Abstract
Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs' roles. These roles are too coarse to represent verbs' semantics. In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb. First we analyze the principles for verb patterns: generality and specificity. Then we propose a nonparametric model based on description length. Experimental results prove the high effectiveness of verb patterns.We further apply verb patterns to context-Aware conceptualization, to show that verb patterns are helpful in semantic-related tasks.
| Original language | English |
|---|---|
| Title of host publication | 30th AAAI Conference on Artificial Intelligence, AAAI 2016 |
| Publisher | AAAI press |
| Pages | 2587-2593 |
| Number of pages | 7 |
| ISBN (Electronic) | 9781577357605 |
| Publication status | Published - 2016 Jan 1 |
| Event | 30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States Duration: 2016 Feb 12 → 2016 Feb 17 |
Publication series
| Name | 30th AAAI Conference on Artificial Intelligence, AAAI 2016 |
|---|
Other
| Other | 30th AAAI Conference on Artificial Intelligence, AAAI 2016 |
|---|---|
| Country | United States |
| City | Phoenix |
| Period | 16/2/12 → 16/2/17 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
Cite this
}
Verb pattern : A probabilistic semantic representation on verbs. / Cui, Wanyun; Zhou, Xiyou; Lin, Hangyu; Xiao, Yanghua; Wang, Haixun; Hwang, Seungwon; Wang, Wei.
30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. p. 2587-2593 (30th AAAI Conference on Artificial Intelligence, AAAI 2016).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Verb pattern
T2 - A probabilistic semantic representation on verbs
AU - Cui, Wanyun
AU - Zhou, Xiyou
AU - Lin, Hangyu
AU - Xiao, Yanghua
AU - Wang, Haixun
AU - Hwang, Seungwon
AU - Wang, Wei
PY - 2016/1/1
Y1 - 2016/1/1
N2 - Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs' roles. These roles are too coarse to represent verbs' semantics. In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb. First we analyze the principles for verb patterns: generality and specificity. Then we propose a nonparametric model based on description length. Experimental results prove the high effectiveness of verb patterns.We further apply verb patterns to context-Aware conceptualization, to show that verb patterns are helpful in semantic-related tasks.
AB - Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs' roles. These roles are too coarse to represent verbs' semantics. In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb. First we analyze the principles for verb patterns: generality and specificity. Then we propose a nonparametric model based on description length. Experimental results prove the high effectiveness of verb patterns.We further apply verb patterns to context-Aware conceptualization, to show that verb patterns are helpful in semantic-related tasks.
UR - http://www.scopus.com/inward/record.url?scp=85007233420&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85007233420&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85007233420
T3 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016
SP - 2587
EP - 2593
BT - 30th AAAI Conference on Artificial Intelligence, AAAI 2016
PB - AAAI press
ER -