aspect is the combination of these two perspectives, how female and male describe the same or opposite gender. In this paper, we present a new gender annotated sentiment dataset of critics reviewing the works of female and male authors. We investigate if this newly annotated dataset contains differences in how the works of male and female authors are critiqued, in particular in terms of positive and negative sentiment. We also explore the differences in how this is done by male and female critics. We show that there are differences in how critics assess the works of authors of the same or opposite gender. For example, male critics rate crime novels written by females, and romantic and sentimental works written by males, more negatively.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Barnes2020,

title = {Improving sentiment analysis with multi-task learning of negation},

author = {J Barnes and Erik Velldal and Lilja Øvrelid},

url = {https://www.cambridge.org/core/journals/natural-language-engineering/article/abs/improving-sentiment-analysis-with-multitask-learning-of-negation/14EF2B829EC4B8EC29E7C0C5C77B95B0},

year  = {2020},

date = {2020-11-11},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Lison2020,

title = {Named Entity Recognition without Labelled Data: A Weak Supervision Approach},

author = {Pierre Lison and Aliaksandr Hubin and Jeremy Barnes and Samia Touileb},

url = {https://arxiv.org/pdf/2004.14723.pdf},

year  = {2020},

date = {2020-04-30},

journal = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},

pages = {1518–1533},

abstract = {Named Entity Recognition (NER) performance often degrades rapidly when applied to target domains that differ from the texts observed during training. When in-domain labelled data is available, transfer learning techniques can be used to adapt existing NER models to the target domain. But what should one do when there is no hand-labelled data for the target domain? This paper presents a simple but powerful approach to learn NER models in the absence of labelled data through weak supervision. The approach relies on a broad spectrum of labelling functions to automatically annotate texts from the target domain. These annotations are then merged together using a hidden Markov model which captures the varying accuracies and confusions of the labelling functions. A sequence labelling model can finally be trained on the basis of this unified annotation. We evaluate the approach on two English datasets (CoNLL 2003 and news articles from Reuters and Bloomberg) and demonstrate an improvement of about 7 percentage points in entity-level F1 scores compared to an out-of-domain neural NER model.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{deSmedt2020,

title = {FAIR Digital Objects for Science: From Data Pieces to Actionable Knowledge Units},

author = {Koenraad de Smedt and D Koureas and P Wittenberg},

url = {https://ideas.repec.org/a/gam/jpubli/v8y2020i2p21-d344422.html},

year  = {2020},

date = {2020-04-01},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Touileb2017,

title = {Automatic identification of unknown names with specific roles},

author = {Samia Touileb and Truls Pedersen and Helle Sjøvaag},

url = {https://www.aclweb.org/anthology/W18-4517.pdf},

year  = {2017},

date = {2017-08-01},

journal = {Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature},

pages = {150-158},

abstract = {Automatically identifying persons in a particular role within a large corpus can be a difficult task, especially if you don’t know who you are actually looking for. Resources compiling names of persons can be available, but no exhaustive lists exist. However, such lists usually contain known names that are “visible” in the national public sphere, and tend to ignore the marginal and international ones. In this article we propose a method for automatically generating suggestions of names found in a corpus of Norwegian news articles, and which “naturally” belong to a given initial list of members, and that were not known (compiled in a list) beforehand. The approach is based, in part, on the assumption that surface level syntactic features reveal parts of the underlying semantic content and can help uncover the structure of the language.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rosén2016,

title = {The enrichment of lexical resources through incremental parsebanking},

author = {V Rosén and M Thunes and P Haugereid and GS Losnegaard and H Dyvik and P Meurer and G Lyse and Koenraad De Smedt},

url = {https://bora.uib.no/bora-xmlui/handle/1956/15680},

year  = {2016},

date = {2016-06-01},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Velldal2012,

title = {Speculation and negation: Rules, rankers, and the role of syntax},

author = {Erik Velldal and Lilja Øvrelid and J Read and S Oepen},

url = {https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00126},

year  = {2012},

date = {2012-01-01},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Touileb2020,

title = {Gender and sentiment, critics and authors: a dataset of Norwegian book reviews},

