paper-with-me

홈 › Papers

Better Than Whitespace: Information Retrieval for Languages without Custom Tokenizers

2022-10-11 · Odunayo Ogundepo, Xinyu Zhang, Jimmy Lin

Tokenization is a crucial step in information retrieval, especially for lexical matching algorithms, where the quality of indexable tokens directly impacts the effectiveness of a retrieval system. Since different languages have unique properties, the design of the tokenization algorithm is usually language-specific and requires at least some lingustic knowledge. However, only a handful of the 7000+ languages on the planet benefit from specialized, custom-built tokenization algorithms, while the other languages are stuck with a "default" whitespace tokenizer, which cannot capture the intricacies of different languages. To address this challenge, we propose a different approach to tokenization for lexical matching retrieval algorithms (e.g., BM25): using the WordPiece tokenizer, which can be built automatically from unsupervised data. We test the approach on 11 typologically diverse languages in the MrTyDi collection: results show that the mBERT tokenizer provides strong relevance signals for retrieval "out of the box", outperforming whitespace tokenization on most languages. In many cases, our approach also improves retrieval effectiveness when combined with existing custom-built tokenizers.

📄 PDF Abstract BibTeX arXiv:2210.05481

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalRetrieval

Methods 이 논문이 사용한 방법론

Test 설명 없음
WordPiece 설명 없음
mBERT mBERT

Similar Papers 제목 키워드 기반

Correcting Whitespace Errors in Digitized Historical Texts

2019-06-01 · WS 2019 6 · S Soni, eep, Lauren Klein, Jacob Eisenstein

Whitespace errors are common to digitized archives. This paper describes a lightweight unsupervised technique for recovering the original whitespace. Our approach is based on count statistics from Google n-grams, which a…

SuperBPE: Space Travel for Language Models

2025-03-17 · Alisa Liu, Jonathan Hayase, Valentin Hofmann, Sewoong Oh 외

The assumption across nearly all language model (LM) tokenization schemes is that tokens should be subwords, i.e., contained within word boundaries. While providing a seemingly reasonable inductive bias, is this common p…

Inductive BiasMMLU

so much depends / upon / a whitespace: Why Whitespace Matters for Poets and LLMs

2025-10-19 · Sriharsh Bhyravajjula, Melanie Walsh, Anna Preus, Maria Antoniak arxiv

Whitespace is a critical component of poetic form, reflecting both adherence to standardized forms and rebellion against those forms. Each poem's whitespace distribution reflects the artistic choices of the poet and is a…

Document Translation vs. Query Translation for Cross-Lingual Information Retrieval in the Medical Domain

2020-07-01 · ACL 2020 6 · Shadi Saleh, Pavel Pecina

We present a thorough comparison of two principal approaches to Cross-Lingual Information Retrieval: document translation (DT) and query translation (QT). Our experiments are conducted using the cross-lingual test collec…

Cross-Lingual Information RetrievalDocument TranslationInformation RetrievalMachine Translation+3

A Character-Aware Encoder for Neural Machine Translation

2016-12-01 · COLING 2016 12 · Zhen Yang, Wei Chen, Feng Wang, Bo Xu

This article proposes a novel character-aware neural machine translation (NMT) model that views the input sequences as sequences of characters rather than words. On the use of row convolution (Amodei et al., 2015), the e…

Machine TranslationNMTTranslation