no code implementations • LREC 2022 • Ghattas Eid, Esther Seyffarth, Ingo Plag
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.
1 code implementation • IWCS (ACL) 2021 • Esther Seyffarth, Younes Samih, Laura Kallmeyer, Hassan Sajjad
This paper addresses the question to which extent neural contextual language models such as BERT implicitly represent complex semantic properties.
no code implementations • COLING 2020 • Esther Seyffarth, Laura Kallmeyer
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.
no code implementations • NAACL 2018 • Esther Seyffarth
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.