Search Results for author:
Found 7 papers, 2 papers with code
The Maaloula Aramaic Speech Corpus (MASC): From Printed Material to a Lemmatized and Time-Aligned Corpus
This 64, 845-word corpus is available in four formats: (1) transcriptions, (2) lemmatized transcriptions, (3) audio files and time-aligned phonetic transcriptions, and (4) an SQLite database.
Implicit representations of event properties within contextual language models: Searching for “causativity neurons”
This paper addresses the question to which extent neural contextual language models such as BERT implicitly represent complex semantic properties.
Corpus-based Identification of Verbs Participating in Verb Alternations Using Classification and Manual Annotation
We use ENCOW and VerbNet data to train classifiers to predict the instrument subject alternation and the causative-inchoative alternation, relying on count-based and vector-based features as well as perplexity-based language model features, which are intended to reflect each alternation{'}s felicity by simulating it.
Verb Alternations and Their Impact on Frame Induction
Frame induction is the automatic creation of frame-semantic resources similar to FrameNet or PropBank, which map lexical units of a language to frame representations of each lexical unit{'}s semantics.
