Language Evolution, Acquisition and Processing (LEAP) workshop

May 6, 2022 | 11:00AM
Social Sciences 108

LEAP will be meeting at 11am-12:20pm (CT). Our own Pamela Sugrue will talk to us about “Probing Word Vector Semantics”. Abstract can be found below. We will have a hybrid meeting, so please feel free to join us in person at Social Sciences 108 or over Zoom.

 

https://uchicago.zoom.us/j/94052449015?pwd=aUNQNU15RnQvSTIzd041dU5QK2t1dz09

Meeting ID: 940 5244 9015

Passcode: 151010

 

-------------------------------------------------------------

LEAP (April 15 at 11am-12:20pm (CT)): Pamela Sugrue (UChicago)

Social Sciences 108 | Zoom (link)

 

Title: Probing Word Vector Semantics

 

Distributional semantic representations of words, also called word vectors or word embeddings, are a popular way of representing the meanings of words in computational systems. Word embeddings are numerical (vector) representations of words, calculated (in various ways, depending on the specific model architecture) using the co-occurrence of all words over large corpora, such that words become located in semantic space near to other, semantically similar, words. The core intuition behind representing meaning this way is the Distributional Hypothesis (Harris 1954), which holds that word meaning is a function of how words are used. While these models are popular in computational systems and perform impressively at many natural language processing tasks, open questions remain about what specific aspects of word meaning that word vectors come to encode (Turton et al. 2020, Utsumi 2020, Lebani and Lenci 2021, among others). Rubinstein et al. (2015) propose that taxonomic properties are better represented in distributional semantic models than other properties. The research I will discuss probes the semantic information encoded in vector representations of English adjectives, specifically investigating whether adjective embeddings encode gradability, lexical dimensionality, and subjectivity, and offers evidence in support of Rubinstein et al.’s hypothesis. 

-------------------------------------------------------------