中文
相关论文

相关论文: Discovery of Linguistic Relations Using Lexical At…

200 篇论文

The success of neural networks on a diverse set of NLP tasks has led researchers to question how much these networks actually ``know'' about natural language. Probes are a natural way of assessing this. When probing, a researcher chooses a…

计算与语言 · 计算机科学 2020-05-26 Tiago Pimentel , Josef Valvoda , Rowan Hall Maudslay , Ran Zmigrod , Adina Williams , Ryan Cotterell

This paper describes a method to automatically acquire the syntactic and semantic classifications of unknown words. Our method reduces the search space of the lexical acquisition problem by utilizing both the left and the right context of…

cmp-lg · 计算机科学 2016-08-31 Ted Pedersen , Weidong Chen

Understanding visual relationships involves identifying the subject, the object, and a predicate relating them. We leverage the strong correlations between the predicate and the (subj,obj) pair (both semantically and spatially) to predict…

计算机视觉与模式识别 · 计算机科学 2017-08-04 Ruichi Yu , Ang Li , Vlad I. Morariu , Larry S. Davis

Semantic associations such as the link between "bird" and "flew" are foundational for language modeling as they enable models to go beyond memorization and instead generalize and generate coherent text. Understanding how these associations…

计算与语言 · 计算机科学 2026-05-14 Shawn Im , Changdae Oh , Zhen Fang , Sharon Li

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of…

计算与语言 · 计算机科学 2022-12-06 Jacob Andreas

Generating a long, coherent text such as a paragraph requires a high-level control of different levels of relations between sentences (e.g., tense, coreference). We call such a logical connection between sentences as a (paragraph) flow. In…

计算与语言 · 计算机科学 2019-09-02 Dongyeop Kang , Hiroaki Hayashi , Alan W Black , Eduard Hovy

Logical formalisms provide a natural and concise means for specifying and reasoning about preferences. In this paper, we propose lexicographic logic, an extension of classical propositional logic that can express a variety of preferences,…

人工智能 · 计算机科学 2020-12-22 Angelos Charalambidis , Giorgos Papadimitriou , Panos Rondogiannis , Antonis Troumpoukis

Dynamical systems theory provides a framework for analyzing iterative processes and evolution over time. Within such systems, repetitive transformations can lead to stable configurations, known as attractors, including fixed points and…

计算与语言 · 计算机科学 2025-05-19 Zhilin Wang , Yafu Li , Jianhao Yan , Yu Cheng , Yue Zhang

This paper proposes methods for unsupervised lexical acquisition for relative spatial concepts using spoken user utterances. A robot with a flexible spoken dialog system must be able to acquire linguistic representation and its meaning…

Verbs form the backbone of language, providing the structure and meaning to sentences. Yet, their intricate semantic nuances pose a longstanding challenge. Understanding verb relations through the concept of lexical entailment is crucial…

计算与语言 · 计算机科学 2024-11-08 Candida M. Greco , Lucio La Cava , Andrea Tagarelli

A discovery system for detecting correspondences in data is described, based on the familiar induction methods of J. S. Mill. Given a set of observations, the system induces the ``causally'' related facts in these observations. Its…

cmp-lg · 计算机科学 2008-02-03 Vladimir Pericliev

Most natural language processing tasks require lexical semantic information. Automated acquisition of this information would thus increase the robustness and portability of NLP systems. This paper describes an acquisition method which makes…

cmp-lg · 计算机科学 2008-02-03 Marc Light

The syntactic structures of sentences can be readily read-out from the activations of large language models (LLMs). However, the ``structural probes'' that have been developed to reveal this phenomenon are typically evaluated on an…

计算与语言 · 计算机科学 2025-08-12 Pablo J. Diego-Simón , Emmanuel Chemla , Jean-Rémi King , Yair Lakretz

Inference in natural language often involves recognizing lexical entailment (RLE); that is, identifying whether one word entails another. For example, "buy" entails "own". Two general strategies for RLE have been proposed: One strategy is…

计算与语言 · 计算机科学 2015-06-02 Peter D. Turney , Saif M. Mohammad

Large language models (LLMs) are increasingly used as agents that interact with users and with the world. To do so successfully, LLMs must construct representations of the world and form probabilistic beliefs about them. To provide…

计算与语言 · 计算机科学 2026-01-16 Linlu Qiu , Fei Sha , Kelsey Allen , Yoon Kim , Tal Linzen , Sjoerd van Steenkiste

Children learning their first language face multiple problems of induction: how to learn the meanings of words, and how to build meaningful phrases from those words according to syntactic rules. We consider how children might solve these…

计算与语言 · 计算机科学 2018-05-15 Jon Gauthier , Roger Levy , Joshua B. Tenenbaum

Modelling the process that a listener actuates in deriving the words intended by a speaker requires setting a hypothesis on how lexical items are stored in memory. This work aims at developing a system that imitates humans when identifying…

音频与语音处理 · 电气工程与系统科学 2021-07-07 Maria-Gabriella Di Benedetto , Stefanie Shattuck-Hufnagel , Jeung-Yoon Choi , Luca De Nardis , Javier Arango , Ian Chan , Alec DeCaprio

Language models (LMs) trained on large quantities of text have been claimed to acquire abstract linguistic representations. Our work tests the robustness of these abstractions by focusing on the ability of LMs to learn interactions between…

计算与语言 · 计算机科学 2020-10-13 Forrest Davis , Marten van Schijndel

Recent neural models for relation extraction with distant supervision alleviate the impact of irrelevant sentences in a bag by learning importance weights for the sentences. Efforts thus far have focused on improving extraction accuracy but…

信息检索 · 计算机科学 2020-06-01 Hamed Shahbazi , Xiaoli Z. Fern , Reza Ghaeini , Prasad Tadepalli

Humans carry stereotypic tacit assumptions (STAs) (Prince, 1978), or propositional beliefs about generic concepts. Such associations are crucial for understanding natural language. We construct a diagnostic set of word prediction prompts to…

计算与语言 · 计算机科学 2020-06-17 Nathaniel Weir , Adam Poliak , Benjamin Van Durme