paper-with-me

홈 › Papers

About Time: Do Transformers Learn Temporal Verbal Aspect?

2022-05-01 · CMCL (ACL) 2022 5 · Eleni Metheniti, Tim Van De Cruys, Nabil Hathout

Aspect is a linguistic concept that describes how an action, event, or state of a verb phrase is situated in time. In this paper, we explore whether different transformer models are capable of identifying aspectual features. We focus on two specific aspectual features: telicity and duration. Telicity marks whether the verb’s action or state has an endpoint or not (telic/atelic), and duration denotes whether a verb expresses an action (dynamic) or a state (stative). These features are integral to the interpretation of natural language, but also hard to annotate and identify with NLP methods. We perform experiments in English and French, and our results show that transformer models adequately capture information on telicity and duration in their vectors, even in their non-finetuned forms, but are somewhat biased with regard to verb tense and word order.

📄 PDF Abstract BibTeX

Code (1)

lenakmeth/telicity_classification 공식 구현 pytorch

Similar Papers 제목 키워드 기반

About Time: Do Transformers Learn Temporal Verbal Aspect?

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Aspect is a linguistic concept that describes how an action, event, or state of a verb phrase is situated in time. In this paper, we explore whether different transformer models are capable of identifying aspectual featu…

Temporal aggregation of audio-visual modalities for emotion recognition

2020-07-08 · Andreea Birhala, Catalin Nicolae Ristea, Anamaria Radoi, Liviu Cristian Dutu

Emotion recognition has a pivotal role in affective computing and in human-computer interaction. The current technological developments lead to increased possibilities of collecting data about the emotional state of a pe…

Emotion Recognition

Do Activation Verbalization Methods Convey Privileged Information?

2025-09-16 · Millicent Li, Alberto Mario Ceballos Arroyo, Giordano Rogers, Naomi Saphra 외 arxiv

Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verbalizer LLM. This is intended to illuminate how the target model represents and…

How to Address Smart Homes with a Social Robot? A Multi-modal Corpus of User Interactions with an Intelligent Environment

2016-05-01 · LREC 2016 5 · Patrick Holthaus, Christian Leichsenring, Jasmin Bernotat, Viktor Richter 외

In order to explore intuitive verbal and non-verbal interfaces in smart environments we recorded user interactions with an intelligent apartment. Besides offering various interactive capabilities itself, the apartment is…

Verbal Aggression as an Indicator of Xenophobic Attitudes in Greek Twitter during and after the Financial Crisis

2020-05-01 · LREC 2020 5 · Maria Pontiki, Maria Gavriilidou, Dimitris Gkoumas, Stelios Piperidis

We present a replication of a data-driven and linguistically inspired Verbal Aggression analysis framework that was designed to examine Twitter verbal attacks against predefined target groups of interest as an indicator …