paper-with-me

Papers

Latin BERT: A Contextual Language Model for Classical Philology

2020-09-21 · David Bamman, Patrick J. Burns

We present 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 affordances of this language-specific model both for work in natural language processing for Latin and in using computational methods 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.

📄 PDF Abstract BibTeX arXiv:2009.10053

Code (1)

dbamman/latin-bert 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingPart-Of-Speech TaggingWord EmbeddingsWord Sense Disambiguation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Weight Decay 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

Graecia capta ferum victorem cepit. Detecting Latin Allusions to Ancient Greek Literature

2023-08-23 · Frederick Riemenschneider, Anette Frank

Intertextual allusions hold a pivotal role in Classical Philology, with Latin authors frequently referencing Ancient Greek texts. Until now, the automatic identification of these intertextual references has been constrai…

Sentence

Exploring Large Language Models for Classical Philology

2023-05-23 · Frederick Riemenschneider, Anette Frank

Recent advances in NLP have led to the creation of powerful language models for many languages including Ancient Greek and Latin. While prior work on Classical languages unanimously uses BERT, in this work we create four…

BenchmarkingDecoderLemmatization

Open Philology at the University of Leipzig

2014-05-01 · LREC 2014 5 · Frederik Baumgardt, Giuseppe Celano, Gregory R. Crane, Stella Dee 외

The Open Philology Project at the University of Leipzig aspires to re-assert the value of philology in its broadest sense. Philology signifies the widest possible use of the linguistic record to enable a deep understandi…

Optical Character Recognition (OCR)

UDPipe at EvaLatin 2020: Contextualized Embeddings and Treebank Embeddings

2020-06-05 · LREC 2020 5 · Milan Straka, Jana Straková

We present our contribution to the EvaLatin shared task, which is the first evaluation campaign devoted to the evaluation of NLP tools for Latin. We submitted a system based on UDPipe 2.0, one of the winners of the CoNLL…

LemmatizationPOSPOS Tagging

PhiloBERTA: A Transformer-Based Cross-Lingual Analysis of Greek and Latin Lexicons

2025-03-07 · Rumi A. Allbert, Makai L. Allbert

We present PhiloBERTA, a cross-lingual transformer model that measures semantic relationships between ancient Greek and Latin lexicons. Through analysis of selected term pairs from classical texts, we use contextual embe…