Stylistic variation over 200 years of court proceedings according to
            gender and social class

Degaetano-Ortlieb, Stefania

doi:10.18653/v1/w18-1601

Cited by 12 publications

(14 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Historical texts are of increasing interest in the computational social sciences and digital humanities, offering insights on patterns of language change (Hilpert and Gries, 2016), social norms (Garg et al, 2018), and the history of ideas and culture (Michel et al, 2011). Syntactic analysis can play an important role: researchers have used part-of-speech tagging to identify syntactic changes (Degaetano-Ortlieb, 2018) and dependency parsing to quantify gender-based patterns of adjectival modification and possession in classic literary texts (Vuillemot et al, 2009;Muralidharan and Hearst, 2013). But despite the appeal of using NLP in historical linguistics and literary analysis, there is relatively little research on how performance is impacted by diachronic transfer.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling

Han¹,

Eisenstein²

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

148

137

View full text Add to dashboard Cite

Contextualized word embeddings such as ELMo and BERT provide a foundation for strong performance across a wide range of natural language processing tasks by pretraining on large corpora of unlabeled text. However, the applicability of this approach is unknown when the target domain varies substantially from the pretraining corpus. We are specifically interested in the scenario in which labeled data is available in only a canonical source domain such as newstext, and the target domain is distinct from both the labeled and pretraining texts. To address this scenario, we propose domain-adaptive finetuning, in which the contextualized embeddings are adapted by masked language modeling on text from the target domain. We test this approach on sequence labeling in two challenging domains: Early Modern English and Twitter. Both domains differ substantially from existing pretraining corpora, and domain-adaptive fine-tuning yields substantial improvements over strong BERT baselines, with particularly impressive results on out-ofvocabulary words. We conclude that domainadaptive fine-tuning offers a simple and effective approach for the unsupervised adaptation of sequence labeling to difficult new domains. 1 2 While it might be desirable to completely retrain contextualized word embedding models in the target domain (e.g., , this requires data and computational resources that are often unavailable.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling

Han¹,

Eisenstein²

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

148

137

View full text Add to dashboard Cite

show abstract

“…H1 Registerial adaptation : due to language-external pressures in more formal contexts (court), middle and upper-class women will linguistically adapt to more formal conventions diachronically to meet social pressure (cf. Degaetano-Ortlieb, 2018 )…”

Section: Introductionmentioning

confidence: 99%

“…As for the second point, analyzing and comparing fixed time periods by pre-defining historical stages has been the standard practice (e.g., Kytö, 1993 ; Nevalainen and Raumolin-Brunberg, 2003 ; Degaetano-Ortlieb, 2015 , 2018 ; Teich et al, 2016 ; Säily et al, 2017a ; Degaetano-Ortlieb et al, 2019c ). The rise in interest in the investigation of temporal dynamics of cultural sociolinguistic phenomena has triggered a whole wave of more exploratory, data-driven approaches targeted toward determining when particular changes occur rather than comparing predefined periods.…”

Section: Introductionmentioning

confidence: 99%

Registerial Adaptation vs. Innovation Across Situational Contexts: 18th Century Women in Transition

Degaetano-Ortlieb

Säily

Bizzoni

2021

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

Endeavors to computationally model language variation and change are ever increasing. While analyses of recent diachronic trends are frequently conducted, long-term trends accounting for sociolinguistic variation are less well-studied. Our work sheds light on the temporal dynamics of language use of British 18th century women as a group in transition across two situational contexts. Our findings reveal that in formal contexts women adapt to register conventions, while in informal contexts they act as innovators of change in language use influencing others. While adopted from other disciplines, our methods inform (historical) sociolinguistic work in novel ways. These methods include diachronic periodization by Kullback-Leibler divergence to determine periods of change and relevant features of variation, and event cascades as influencer models.

show abstract

“…Our work fits within this line of research and extends it in novel ways. Similar to prior work, we use an information-theoretic notion of entropy and surprisal to model linguistic relationships (Hughes et al, 2012;Bochkarev et al, 2014;Fankhauser et al, 2014;Vilhena et al, 2014;Evans et al, 2016;Degaetano-Ortlieb, 2018;Degaetano-Ortlieb and Teich, 2018). The consideration of analyzing language change and the development of sublanguages from an informationtheoretic perspective goes back to Harris (1991): in striving for successful communication, distinctive codes develop which facilitate communication -over time and within subgroups.…”

Section: Related Workmentioning

confidence: 99%

The Scientization of Literary Study

Degaetano-Ortlieb

Piper

2019

Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities An

Self Cite

View full text Add to dashboard Cite

Scholarly practices within the humanities have historically been perceived as distinct from the natural sciences. We look at literary studies, a discipline strongly anchored in the humanities, and hypothesize that over the past half-century literary studies has instead undergone a process of "scientization", adopting linguistic behavior similar to the sciences. We test this using methods based on information theory, comparing a corpus of literary studies articles (around 63,400) with a corpus of standard English and scientific English respectively. We show evidence for "scientization" effects in literary studies, though at a more muted level than scientific English, suggesting that literary studies occupies a middle ground with respect to standard English in the larger space of academic disciplines. More generally, our methodology can be applied to investigate the social positioning and development of language use across different domains (e.g. scientific disciplines, language varieties, registers).

show abstract

Stylistic variation over 200 years of court proceedings according to gender and social class

Cited by 12 publications

References 31 publications

Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling

Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling

Registerial Adaptation vs. Innovation Across Situational Contexts: 18th Century Women in Transition

The Scientization of Literary Study

Contact Info

Product

Resources

About