paper-with-me

Papers

Ling-CL: Understanding NLP Models through Linguistic Curricula

2023-10-31 · Mohamed Elgaar, Hadi Amiri

We employ a characterization of linguistic complexity from psycholinguistic and language acquisition research to develop data-driven curricula to understand the underlying linguistic knowledge that models learn to address NLP tasks. The novelty of our approach is in the development of linguistic curricula derived from data, existing knowledge about linguistic complexity, and model behavior during training. By analyzing several benchmark NLP datasets, our curriculum learning approaches identify sets of linguistic metrics (indices) that inform the challenges and reasoning required to address each task. Our work will inform future research in all NLP areas, allowing linguistic complexity to be considered early in the research and development process. In addition, our work prompts an examination of gold standards and fair evaluation in NLP.

📄 PDF Abstract BibTeX arXiv:2310.20121

Code (1)

clu-uml/ling-cl 공식 구현

Tasks

Language Acquisition

Similar Papers 제목 키워드 기반

Teaching NLP with Bracelets and Restaurant Menus: An Interactive Workshop for Italian Students

2021-04-26 · NAACL (TeachingNLP) 2021 6 · Ludovica Pannitto, Lucia Busso, Claudia Roberta Combei, Lucio Messina 외

Although Natural Language Processing (NLP) is at the core of many tools young people use in their everyday life, high school curricula (in Italy) do not include any computational linguistics education. This lack of expos…

Less is More: Pre-Training Cross-Lingual Small-Scale Language Models with Cognitively-Plausible Curriculum Learning Strategies

2024-10-30 · Suchir Salhan, Richard Diehl Martinez, Zébulon Goriely, Paula Buttery

Curriculum Learning has been a popular strategy to improve the cognitive plausibility of Small-Scale Language Models (SSLMs) in the BabyLM Challenge. However, it has not led to considerable improvements over non-curricul…

Language AcquisitionMasked Language Modeling

VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks

2024-10-17 · Shailaja Keyur Sampat, Mutsumi Nakamura, Shankar Kailas, Kartik Aggarwal 외

Deriving inference from heterogeneous inputs (such as images, text, and audio) is an important skill for humans to perform day-to-day tasks. A similar ability is desirable for the development of advanced Artificial Intel…

Natural Language Understanding

Beyond Shallow Heuristics: Leveraging Human Intuition for Curriculum Learning

2025-08-27 · Vanessa Toborek, Sebastian Müller, Tim Selbach, Tamás Horváth 외 arxiv

Curriculum learning (CL) aims to improve training by presenting data from "easy" to "hard", yet defining and measuring linguistic difficulty remains an open challenge. We investigate whether human-curated simple language…

Curriculum Learning for LLM Pretraining: An Analysis of Learning Dynamics

2026-01-29 · Mohamed Elgaar, Hadi Amiri arxiv

Curriculum learning changes the order of pretraining data, but it remains unclear how ordering changes the learning dynamics. We pretrain models from 14M to 1B parameters for 300B tokens under three linguistically motiva…