Sarcastic or Not:
Word Embeddings to Predict the
Literal or Sarcastic Meaning of Words
Debanjan Ghosh, Weiwei Guo, and Smaranda Muresan
EMNLP2015
ୈ8ճ࠷ઌNLPษڧձ 2016/09/10
ൃද୲ɿా ॡଠʢ౦େ ӨӜݚ | D1ʣ
1
2 Collection of Target Words
1. ΫϥυιʔγϯάͰൽΛؚΉίʔύεΛፊ
తͳදݱʹஔ͖͑ͨίʔύεΛੜ͢Δ
2. ಘΒΕͨύϥϨϧͳίʔύεʹ unsupervised
alignment ʢ୯ޠΞϥΠϝϯτʣΛద༻ͯ͠ରٛޠ
ϖΞΛऩू
3
Slide 4
Slide 4 text
2 Collection of Target Words
I love going to the dentist
I hate going to the dentist
1. Turkers ʹΑΔݴ͍͑
3. ݩͷπΠʔτʹ͋ͬͨ
΄͏ͷ୯ޠΛ target
words ʹՃ͑Δ
2. Unsupervised
alignment ͰϖΞΛ
ݟ͚ͭΔ
4
(1) Ϋϥυιʔγϯά 1000 πΠʔτ
from searching for
#sarcasm/#sarcastic
5000 πΠʔτ
by 5 Turkers
Slide 5
Slide 5 text
2 Collection of Target Words
(2) Unsupervised alignment
1. co-training algorithm for paraphrase
detection (Barzilay and McKeown, 2001)
2. Statistical machine translation alignment
(IBM Model 4 with HMM alignment in Giza+
+; Och and Ney, 2000)
5
→ 367 ϖΞ
→ 70 ϖΞ
obtained
# of t
φ ≥ 0.8
Slide 6
Slide 6 text
3 Literal/Sarcastic Sense Disambiguation
• ೖྗςΩετͱ target word (t) ͕ࢦఆ͞Εͨͱ͖
ʹɺt ͷҙຯ͕ sarcastic (S) ͔ literal (L) ͔Λਪఆ
• ֶशͷͨΊʹɺ֤ t ʹ͍ͭͯ S/L ͦΕͧΕͷҙຯͰ
༻͍ΒΕ͍ͯΔྫจσʔλ͕ඞཁ
6
Slide 7
Slide 7 text
3.1 Data Collection
• target words ΛؚΉπΠʔτΛݕࡧ͠ɺ#sarcasm/
#sarcastic ΛؚΉͷΛ S, ͦ͏Ͱͳ͍ͷΛ L ͱ
ͨ͠
• ͨͩ͠ L ʹ͍ͭͯ ײʢϙδɾωΨʣ͕ϋογϡ
λάͱͯ͠ϥϕϧ͚͞Ε͍ͯΔͷΛ Lsent
ͱͨ͠
• S/Lsent
ͷํ͕͍͠ͱ͍ΘΕΔ (Gonzalez et al.,
2011)
7
I
going
to
the
dentist
ignored being waking work sick ...
suppose: u = “I love going to the dentist” (t = “love”)
love ͷจ຺ޠ ck
in S
love ͷจ຺ޠ wj
in u
-0.9 -0.9 -0.9 -0.9 -0.9
-0.9 -0.9
0.8 0.5 0.3
0.5
-0.9
-0.9
-0.9
-0.9 -0.9 -0.9 -0.9
0.3
-0.9
0.1 -0.1
-0.9 -0.9 -0.9
Sim = 0
...
...
...
...
...
ߦྻ M
Sim = 0.8
0.3
repeat until max = 0 or size(M) = (0, 0)
16