דלג לתוכן (מקש קיצור 's')
אירועים

אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

event speaker icon
Dor Ringel (הרצאה סמינריונית למגיסטר)
event date icon
יום ראשון, 15.09.2019, 10:30
event location icon
טאוב 601
event speaker icon
מנחה: Prof. S. markovitch, Dr. K. Radinsky
Large training datasets are required to achieve competitive performance in most natural language tasks. The acquisition process for these datasets is labor intensive, expensive, and time consuming. This process is also prone to human errors. In this work, we show that cross-cultural differences can be harnessed for natural language text classification. We present a transfer-learning framework that leverages widely-available unaligned bilingual corpora for classification tasks, using no task-specific data. Our empirical evaluation on two tasks -- formality classification and sarcasm detection -- shows that the cross-cultural difference between German and American English, as manifested in product review text, can be applied to achieve good performance for formality classification, while the difference between Japanese and American English can be applied to achieve good performance for sarcasm detection -- both without any task-specific labeled data.