中文
相关论文

相关论文: "Not not bad" is not "bad": A distributional accou…

200 篇论文

Negation is both an operation in formal logic and in natural language by which a proposition is replaced by one stating the opposite, as by the addition of "not" or another negation cue. Treating negation in an adequate way is required for…

计算与语言 · 计算机科学 2021-10-14 Claudia Schon , Sophie Siebert , Frieder Stolzenburg

Word embeddings are an essential component in a wide range of natural language processing applications. However, distributional semantic models are known to struggle when only a small number of context sentences are available. Several…

计算与语言 · 计算机科学 2019-10-02 Jeroen Van Hautte , Guy Emerson , Marek Rei

Language models have demonstrated the ability to generate highly fluent text; however, it remains unclear whether their output retains coherent high-level structure (e.g., story progression). Here, we propose to apply a statistical tool,…

计算与语言 · 计算机科学 2022-10-18 Yuntian Deng , Volodymyr Kuleshov , Alexander M. Rush

We provide an overview of the hybrid compositional distributional model of meaning, developed in Coecke et al. (arXiv:1003.4394v1 [cs.CL]), which is based on the categorical methods also applied to the analysis of information flow in…

计算与语言 · 计算机科学 2011-06-08 Mehrnoosh Sadrzadeh , Edward Grefenstette

The functional approach to compositional distributional semantics considers transitive verbs to be linear maps that transform the distributional vectors representing nouns into a vector representing a sentence. We conduct an initial…

计算与语言 · 计算机科学 2014-12-15 Tamara Polajnar , Laura Rimell , Stephen Clark

Distributional semantics has had enormous empirical success in Computational Linguistics and Cognitive Science in modeling various semantic phenomena, such as semantic similarity, and distributional models are widely used in…

计算与语言 · 计算机科学 2019-05-20 Matthijs Westera , Gemma Boleda

Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless…

计算与语言 · 计算机科学 2024-06-12 MohammadHossein Rezaei , Eduardo Blanco

The extent to which neural networks are able to acquire and represent symbolic rules remains a key topic of research and debate. Much current work focuses on the impressive capabilities of large language models, as well as their often…

机器学习 · 计算机科学 2025-06-11 Anna Langedijk , Jaap Jumelet , Willem Zuidema

We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that…

计算与语言 · 计算机科学 2026-05-06 Zhejian Zhou , Tianyi Zhou , Robin Jia , Jonathan May

This thesis is about the problem of compositionality in distributional semantics. Distributional semantics presupposes that the meanings of words are a function of their occurrences in textual contexts. It models words as distributions over…

计算与语言 · 计算机科学 2013-11-08 Edward Grefenstette

This paper provides a method for improving tensor-based compositional distributional models of meaning by the addition of an explicit disambiguation step prior to composition. In contrast with previous research where this hypothesis has…

计算与语言 · 计算机科学 2014-08-28 Dimitri Kartsaklis , Nal Kalchbrenner , Mehrnoosh Sadrzadeh

Sentiment analysis is directly affected by compositional phenomena in language that act on the prior polarity of the words and phrases found in the text. Negation is the most prevalent of these phenomena and in order to correctly predict…

计算与语言 · 计算机科学 2021-07-01 Jeremy Barnes , Erik Velldal , Lilja Øvrelid

Building meaningful representations of noun compounds is not trivial since many of them scarcely appear in the corpus. To that end, composition functions approximate the distributional representation of a noun compound by combining its…

计算与语言 · 计算机科学 2019-06-13 Vered Shwartz

Distributional models are derived from co-occurrences in a corpus, where only a small proportion of all possible plausible co-occurrences will be observed. This results in a very sparse vector space, requiring a mechanism for inferring…

计算与语言 · 计算机科学 2016-08-25 Thomas Kober , Julie Weeds , Jeremy Reffin , David Weir

Reasoning using negation is known to be difficult for transformer-based language models. While previous studies have used the tools of psycholinguistics to probe a transformer's ability to reason over negation, none have focused on the…

计算与语言 · 计算机科学 2022-05-02 Antonio Laverghetta , John Licato

Current vision-language detection and grounding models predominantly focus on prompts with positive semantics and often struggle to accurately interpret and ground complex expressions containing negative semantics. A key reason for this…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Zesheng Yang , Xi Jiang , Bingzhang Hu , Weili Guan , Runmin Cong , Guo-Jun Qi , Feng Zheng

Negation and uncertainty modeling are long-standing tasks in natural language processing. Linguistic theory postulates that expressions of negation and uncertainty are semantically independent from each other and the content they modify.…

计算与语言 · 计算机科学 2022-04-04 Jake Vasilakes , Chrysoula Zerva , Makoto Miwa , Sophia Ananiadou

Three-way logical question answering (QA) assigns one of $\text{True}$, $\text{False}$, or $\text{Unknown}$ to a hypothesis $H$ given a premise set $S$. We study this task as a compact compositional inference problem: predictions for $H$…

计算与语言 · 计算机科学 2026-05-28 Tianyi Huang , Ming Hou , Jiaheng Su , Yutong Zhang , Ziling Zhang

We provide a comparative study between neural word representations and traditional vector spaces based on co-occurrence counts, in a number of compositional tasks. We use three different semantic spaces and implement seven tensor-based…

计算与语言 · 计算机科学 2014-08-27 Dmitrijs Milajevs , Dimitri Kartsaklis , Mehrnoosh Sadrzadeh , Matthew Purver

Data-driven representation learning for words is a technique of central importance in NLP. While indisputably useful as a source of features in downstream tasks, such vectors tend to consist of uninterpretable components whose relationship…

计算与语言 · 计算机科学 2015-06-18 Manaal Faruqui , Chris Dyer