paper-with-me

홈 › Papers

Less is Better: A cognitively inspired unsupervised model for language segmentation

2020-12-01 · COLING (CogALex) 2020 12 · Jinbiao Yang, Stefan L. Frank, Antal Van den Bosch

Language users process utterances by segmenting them into many cognitive units, which vary in their sizes and linguistic levels. Although we can do such unitization/segmentation easily, its cognitive mechanism is still not clear. This paper proposes an unsupervised model, Less-is-Better (LiB), to simulate the human cognitive process with respect to language unitization/segmentation. LiB follows the principle of least effort and aims to build a lexicon which minimizes the number of unit tokens (alleviating the effort of analysis) and number of unit types (alleviating the effort of storage) at the same time on any given corpus. LiB’s workflow is inspired by empirical cognitive phenomena. The design makes the mechanism of LiB cognitively plausible and the computational requirement light-weight. The lexicon generated by LiB performs the best among different types of lexicons (e.g. ground-truth words) both from an information-theoretical view and a cognitive view, which suggests that the LiB lexicon may be a plausible proxy of the mental lexicon.

📄 PDF Abstract BibTeX

Code (1)

ray306/lib 공식 구현

Tasks

Segmentation

Similar Papers 제목 키워드 기반

Cooking Up Creativity: A Cognitively-Inspired Approach for Enhancing LLM Creativity through Structured Representations

2025-04-29 · Moran Mizrahi, Chen Shani, Gabriel Stanovsky, Dan Jurafsky 외

Large Language Models (LLMs) excel at countless tasks, yet struggle with creativity. In this paper, we introduce a novel approach that couples LLMs with structured representations and cognitively inspired manipulations t…

Diversity

Increasing The Performance of Cognitively Inspired Data-Efficient Language Models via Implicit Structure Building

2023-10-31 · Omar Momen, David Arps, Laura Kallmeyer

In this paper, we describe our submission to the BabyLM Challenge 2023 shared task on data-efficient language model (LM) pretraining (Warstadt et al., 2023). We train transformer-based masked language models that incorpo…

Language ModelingLanguage ModellingSentence

CogNLP-Sheffield at CMCL 2021 Shared Task: Blending Cognitively Inspired Features with Transformer-based Language Models for Predicting Eye Tracking Patterns

2021-06-01 · NAACL (CMCL) 2021 6 · Peter Vickers, Rosa Wainwright, Harish Tayyar Madabushi, Aline Villavicencio

The CogNLP-Sheffield submissions to the CMCL 2021 Shared Task examine the value of a variety of cognitively and linguistically inspired features for predicting eye tracking patterns, as both standalone model inputs and a…

Word Embeddings

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

MERALI at SemEval-2017 Task 2 Subtask 1: a Cognitively Inspired approach

2017-08-01 · SEMEVAL 2017 8 · Enrico Mensa, Daniele P. Radicioni, Antonio Lieto

In this paper we report on the participation of the MERALI system to the SemEval Task 2 Subtask 1. The MERALI system approaches conceptual similarity through a simple, cognitively inspired, heuristics; it builds on a lin…

Common Sense ReasoningTask 2