中文
相关论文

相关论文: Are Representations Built from the Ground Up? An E…

200 篇论文

By virtue of linguistic compositionality, few syntactic rules and a finite lexicon can generate an unbounded number of sentences. That is, language, though seemingly high-dimensional, can be explained using relatively few degrees of…

计算与语言 · 计算机科学 2025-06-18 Jin Hwa Lee , Thomas Jiralerspong , Lei Yu , Yoshua Bengio , Emily Cheng

Semantically non-compositional phrases constitute an intriguing research topic in Natural Language Processing. Semantic non-compositionality --the situation when the meaning of a phrase cannot be derived from the meaning of its components,…

计算与语言 · 计算机科学 2019-08-16 Meghdad Farahmand

Compositionality in language refers to how much the meaning of some phrase can be decomposed into the meaning of its constituents and the way these constituents are combined. Based on the premise that substitution by synonyms is…

计算与语言 · 计算机科学 2017-03-13 Christina Lioma , Niels Dalum Hansen

Compositionality is believed to be fundamental to intelligence. In humans, it underlies the structure of thought, language, and higher-level reasoning. In AI, compositional representations can enable a powerful form of out-of-distribution…

计算与语言 · 计算机科学 2025-06-04 Eric Elmoznino , Thomas Jiralerspong , Yoshua Bengio , Guillaume Lajoie

Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to ask whether this…

机器学习 · 计算机科学 2019-04-09 Jacob Andreas

Deep transformer models have pushed performance on NLP tasks to new limits, suggesting sophisticated treatment of complex linguistic inputs, such as phrases. However, we have limited understanding of how these models handle representation…

计算与语言 · 计算机科学 2020-10-15 Lang Yu , Allyson Ettinger

Compositionality is considered central to language abilities. As performant language systems, how do large language models (LLMs) do on compositional tasks? We evaluate adjective-noun compositionality in LLMs using two complementary setups:…

计算与语言 · 计算机科学 2026-03-17 Ruchira Dhar , Qiwei Peng , Anders Søgaard

Natural language allows us to refer to novel composite concepts by combining expressions denoting their parts according to systematic rules, a property known as \emph{compositionality}. In this paper, we study whether the language emerging…

计算与语言 · 计算机科学 2020-04-21 Rahma Chaabouni , Eugene Kharitonov , Diane Bouchacourt , Emmanuel Dupoux , Marco Baroni

A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., grammatical rules) implicit in their sensory observations…

机器学习 · 计算机科学 2021-05-20 Jacob Russin , Roland Fernandez , Hamid Palangi , Eric Rosen , Nebojsa Jojic , Paul Smolensky , Jianfeng Gao

Building meaningful phrase representations is challenging because phrase meanings are not simply the sum of their constituent meanings. Lexical composition can shift the meanings of the constituent words and introduce implicit information.…

计算与语言 · 计算机科学 2019-05-21 Vered Shwartz , Ido Dagan

Compositionality has traditionally been understood as a major factor in productivity of language and, more broadly, human cognition. Yet, recently, some research started to question its status, showing that artificial neural networks are…

计算与语言 · 计算机科学 2022-06-13 Michal Auersperger , Pavel Pecina

Recent work in NLP shows that LSTM language models capture compositional structure in language data. For a closer look at how these representations are composed hierarchically, we present a novel measure of interdependence between word…

计算与语言 · 计算机科学 2020-04-29 Naomi Saphra , Adam Lopez

Compositionality is a hallmark of human language that not only enables linguistic generalization, but also potentially facilitates acquisition. When simulating language emergence with neural networks, compositionality has been shown to…

计算与语言 · 计算机科学 2023-05-23 Emily Cheng , Mathieu Rita , Thierry Poibeau

Word embeddings are usually derived from corpora containing text from many individuals, thus leading to general purpose representations rather than individually personalized representations. While personalized embeddings can be useful to…

计算与语言 · 计算机科学 2020-11-22 Charles Welch , Jonathan K. Kummerfeld , Verónica Pérez-Rosas , Rada Mihalcea

People acquire concepts through rich physical and social experiences and use them to understand and navigate the world. In contrast, large language models (LLMs), trained solely through next-token prediction on text, exhibit strikingly…

计算与语言 · 计算机科学 2025-11-11 Ningyu Xu , Qi Zhang , Chao Du , Qiang Luo , Xipeng Qiu , Xuanjing Huang , Menghan Zhang

Compositionality is a widely discussed property of natural languages, although its exact definition has been elusive. We focus on the proposal that compositionality can be assessed by measuring meaning-form correlation. We analyze…

计算与语言 · 计算机科学 2020-12-08 Timothee Mickus , Timothée Bernard , Denis Paperno

Understanding how sentences are internally represented in the human brain, as well as in large language models (LLMs) such as ChatGPT, is a major challenge for cognitive science. Classic linguistic theories propose that the brain represents…

计算与语言 · 计算机科学 2024-05-29 Wei Liu , Ming Xiang , Nai Ding

The mathematical representation of semantics is a key issue for Natural Language Processing (NLP). A lot of research has been devoted to finding ways of representing the semantics of individual words in vector spaces. Distributional…

计算与语言 · 计算机科学 2014-11-13 Karl Moritz Hermann

Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they…

计算与语言 · 计算机科学 2017-04-28 Clara Vania , Adam Lopez

Large language models (LLMs) have demonstrated remarkable performances on a wide range of natural language tasks. Yet, LLMs' successes have been largely restricted to tasks concerning words, sentences, or documents, and it remains…

计算与语言 · 计算机科学 2024-07-24 Andrew Shin , Kunitake Kaneko
‹ 上一页 1 2 3 10 下一页 ›