中文
相关论文

相关论文: A Tale of Two Laws of Semantic Change: Predicting …

200 篇论文

We propose a scalable, multifactorial experimental framework that systematically probes LLM sensitivity to subtle semantic changes in pairwise document comparison. We analogize this as a needle-in-a-haystack problem: a single semantically…

计算与语言 · 计算机科学 2026-04-22 Sinan G. Aksoy , Alexandra A. Sabrio , Erik VonKaenel , Lee Burke

Why do children learn some words before others? Understanding individual variability across children and also variability across words, may be informative of the learning processes that underlie language learning. We investigated item-based…

计算与语言 · 计算机科学 2021-11-23 Andrew Z. Flores , Jessica Montag , Jon Willits

In an online community, new words come and go: today's "haha" may be replaced by tomorrow's "lol." Changes in online writing are usually studied as a social process, with innovations diffusing through a network of individuals in a speech…

计算与语言 · 计算机科学 2018-02-15 Ian Stewart , Jacob Eisenstein

In an online community, new words come and go: today's "haha" may be replaced by tomorrow's "lol." Changes in online writing are usually studied as a social process, with innovations diffusing through a network of individuals in a speech…

计算与语言 · 计算机科学 2018-09-03 Ian Stewart , Jacob Eisenstein

Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models…

计算与语言 · 计算机科学 2024-06-11 Zhu Liu , Cunliang Kong , Ying Liu , Maosong Sun

Distributional semantics has deeply changed in the last decades. First, predict models stole the thunder from traditional count ones, and more recently both of them were replaced in many NLP applications by contextualized vectors produced…

计算与语言 · 计算机科学 2022-04-04 Alessandro Lenci , Magnus Sahlgren , Patrick Jeuniaux , Amaru Cuba Gyllensten , Martina Miliani

Contextualized word embeddings in language models have given much advance to NLP. Intuitively, sentential information is integrated into the representation of words, which can help model polysemy. However, context sensitivity also leads to…

计算与语言 · 计算机科学 2022-08-23 Yile Wang , Yue Zhang

With the increasing capabilities of Large Language Models (LLMs), parallel reasoning has emerged as a new inference paradigm that enhances reasoning robustness by concurrently exploring multiple lines of thought before converging on a final…

计算与语言 · 计算机科学 2025-10-15 Ziqi Wang , Boye Niu , Zipeng Gao , Zhi Zheng , Tong Xu , Linghui Meng , Zhongli Li , Jing Liu , Yilong Chen , Chen Zhu , Hua Wu , Haifeng Wang , Enhong Chen

The article is an attempt to contribute to explorations of a common origin for language and planned-collaborative action. It gives `semantics of change' the central stage in the synthesis, from its history and recordkeeping to its…

计算与语言 · 计算机科学 2024-05-14 Cem Bozsahin

Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedness which is not…

计算与语言 · 计算机科学 2014-03-21 Karl Moritz Hermann , Phil Blunsom

This paper presents a new approach for measuring semantic similarity/distance between words and concepts. It combines a lexical taxonomy structure with corpus statistical information so that the semantic distance between nodes in the…

cmp-lg · 计算机科学 2008-02-03 Jay J. Jiang , David W. Conrath

Although much has been said about parallelism in discourse, a formal, computational theory of parallelism structure is still outstanding. In this paper, we present a theory which given two parallel utterances predicts which are the parallel…

cmp-lg · 计算机科学 2008-02-03 Claire Gardent , Michael Kohlhase

This paper explores the robustness of language models (LMs) to variations in the temporal context within factual knowledge. It examines whether LMs can correctly associate a temporal context with a past fact valid over a defined period, by…

计算与语言 · 计算机科学 2025-06-24 Hichem Ammar Khodja , Frédéric Béchet , Quentin Brabant , Alexis Nasr , Gwénolé Lecorvé

Lexical Substitution is the task of replacing a single word in a sentence with a similar one. This should ideally be one that is not necessarily only synonymous, but also fits well into the surrounding context of the target word, while…

计算与语言 · 计算机科学 2025-02-07 Juraj Vladika , Stephen Meisenbacher , Florian Matthes

Recent advances in language and vision push forward the research of captioning a single image to describing visual differences between image pairs. Suppose there are two images, I_1 and I_2, and the task is to generate a description W_{1,2}…

计算机视觉与模式识别 · 计算机科学 2021-02-04 An Yan , Xin Eric Wang , Tsu-Jui Fu , William Yang Wang

This paper introduces a new data augmentation method for neural machine translation that can enforce stronger semantic consistency both within and across languages. Our method is based on Conditional Masked Language Model (CMLM) which is…

计算与语言 · 计算机科学 2022-09-23 Qiao Cheng , Jin Huang , Yitao Duan

We propose an alternate approach to quantifying how well language models learn natural language: we ask how well they match the statistical tendencies of natural language. To answer this question, we analyze whether text generated from…

计算与语言 · 计算机科学 2021-08-31 Clara Meister , Ryan Cotterell

We study the time taken by a language learner to correctly identify the meaning of all words in a lexicon under conditions where many plausible meanings can be inferred whenever a word is uttered. We show that the most basic form of…

物理与社会 · 物理学 2015-05-26 Rainer Reisenauer , Kenny Smith , Richard A. Blythe

Semantic communication aims to convey meaning rather than bit-perfect reproduction, representing a paradigm shift from traditional communication. This paper investigates distribution learning in semantic communication where receivers must…

机器学习 · 计算机科学 2025-08-15 Samer Lahoud , Kinda Khawam

Lexical semantic change detection is a new and innovative research field. The optimal fine-tuning of models including pre- and post-processing is largely unclear. We optimize existing models by (i) pre-training on large corpora and refining…

计算与语言 · 计算机科学 2021-01-28 Jens Kaiser , Sinan Kurtyigit , Serge Kotchourko , Dominik Schlechtweg