Humanist Discussion Group

Humanist Archives: June 23, 2023, 6:49 a.m. Humanist 37.123 - events: conceptual language model for classical philology

				
              Humanist Discussion Group, Vol. 37, No. 123.
        Department of Digital Humanities, University of Cologne
                      Hosted by DH-Cologne
                       www.dhhumanist.org
                Submit to: humanist@dhhumanist.org




        Date: 2023-06-22 19:04:53+00:00
        From: Willard McCarty <willard.mccarty@mccarty.org.uk>
        Subject: Digital Classicist London seminar: Latin BERT: A Contextual Language Model for Classical Philology

[From:   Marco Dosi, The Digital Classicist List <DIGITALCLASSICIST@JISCMAIL.AC.UK>]


Latin BERT: A Contextual Language Model for Classical Philology
David Bamman (Berkeley)

Friday June 23, 2023, 17:00 BST
Room 349, Third Floor, Senate House, Malet Street, London WC1E 7HU

This seminar will also be livestreamed at
<https://www.youtube.com/watch?v=JDiYA8_AHus>

Much work in the space of natural language processing has shifted toward
exploring the affordances of contextual language models (such as the
BERT and GPT families), which learn representations of words that are
sensitive to the sentence context in which they are used. In this talk,
I'll discuss Latin BERT, a contextual language model for the Latin
language, trained on 642.7 million words from a variety of sources
spanning the Classical era to the 21st century. In a series of case
studies, we illustrate the uses of this language-specific model both for
work in natural language processing for Latin and for traditional
scholarship: we show that Latin BERT achieves a new state of the art for
part-of-speech tagging on all three Universal Dependency datasets for
Latin and can be used for predicting missing text (including critical
emendations); we create a new dataset for assessing word sense
disambiguation for Latin and demonstrate that Latin BERT outperforms
static word embeddings; and we show that it can be used for
semantically-informed search by querying contextual nearest neighbors.
We publicly release trained models to help drive future work in this space.



_______________________________________________
Unsubscribe at: http://dhhumanist.org/Restricted
List posts to: humanist@dhhumanist.org
List info and archives at at: http://dhhumanist.org
Listmember interface at: http://dhhumanist.org/Restricted/
Subscribe at: http://dhhumanist.org/membership_form.php