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

url = {https://www.aclweb.org/anthology/2020.gebnlp-1.11.pdf},

year  = {2020},

date = {2020-12-01},

journal = {Gender Bias in Natural Language Processing. Association for Computational Linguistics},

abstract = {Gender bias in models and datasets is widely studied in NLP. The focus has usually been on analysing how females and males express themselves, or how females and males are described. However, a less studied aspect is the combination of these two perspectives, how female and male describe the same or opposite gender. In this paper, we present a new gender annotated sentiment dataset of critics reviewing the works of female and male authors. We investigate if this newly annotated dataset contains differences in how the works of male and female authors are critiqued, in particular in terms of positive and negative sentiment. We also explore the differences in how this is done by male and female critics. We show that there are differences in how critics assess the works of authors of the same or opposite gender. For example, male critics rate crime novels written by females, and romantic and sentimental works written by males, more negatively.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Barnes2020,

title = {Improving sentiment analysis with multi-task learning of negation},

author = {J Barnes and Erik Velldal and Lilja Øvrelid},

url = {https://www.cambridge.org/core/journals/natural-language-engineering/article/abs/improving-sentiment-analysis-with-multitask-learning-of-negation/14EF2B829EC4B8EC29E7C0C5C77B95B0},

year  = {2020},

date = {2020-11-11},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Lison2020,

title = {Named Entity Recognition without Labelled Data: A Weak Supervision Approach},

author = {Pierre Lison and Aliaksandr Hubin and Jeremy Barnes and Samia Touileb},

url = {https://arxiv.org/pdf/2004.14723.pdf},

year  = {2020},

date = {2020-04-30},

journal = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},

pages = {1518–1533},

abstract = {Named Entity Recognition (NER) performance often degrades rapidly when applied to target domains that differ from the texts observed during training. When in-domain labelled data is available, transfer learning techniques can be used to adapt existing NER models to the target domain. But what should one do when there is no hand-labelled data for the target domain? This paper presents a simple but powerful approach to learn NER models in the absence of labelled data through weak supervision. The approach relies on a broad spectrum of labelling functions to automatically annotate texts from the target domain. These annotations are then merged together using a hidden Markov model which captures the varying accuracies and confusions of the labelling functions. A sequence labelling model can finally be trained on the basis of this unified annotation. We evaluate the approach on two English datasets (CoNLL 2003 and news articles from Reuters and Bloomberg) and demonstrate an improvement of about 7 percentage points in entity-level F1 scores compared to an out-of-domain neural NER model.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{deSmedt2020,

title = {FAIR Digital Objects for Science: From Data Pieces to Actionable Knowledge Units},

author = {Koenraad de Smedt and D Koureas and P Wittenberg},

url = {https://ideas.repec.org/a/gam/jpubli/v8y2020i2p21-d344422.html},

year  = {2020},

date = {2020-04-01},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Touileb2017,

title = {Automatic identification of unknown names with specific roles},

author = {Samia Touileb and Truls Pedersen and Helle Sjøvaag},

url = {https://www.aclweb.org/anthology/W18-4517.pdf},

year  = {2017},

date = {2017-08-01},

journal = {Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature},

pages = {150-158},

abstract = {Automatically identifying persons in a particular role within a large corpus can be a difficult task, especially if you don’t know who you are actually looking for. Resources compiling names of persons can be available, but no exhaustive lists exist. However, such lists usually contain known names that are “visible” in the national public sphere, and tend to ignore the marginal and international ones. In this article we propose a method for automatically generating suggestions of names found in a corpus of Norwegian news articles, and which “naturally” belong to a given initial list of members, and that were not known (compiled in a list) beforehand. The approach is based, in part, on the assumption that surface level syntactic features reveal parts of the underlying semantic content and can help uncover the structure of the language.},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rosén2016,

title = {The enrichment of lexical resources through incremental parsebanking},

author = {V Rosén and M Thunes and P Haugereid and GS Losnegaard and H Dyvik and P Meurer and G Lyse and Koenraad De Smedt},

url = {https://bora.uib.no/bora-xmlui/handle/1956/15680},

year  = {2016},

date = {2016-06-01},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Velldal2012,

title = {Speculation and negation: Rules, rankers, and the role of syntax},

author = {Erik Velldal and Lilja Øvrelid and J Read and S Oepen},

url = {https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00126},

year  = {2012},

date = {2012-01-01},

note = {Pre SFI},

keywords = {},

pubstate = {published},

tppubtype = {article}

}