paper-with-me

홈 › Papers

Repetition Facilitates Processing: The Processing Advantage of Construction Repetition in Dialogue

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Repetitions occur frequently in dialogue. This study focuses on the repetition of lexicalised constructions—i.e., recurring multi-word units—in English open domain spoken dialogues. We hypothesise that construction repetition is an efficient communication strategy that reduces processing effort, and make three predictions based on this hypothesis. Our three predictions are confirmed: repetitions facilitate the processing of constructions and of their linguistic context; facilitating effects are higher when repetitions accumulate, and lower when repetitions are less locally distributed. We measure reduction in processing effort using two surprisal-based measures and estimate surprisal with an adaptive neural language model. Our findings suggest that human-like patterns of repetitions can be learned implicitly by utterance generation models equipped with psycholinguistically motivated surprisal-based objectives and adaptation mechanisms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

A Predictive Model for Music Based on Learned Interval Representations

2018-06-22 · Stefan Lattner, Maarten Grachten, Gerhard Widmer

Connectionist sequence models (e.g., RNNs) applied to musical sequences suffer from two known problems: First, they have strictly "absolute pitch perception". Therefore, they fail to generalize over musical concepts whic…

Voice and accompaniment separation in music using self-attention convolutional neural network

2020-03-19 · Yuzhou Liu, Balaji Thoshkahna, Ali Milani, Trausti Kristjansson

Music source separation has been a popular topic in signal processing for decades, not only because of its technical difficulty, but also due to its importance to many commercial applications, such as automatic karoake a…

Music Source Separation

Cross-Lingual Query-by-Example Spoken Term Detection: A Transformer-Based Approach

2024-10-05 · Allahdadi Fatemeh, Mahdian Toroghi Rahil, Zareian Hassan

Query-by-example spoken term detection (QbE-STD) is typically constrained by transcribed data scarcity and language specificity. This paper introduces a novel, language-agnostic QbE-STD model leveraging image processing …

Specificity

Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning

2023-06-06 · Chujie Zheng, Pei Ke, Zheng Zhang, Minlie Huang

It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllab…

Contrastive LearningText Generation

Construction Repetition Reduces Information Rate in Dialogue

2022-10-15 · Mario Giulianelli, Arabella Sinclair, Raquel Fernández

Speakers repeat constructions frequently in dialogue. Due to their peculiar information-theoretic properties, repetitions can be thought of as a strategy for cost-effective communication. In this study, we focus on the r…

Language ModelingLanguage Modelling