paper-with-me

Papers

Morphology Informed Selections for Subword Vocabulary Size

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Currently, guidance around selection of an optimal or appropriate subword vocabulary size is incomplete and confusing at best. Using a measure of subword-morpheme overlap, our analysis shows that one can find a "sweet spot" for a morphology informed subword vocabulary size. This sweet spot exhibits some variation with respect to text complexity and the morphological characteristics of a language. However, it is relatively constant with respect to corpus size.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Optimal Turkish Subword Strategies at Scale: Systematic Evaluation of Data, Vocabulary, Morphology Interplay

2026-02-06 · Duygu Altinok arxiv

Tokenization is a pivotal design choice for neural language modeling in morphologically rich languages (MRLs) such as Turkish, where productive agglutination challenges both vocabulary efficiency and morphological fideli…

Dependency ParsingSentiment Analysis

Morphological and Language-Agnostic Word Segmentation for NMT

2018-06-14 · Dominik Macháček, Jonáš Vidra, Ondřej Bojar

The state of the art of handling rich morphology in neural machine translation (NMT) is to break word forms into subword units, so that the overall vocabulary size of these units fits the practical limits given by the NM…

GPUMachine TranslationNMTTranslation

SubICap: Towards Subword-informed Image Captioning

2020-12-24 · Naeha Sharif, Mohammed Bennamoun, Wei Liu, Syed Afaq Ali Shah

Existing Image Captioning (IC) systems model words as atomic units in captions and are unable to exploit the structural information in the words. This makes representation of rare words very difficult and out-of-vocabula…

Image CaptioningLanguage ModelingLanguage Modelling

Greed is All You Need: An Evaluation of Tokenizer Inference Methods

2024-03-02 · Omri Uzan, Craig W. Schmidt, Chris Tanner, Yuval Pinter

While subword tokenizers such as BPE and WordPiece are typically used to build vocabularies for NLP models, the method of decoding text into a sequence of tokens from these vocabularies is often left unspecified, or ill-…

All

Subword-level Composition Functions for Learning Word Embeddings

2018-06-01 · WS 2018 6 · Bofang Li, Aleks Drozd, R, Tao Liu 외

Subword-level information is crucial for capturing the meaning and morphology of words, especially for out-of-vocabulary entries. We propose CNN- and RNN-based subword-level composition functions for learning word embedd…

Learning Word EmbeddingsWord Embeddings