paper-with-me

홈 › Papers

What does it mean to be language-agnostic? Probing multilingual sentence encoders for typological properties

2020-09-27 · Rochelle Choenni, Ekaterina Shutova

Multilingual sentence encoders have seen much success in cross-lingual model transfer for downstream NLP tasks. Yet, we know relatively little about the properties of individual languages or the general patterns of linguistic variation that they encode. We propose methods for probing sentence representations from state-of-the-art multilingual encoders (LASER, M-BERT, XLM and XLM-R) with respect to a range of typological properties pertaining to lexical, morphological and syntactic structure. In addition, we investigate how this information is distributed across all layers of the models. Our results show interesting differences in encoding linguistic variation associated with different pretraining strategies.

📄 PDF Abstract BibTeX arXiv:2009.12862

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceXLM-R

Methods 이 논문이 사용한 방법론

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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Multi-Head Attention 설명 없음
Attention 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents

2026-06-22 · Yanhang Li, Zhichao Fan, Zexin Zhuang arxiv

Hidden-state probing -- a linear classifier on a frozen vision-language model's internal activations -- has emerged as an attractive evaluation tool for flagging indirect prompt injection (IPI) in multimodal computer-use…

Does BERT Understand Idioms? A Probing-Based Empirical Study of BERT Encodings of Idioms

2021-09-01 · RANLP 2021 9 · Minghuan Tan, Jing Jiang

Understanding idioms is important in NLP. In this paper, we study to what extent pre-trained BERT model can encode the meaning of a potentially idiomatic expression (PIE) in a certain context. We make use of a few existi…

Paraphrase Identification

Probing Graph Representations

2023-03-07 · Mohammad Sadegh Akhondzadeh, Vijay Lingam, Aleksandar Bojchevski

Today we have a good theoretical understanding of the representational power of Graph Neural Networks (GNNs). For example, their limitations have been characterized in relation to a hierarchy of Weisfeiler-Lehman (WL) is…

Diagnostic

Does He Wink or Does He Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models

2021-02-06 · Lutfi Kerem Senel, Hinrich Schütze

Recent progress in pretraining language models on large corpora has resulted in large performance gains on many NLP tasks. These large models acquire linguistic knowledge during pretraining, which helps to improve perfor…

Language ModelingLanguage Modelling

Does She Wink or Does She Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models

2021-04-01 · EACL 2021 2 · Lutfi Kerem Senel, Hinrich Sch{\"u}tze

Recent progress in pretraining language models on large corpora has resulted in significant performance gains on many NLP tasks. These large models acquire linguistic knowledge during pretraining, which helps to improve …

Language ModelingLanguage Modelling