paper-with-me

홈 › Papers

A Crucial Parameter for Rank-Frequency Relation in Natural Languages

2024-02-01 · Chenchen Ding

$f \propto r^{-\alpha} \cdot (r+\gamma)^{-\beta}$ has been empirically shown more precise than a na\"ive power law $f\propto r^{-\alpha}$ to model the rank-frequency ($r$-$f$) relation of words in natural languages. This work shows that the only crucial parameter in the formulation is $\gamma$, which depicts the resistance to vocabulary growth on a corpus. A method of parameter estimation by searching an optimal $\gamma$ is proposed, where a ``zeroth word'' is introduced technically for the calculation. The formulation and parameters are further discussed with several case studies.

📄 PDF Abstract BibTeX arXiv:2402.00271

Code (0)

등록된 구현이 없습니다.

Tasks

parameter estimationRelation

Similar Papers 제목 키워드 기반

A Three-Parameter Rank-Frequency Relation in Natural Languages

2020-07-01 · ACL 2020 6 · Chenchen Ding, Masao Utiyama, Eiichiro Sumita

We present that, the rank-frequency relation in textual data follows $f \propto r^{-\alpha}(r+\gamma)^{-\beta}$, where $f$ is the token frequency and $r$ is the rank by frequency, with ($\alpha$, $\beta$, $\gamma$) as pa…

Relation

Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting

2022-05-01 · ACL 2022 5 · Ying Su, Hongming Zhang, Yangqiu Song, Tong Zhang

Word sense disambiguation (WSD) is a crucial problem in the natural language processing (NLP) community. Current methods achieve decent performance by utilizing supervised learning and large pre-trained language models. …

RelationWord Sense Disambiguation

A Two Parameters Equation for Word Rank-Frequency Relation

2022-05-02 · Chenchen Ding

Let $f (\cdot)$ be the absolute frequency of words and $r$ be the rank of words in decreasing order of frequency, then the following function can fit the rank-frequency relation \[ f (r;s,t) = \left(\frac{r_{\tt max}}{r}…

RelationVocal Bursts Valence Prediction

FAAR: Efficient Frequency-Aware Multi-Task Fine-Tuning via Automatic Rank Selection

2026-03-20 · Maxime Fontana, Michael Spratling, Miaojing Shi arxiv

Adapting models pre-trained on large-scale datasets is a proven way to reach strong performance quickly for down-stream tasks. However, the growth of state-of-the-art mod-els makes traditional full fine-tuning unsuitable…

parameter-efficient fine-tuningMulti-Task Learning

Fourier Low-rank and Sparse Tensor for Efficient Tensor Completion

2025-05-16 · Jingyang Li, Jiuqian Shang, Yang Chen

Tensor completion is crucial in many scientific domains with missing data problems. Traditional low-rank tensor models, including CP, Tucker, and Tensor-Train, exploit low-dimensional structures to recover missing data. …

Computational Efficiency