paper-with-me

홈 › Papers

Unsupervised Discovery of Unaccusative and Unergative Verbs

2021-11-01 · Sharid Loáiciga, Luca Bevacqua, Christian Hardmeier

We present an unsupervised method to detect English unergative and unaccusative verbs. These categories allow us to identify verbs participating in the causative-inchoative alternation without knowing the semantic roles of the verb. The method is based on the generation of intransitive sentence variants of candidate verbs and probing a language model. We obtained results on par with similar approaches, with the added benefit of not relying on annotated resources.

📄 PDF Abstract BibTeX arXiv:2111.00808

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingSentence

Similar Papers 제목 키워드 기반

Interpretable dimensions support an effect of agentivity and telicity on split intransitivity

2025-11-20 · Eva Neu, Brian Dillon, Katrin Erk arxiv

Intransitive verbs fall into two different syntactic classes, unergatives and unaccusatives. It has long been argued that verbs describing an agentive action are more likely to appear in an unergative syntax, and those d…

Detecting Optional Arguments of Verbs

2016-05-01 · LREC 2016 5 · Andr{\'a}s Kornai, D{\'a}vid M{\'a}rk Nemeskey, G{\'a}bor Recski

We propose a novel method for detecting optional arguments of Hungarian verbs using only positive data. We introduce a custom variant of collexeme analysis that explicitly models the noise in verb frames. Our method is, …

Clustering

Unsupervised Classification of English Words Based on Phonological Information: Discovery of Germanic and Latinate Clusters

2025-04-16 · Takashi Morita, Timothy J. O'Donnell

Cross-linguistically, native words and loanwords follow different phonological rules. In English, for example, words of Germanic and Latinate origin exhibit different stress patterns, and a certain syntactic structure is…

Improving Classification by Improving Labelling: Introducing Probabilistic Multi-Label Object Interaction Recognition

2017-03-24 · Michael Wray, Davide Moltisanti, Walterio Mayol-Cuevas, Dima Damen

This work deviates from easy-to-define class boundaries for object interactions. For the task of object interaction recognition, often captured using an egocentric view, we show that semantic ambiguities in verbs and rec…

General ClassificationObject

Corpus-based Identification of Verbs Participating in Verb Alternations Using Classification and Manual Annotation

2020-12-01 · COLING 2020 8 · Esther Seyffarth, Laura Kallmeyer

English verb alternations allow participating verbs to appear in a set of syntactically different constructions whose associated semantic frames are systematically related. We use ENCOW and VerbNet data to train classifi…

Language ModelingLanguage Modelling