BEGIN:VCALENDAR
METHOD:PUBLISH
PRODID:www-dhss-phil-fau-de//Events//DE
VERSION:2.0
BEGIN:VEVENT
SUMMARY:Julian Häußler (Darmstadt): Teaching Distributional Semantic
 s Through Concordance Analysis
UID:f157-772b-2225-67843@www.dhss.phil.fau.de
DESCRIPTION:Join us for the RC21 Project Symposium\, where invited spe
 akers and project team members\, Poster Presenters will present their 
 work on methodology and applications of concordance analysis! &nbsp\; 
 Julian Häußler (Darmstadt): » Teaching Distributional Semantics Thr
 ough Concordance Analysis« Abstract: Distributional semantics\, the i
 dea that a word’s meaning can be captured by its surroundings in a t
 ext\, is a fundamental concept in corpus linguistics and through its i
 mplementation\, e.g.\, as Word Embedding Models\, also a cornerstone o
 f Natural Language Processing (NLP) and Computational Literary Studies
  (CLS). However\, concordances can also be used to form an understandi
 ng of distributional semantics\, are easily experimented with and offe
 r a low barrier to entry. This poster will introduce a teaching unit o
 n this topic directed at Master’s students with limited background k
 nowledge in corpus linguistics. Its objective is to train students in 
 using concordance analysis to understand distributional semantics and 
 to enable them to apply it and its implementations in NLP/CLS research
  workflows. The idea that the meaning of a word can be identified by l
 ooking at the surroundings of said word in a text is simple yet powerf
 ul. It is ascribed in its most basic form\, the distributional hypothe
 sis (“You shall know a word by the company it keeps!”)\, to Firth 
 (1957)\, who cites Wittgenstein (2003\, §43). This assumption is toda
 y the foundation of distributional semantics and NLP-methods such as W
 ord Embedding Models (Mikolov et al. 2013) and Topic Modeling\, specif
 ically LDA (Blei\, Ng and Jordan 2003). However\, these implementation
 s work by reducing the information on words’ surroundings to numeric
 al values and only allow the analysis as such. Therefore\, ‘manually
 ’ analyzing these surroundings by looking at concordances is most be
 neficial for properly understanding how distributional semantics works
 . This poster will introduce a teaching unit on distributional semanti
 c
DTSTART:20250321T113000Z
DTEND:20250321T140000Z
LOCATION:Kollegienhaus\, Universitätsstraße 15\, 91054 Erlangen
DTSTAMP:20260428T094455Z
END:VEVENT
END:VCALENDAR