Domain-Specific Word Embeddings with Structure Prediction

Autor: Brandl, Stephanie, Lassner, David, Baillot, Anne, Nakajima, Shinichi

Complementary to finding good general word embeddings, an important question for representation learning is to find dynamic word embeddings, e.g., across time or domain. Current methods do not offer a way to use or predict information on structure be

Externí odkaz: http://arxiv.org/abs/2210.04962

Balancing the composition of word embeddings across heterogenous data sets

Autor: Brandl, Stephanie, Lassner, David, Alber, Maximilian

Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relationships are solely learned from the data and subsequently the data co

Externí odkaz: http://arxiv.org/abs/2001.04693

Humanistic NLP: Bridging the Gap Between Digital Humanities and Natural Language Processing

Autor: Tasovac, Toma, Ermolaev, Natalia, Janco, Andrew, Lassner, David, Budak, Nick

Humanistic NLP articulates the multiple challenges facing interactions between NLP and humanities research and offers solutions to bridge this gap. Not merely an application of NLP in DH, it should be considered as an opportunity to engage more human

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf3f86008425f49d1c2b9e1320945395

Analysis of textual variants with robust machine learning methods: Towards novel insights for the digital humanities

Autor: Lassner, David

The analysis of textual variants allows us to explore how a given literary text came into being. This involves the analysis of the author’s writing process and aesthetic inspirations but also analysing others who influenced the history of the text,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fa52c8113222bef01c4d3cfe5632ab62

Publishing an OCR ground truth data set for reuse in an unclear copyright setting.: Two case studies with legal and technical solutions to enable a collective OCR ground truth data set effort

Autor: Lassner, David, Neudecker, Clemens, Coburger, Julius, Baillot, Anne

Publikováno v: Zeitschrift für digitale Geisteswissenschaften
Zeitschrift für digitale Geisteswissenschaften, 2021, Fabrikation von Erkenntnis – Experimente in den Digital Humanities, Sonderband 5, ⟨10.17175/sb005_006⟩

International audience; We present an OCR ground truth data set for historical prints and show improvement of recognition results over baselines with training on this data. We reflect on reusability of the ground truth data set based on two experimen

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::b28f005a4e24fef1f776b3ecf838aae1
https://hal.archives-ouvertes.fr/hal-03482671/document