Don't Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations

2020-12-01 · COLING 2020 8 · Paolo Pedinotti, Alessandro Lenci

In this work, we carry out two experiments in order to assess the ability of BERT to capture the meaning shift associated with metonymic expressions. We test the model on a new dataset that is representative of the most common types of metonymy. We compare BERT with the Structured Distributional Model (SDM), a model for the representation of words in context which is based on the notion of Generalized Event Knowledge. The results reveal that, while BERT ability to deal with metonymy is quite limited, SDM is good at predicting the meaning of metonymic expressions, providing support for an account of metonymy based on event knowledge.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Weight Decay 설명 없음

Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Residual Connection 설명 없음

Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification

2017-04-15 · Xiang Bai, Mingkun Yang, Pengyuan Lyu, Yongchao Xu 외

Text in natural images contains rich semantics that are often highly relevant to objects or scene. In this paper, we focus on the problem of fully exploiting scene text for visual understanding. The main idea is combinin…

Classification Fine-Grained Image Classification General Classification image-classification+2

Is Arrow's Dictator a Drinker?

2023-10-07 · Jeffrey Uhlmann

We critique the formulation of Arrow's no-dictator condition to show that it does not correspond to the accepted informal/intuitive interpretation. This has implications for the theorem's scope of applicability.

Effect of caffeine and energy drinks on sleep quality and brain activity in college students

2024-07-02 · Introducción a Señales Biomédicas UPCH 2024-I 2024 7 · Oviedo, N., Tito, K. 외

This study investigates the impact of caffeine and energy drink consumption on sleep quality and brain activity among college students. Using EEG technology, the research identifies specific brain activity patterns assoc…

EEG Sleep Quality

The InviTE Corpus: Annotating Invectives in Tudor English Texts for Computational Modeling

2025-09-26 · Sophie Spliethoff, Sanne Hoeken, Silke Schwandt, Sina Zarrieß 외 arxiv

In this paper, we aim at the application of Natural Language Processing (NLP) techniques to historical research endeavors, particularly addressing the study of religious invectives in the context of the Protestant Reform…

Détection d’anomalies textuelles à base de l’ingénierie d’invite (Prompt Engineering-Based Text Anomaly Detection )

2022-06-01 · JEP/TALN/RECITAL 2022 6 · Yizhou Xu, Kata Gábor, Leila Khouas, Frédérique Segond

La détection d’anomalies textuelles est une tâche importante de la fouille de textes. Plusieurs approches générales, visant l’identification de points de données aberrants, ont été appliqués dans ce domaine. Néanmoins, c…

Anomaly Detection Prompt Engineering