paper-with-me

홈 › Papers

It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning

2021-06-22 · Alexey Tikhonov, Max Ryabinin

Commonsense reasoning is one of the key problems in natural language processing, but the relative scarcity of labeled data holds back the progress for languages other than English. Pretrained cross-lingual models are a source of powerful language-agnostic representations, yet their inherent reasoning capabilities are still actively studied. In this work, we design a simple approach to commonsense reasoning which trains a linear classifier with weights of multi-head attention as features. To evaluate this approach, we create a multilingual Winograd Schema corpus by processing several datasets from prior work within a standardized pipeline and measure cross-lingual generalization ability in terms of out-of-sample performance. The method performs competitively with recent supervised and unsupervised approaches for commonsense reasoning, even when applied to other languages in a zero-shot manner. Also, we demonstrate that most of the performance is given by the same small subset of attention heads for all studied languages, which provides evidence of universal reasoning capabilities in multilingual encoders.

📄 PDF Abstract BibTeX arXiv:2106.12066

Code (1)

yandex-research/crosslingual_winograd 공식 구현 pytorch

Tasks

AllCross-Lingual Transfer

Methods 이 논문이 사용한 방법론

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 $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

It’s All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning

2021-08-01 · Findings (ACL) 2021 8 · Alexey Tikhonov, Max Ryabinin
AllCross-Lingual Transfer

Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks

2021-08-18 · ACL 2021 5 · Weicheng Ma, Kai Zhang, Renze Lou, Lili Wang 외

This paper studies the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. Prior research has found that only a few attention heads a…

XLM-R

Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads

2026-02-25 · Shaswat Patel, Vishvesh Trivedi, Yue Han, Yihuai Hong 외 arxiv

Recent work has identified a subset of attention heads in Transformer as retrieval heads, which are responsible for retrieving information from the context. In this work, we first investigate retrieval heads in multiling…

Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?

2021-05-31 · Findings (ACL) 2021 8 · Zae Myung Kim, Laurent Besacier, Vassilina Nikoulina, Didier Schwab

Recent studies on the analysis of the multilingual representations focus on identifying whether there is an emergence of language-independent representations, or whether a multilingual model partitions its weights among …

DecoderMachine TranslationNMTTranslation

Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models

2025-11-10 · Xin Liu, Qiyang Song, Qihang Zhou, Haichao Du 외 arxiv

Large language models (LLMs) increasingly support multilingual understanding and generation. Meanwhile, efforts to interpret their internal mechanisms have emerged, offering insights to enhance multilingual performance. …