中文
相关论文

相关论文: Which Word Orders Facilitate Length Generalization…

200 篇论文

Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans. However, empirical evidence has been limited to experiments with highly simplified artificial languages, and whether…

计算与语言 · 计算机科学 2025-02-19 Tianyang Xu , Tatsuki Kuribayashi , Yohei Oseki , Ryan Cotterell , Alex Warstadt

The world's languages exhibit certain so-called typological or implicational universals; for example, Subject-Object-Verb (SOV) languages typically use postpositions. Explaining the source of such biases is a key goal of linguistics. We…

计算与语言 · 计算机科学 2024-06-11 Tatsuki Kuribayashi , Ryo Ueda , Ryo Yoshida , Yohei Oseki , Ted Briscoe , Timothy Baldwin

Since language models are used to model a wide variety of languages, it is natural to ask whether the neural architectures used for the task have inductive biases towards modeling particular types of languages. Investigation of these biases…

计算与语言 · 计算机科学 2021-06-03 Jennifer C. White , Ryan Cotterell

Do language models (LMs) offer insights into human language learning? A common argument against this idea is that because their architecture and training paradigm are so vastly different from humans, LMs can learn arbitrary inputs as easily…

计算与语言 · 计算机科学 2025-09-24 Xiulin Yang , Tatsuya Aoyama , Yuekun Yao , Ethan Wilcox

Many of the thousands of attested languages share common configurations of features, creating a spectrum from typologically very rare (e.g., object-verb-subject word order) or impossible languages to very common combinations of features…

计算与语言 · 计算机科学 2026-04-30 Nadine El-Naggar , Tatsuki Kuribayashi , Ted Briscoe

Large language models (LLMs) are solidifying their position in the modern world as effective tools for the automatic generation of text. Their use is quickly becoming commonplace in fields such as education, healthcare, and scientific…

计算与语言 · 计算机科学 2025-10-08 Luka Terčon , Kaja Dobrovoljc

Futrell and Mahowald (2025) frame the success of neural language models (LMs) as supporting gradient, usage-based linguistic theories. I argue that LMs can also instantiate theories based on formal structures - the types of theories seen in…

计算与语言 · 计算机科学 2026-05-12 R. Thomas McCoy

Large language models (LLMs) are advanced artificial intelligence (AI) systems that can perform a variety of tasks commonly found in human intelligence tests, such as defining words, performing calculations, and engaging in verbal…

计算与语言 · 计算机科学 2024-09-12 David Ilić , Gilles E. Gignac

What mechanisms underlie linguistic generalization in large language models (LLMs)? This question has attracted considerable attention, with most studies analyzing the extent to which the language skills of LLMs resemble rules. As of yet,…

计算与语言 · 计算机科学 2024-11-13 Valentin Hofmann , Leonie Weissweiler , David Mortensen , Hinrich Schütze , Janet Pierrehumbert

Linguistic evaluations of how well LMs generalize to produce or understand language often implicitly take for granted that natural languages are generated by symbolic rules. According to this perspective, grammaticality is determined by…

计算与语言 · 计算机科学 2025-09-19 Leonie Weissweiler , Kyle Mahowald , Adele Goldberg

Can a machine understand the meanings of natural language? Recent developments in the generative large language models (LLMs) of artificial intelligence have led to the belief that traditional philosophical assumptions about machine…

计算与语言 · 计算机科学 2023-10-27 Vladimír Havlík

Empirical grammar research has become increasingly data-driven, but the systematic analysis of annotated corpora still requires substantial methodological and technical effort. We explore how agentic large language models (LLMs) can…

计算与语言 · 计算机科学 2025-12-02 Matej Klemen , Tjaša Arčon , Luka Terčon , Marko Robnik-Šikonja , Kaja Dobrovoljc

Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…

计算与语言 · 计算机科学 2024-12-16 Tom Kouwenhoven , Max Peeperkorn , Tessa Verhoef

Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human,…

计算与语言 · 计算机科学 2025-05-29 Tom Kouwenhoven , Max Peeperkorn , Roy de Kleijn , Tessa Verhoef

Language models are typically evaluated on their success at predicting the distribution of specific words in specific contexts. Yet linguistic knowledge also encodes relationships between contexts, allowing inferences between word…

计算与语言 · 计算机科学 2023-11-09 Michael Wilson , Jackson Petty , Robert Frank

Lambek Grammars (LG) are a computational modelling of natural language, based on non-commutative compositional types. It has been widely studied, especially for languages where the syntax plays a major role (like English). The goal of this…

计算与语言 · 计算机科学 2020-02-04 Valentin D. Richard

The advent of Large Language Models (LLMs) has significantly transformed the fields of natural and social sciences. Generative Agent-Based Models (GABMs), which utilize large language models in place of real subjects, are gaining increasing…

物理与社会 · 物理学 2024-08-20 Yikang Lu , Alberto Aleta , Chunpeng Du , Lei Shi , Yamir Moreno

Grammaticality and likelihood are distinct notions in human language. Pretrained language models (LMs), which are probabilistic models of language fitted to maximize corpus likelihood, generate grammatically well-formed text and…

计算与语言 · 计算机科学 2026-05-07 Yingshan Susan Wang , Linlu Qiu , Zhaofeng Wu , Roger P. Levy , Yoon Kim

In the past year, Generative Recommendations (GRs) have undergone substantial advancements, especially in leveraging the powerful sequence modeling and reasoning capabilities of Large Language Models (LLMs) to enhance overall recommendation…

信息检索 · 计算机科学 2025-07-15 Zhen Yang , Haitao Lin , Jiawei xue , Ziji Zhang

We examine a methodology using neural language models (LMs) for analyzing the word order of language. This LM-based method has the potential to overcome the difficulties existing methods face, such as the propagation of preprocessor errors…

计算与语言 · 计算机科学 2020-05-05 Tatsuki Kuribayashi , Takumi Ito , Jun Suzuki , Kentaro Inui
‹ 上一页 1 2 3 10 下一页 ›