中文
相关论文

相关论文: Expect the Unexpected? Testing the Surprisal of Sa…

200 篇论文

The Uniform Information Density (UID) hypothesis posits that speakers tend to distribute information evenly across linguistic units to achieve efficient communication. Of course, information rate in texts and discourses is not perfectly…

计算与语言 · 计算机科学 2024-10-22 Eleftheria Tsipidi , Franz Nowak , Ryan Cotterell , Ethan Wilcox , Mario Giulianelli , Alex Warstadt

Entities in discourse vary in salience: main participants, objects and locations stay prominent, while others are quickly forgotten, raising questions about how humans signal and infer discourse-level salience. Using a graded…

计算与语言 · 计算机科学 2026-04-21 Amir Zeldes , Jessica Lin

The Uniform Information Density (UID) hypothesis posits that speakers are subject to a communicative pressure to distribute information evenly within utterances, minimising surprisal variance. While this hypothesis has been tested…

计算与语言 · 计算机科学 2026-02-17 Matteo Gay , Coleman Haley , Mario Giulianelli , Edoardo Ponti

The uniform information density (UID) hypothesis posits a preference among language users for utterances structured such that information is distributed uniformly across a signal. While its implications on language production have been well…

计算与语言 · 计算机科学 2021-09-27 Clara Meister , Tiago Pimentel , Patrick Haller , Lena Jäger , Ryan Cotterell , Roger Levy

Identifying the salience (i.e. importance) of discourse units is an important task in language understanding. While events play important roles in text documents, little research exists on analyzing their saliency status. This paper…

计算与语言 · 计算机科学 2018-09-10 Zhengzhong Liu , Chenyan Xiong , Teruko Mitamura , Eduard Hovy

In text documents such as news articles, the content and key events usually revolve around a subset of all the entities mentioned in a document. These entities, often deemed as salient entities, provide useful cues of the aboutness of a…

Speakers often have multiple ways to express the same meaning. The Uniform Information Density (UID) hypothesis suggests that speakers exploit this variability to maintain a consistent rate of information transmission during language…

计算与语言 · 计算机科学 2025-10-27 Hailin Hao , Elsi Kaiser

Salience Estimation aims to predict term importance in documents. Due to few existing human-annotated datasets and the subjective notion of salience, previous studies typically generate pseudo-ground truth for evaluation. However, our…

计算与语言 · 计算机科学 2021-04-15 Jiaying Lu , Jinho D. Choi

Determining and ranking the most salient entities in a text is critical for user-facing systems, especially as users increasingly rely on models to interpret long documents they only partially read. Graded entity salience addresses this…

计算与语言 · 计算机科学 2025-06-02 Jessica Lin , Amir Zeldes

The uniform information density (UID) hypothesis proposes that speakers aim to distribute information evenly throughout a text, balancing production effort and listener comprehension difficulty. However, language typically does not maintain…

The Uniform Information Density (UID) hypothesis posits that speakers optimize the communicative properties of their utterances by avoiding spikes in information, thereby maintaining a relatively uniform information profile over time. This…

计算与语言 · 计算机科学 2024-06-03 Ella Rabinovich

A fundamental result in psycholinguistics is that less predictable words take a longer time to process. One theoretical explanation for this finding is Surprisal Theory (Hale, 2001; Levy, 2008), which quantifies a word's predictability as…

计算与语言 · 计算机科学 2025-04-15 Ethan Gotlieb Wilcox , Tiago Pimentel , Clara Meister , Ryan Cotterell , Roger P. Levy

While natural languages differ widely in both canonical word order and word order flexibility, their word orders still follow shared cross-linguistic statistical patterns, often attributed to functional pressures. In the effort to identify…

计算与语言 · 计算机科学 2023-07-11 Thomas Hikaru Clark , Clara Meister , Tiago Pimentel , Michael Hahn , Ryan Cotterell , Richard Futrell , Roger Levy

We present a new perspective on how readers integrate context during real-time language comprehension. Our proposals build on surprisal theory, which posits that the processing effort of a linguistic unit (e.g., a word) is an affine…

计算与语言 · 计算机科学 2025-06-26 Andreas Opedal , Eleanor Chodroff , Ryan Cotterell , Ethan Gotlieb Wilcox

Detecting salient parts in text using natural language processing has been widely used to mitigate the effects of information overflow. Nevertheless, most of the datasets available for this task are derived mainly from academic…

计算与语言 · 计算机科学 2024-03-26 Andrés García-Silva , Cristian Berrío , José Manuel Gómez-Pérez

Implicit feedback, such as user clicks, serves as the primary data source for modern recommender systems. However, click interactions inherently contain substantial noise, including accidental clicks, clickbait-induced interactions, and…

信息检索 · 计算机科学 2026-02-18 Xikai Yang , Yang Wang , Yilin Li , Sebastian Sun

Surprisal theory posits that the cognitive effort required to comprehend a word is determined by its contextual predictability, quantified as surprisal. Traditionally, surprisal theory treats words as distinct entities, overlooking any…

计算与语言 · 计算机科学 2024-10-24 Clara Meister , Mario Giulianelli , Tiago Pimentel

We advance a novel explanation of similarity-based interference effects in subject-verb and reflexive pronoun agreement processing, grounded in surprisal values computed from a pretrained large-scale Transformer model, GPT-2. Specifically,…

计算与语言 · 计算机科学 2021-04-28 Soo Hyun Ryu , Richard L. Lewis

Eliciting information to reduce uncertainty about a latent entity is a critical task in many application domains, e.g., assessing individual student learning outcomes, diagnosing underlying diseases, or learning user preferences. Though…

计算与语言 · 计算机科学 2025-07-10 Jimmy Wang , Thomas Zollo , Richard Zemel , Hongseok Namkoong

News articles typically mention numerous entities, a large fraction of which are tangential to the story. Detecting the salience of entities in articles is thus important to applications such as news search, analysis and summarization. In…

计算与语言 · 计算机科学 2024-06-03 Eliyar Asgarieh , Kapil Thadani , Neil O'Hare
‹ 上一页 1 2 3 10 下一页 ›