paper-with-me

Papers

Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages

2023-05-03 · Elena Sofia Ruzzetti, Federico Ranaldi, Felicia Logozzo, Michele Mastromattei, Leonardo Ranaldi, Fabio Massimo Zanzotto

The impressive achievements of transformers force NLP researchers to delve into how these models represent the underlying structure of natural language. In this paper, we propose a novel standpoint to investigate the above issue: using typological similarities among languages to observe how their respective monolingual models encode structural information. We aim to layer-wise compare transformers for typologically similar languages to observe whether these similarities emerge for particular layers. For this investigation, we propose to use Centered Kernel Alignment to measure similarity among weight matrices. We found that syntactic typological similarity is consistent with the similarity between the weights in the middle layers, which are the pretrained BERT layers to which syntax encoding is generally attributed. Moreover, we observe that a domain adaptation on semantically equivalent texts enhances this similarity among weight matrices.

📄 PDF Abstract BibTeX arXiv:2305.02215

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Methods 이 논문이 사용한 방법론

Attention 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 $x$…
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
WordPiece 설명 없음
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

The Past, Present, and Future of Typological Databases in NLP

2023-10-20 · Emi Baylor, Esther Ploeger, Johannes Bjerva

Typological information has the potential to be beneficial in the development of NLP models, particularly for low-resource languages. Unfortunately, current large-scale typological databases, notably WALS and Grambank, a…

Language ModelingLanguage Modelling

Are All Good Word Vector Spaces Isomorphic?

2020-04-08 · EMNLP 2020 11 · Ivan Vulić, Sebastian Ruder, Anders Søgaard

Existing algorithms for aligning cross-lingual word vector spaces assume that vector spaces are approximately isomorphic. As a result, they perform poorly or fail completely on non-isomorphic spaces. Such non-isomorphism…

All

Investigating Language Relationships in Multilingual Sentence Encoders Through the Lens of Linguistic Typology

2022-09-01 · CL (ACL) 2022 9 · Rochelle Choenni, Ekaterina Shutova

Multilingual sentence encoders have seen much success in cross-lingual model transfer for downstream NLP tasks. The success of this transfer is, however, dependent on the model’s ability to encode the patterns of cross-l…

SentenceXLM-R

Toward Universal Dependencies for Shipibo-Konibo

2018-11-01 · WS 2018 11 · Alonso Vasquez, Renzo Ego Aguirre, C Angulo, y 외

We present an initial version of the Universal Dependencies (UD) treebank for Shipibo-Konibo, the first South American, Amazonian, Panoan and Peruvian language with a resource built under UD. We describe the linguistic a…

Dependency ParsingMachine Translation

Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models

2026-02-03 · Vitalii Hirak, Jaap Jumelet, Arianna Bisazza arxiv

Despite major advances in multilingual modeling, large quality disparities persist across languages. Besides the obvious impact of uneven training resources, typological properties have also been proposed to determine th…

Machine Translation