TY - GEN
T1 - A Unified Approach to Word Sense Representation and Disambiguation
AU - Lee, Do Myoung
AU - Kim, Yeachan
AU - Lee, Ji Min
AU - Lee, Sang-Geun
N1 - Funding Information:
ACKNOWLEDGMENT This research was supported in part by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT (number 2015R1A2A1A10052665). This research was also in part supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2018-2016-0-00464) supervised by the IITP(Institute for Information & communications Technology Promotion).
Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/4
Y1 - 2018/10/4
N2 - The lexical ambiguity of words has been successfully clarified by representing words at a sense level instead of a word level. This is known as word sense representation (WSR). However, WSR models are typically trained in an unsupervised fashion without any guidance from sense inventories. Therefore, the number of sense vectors assigned to a word varies from model to model. This implies that some senses are missed or unnecessarily added. Moreover, to utilize their sense vectors in natural language processing tasks, we must determine which sense of a word to choose. In this paper, we introduce a unified neural model that incorporates WSR into word sense disambiguation (WSD), thereby leveraging the sense inventory. We use bidirectional long short-term memory networks to capture the sequential information of contexts effectively. To overcome the limitation of size with the labeled dataset, we train our model in a semi-supervised fashion to scale up the size of the dataset by leveraging a large-scale unlabeled dataset. We evaluate our proposed model on both WSR and WSD tasks. The experimental results demonstrate that our model outperforms state-of-the-art on WSR task by 0.27%, while, on WSD task, by 1.4% in terms of Spearman's correlation and F'l-score, respectively.
AB - The lexical ambiguity of words has been successfully clarified by representing words at a sense level instead of a word level. This is known as word sense representation (WSR). However, WSR models are typically trained in an unsupervised fashion without any guidance from sense inventories. Therefore, the number of sense vectors assigned to a word varies from model to model. This implies that some senses are missed or unnecessarily added. Moreover, to utilize their sense vectors in natural language processing tasks, we must determine which sense of a word to choose. In this paper, we introduce a unified neural model that incorporates WSR into word sense disambiguation (WSD), thereby leveraging the sense inventory. We use bidirectional long short-term memory networks to capture the sequential information of contexts effectively. To overcome the limitation of size with the labeled dataset, we train our model in a semi-supervised fashion to scale up the size of the dataset by leveraging a large-scale unlabeled dataset. We evaluate our proposed model on both WSR and WSD tasks. The experimental results demonstrate that our model outperforms state-of-the-art on WSR task by 0.27%, while, on WSD task, by 1.4% in terms of Spearman's correlation and F'l-score, respectively.
KW - Artificial neural nets
KW - Computational Intelligence
KW - Natural language processing
KW - Recurrent neural networks
UR - http://www.scopus.com/inward/record.url?scp=85056479283&partnerID=8YFLogxK
U2 - 10.1109/ICCI-CC.2018.8482041
DO - 10.1109/ICCI-CC.2018.8482041
M3 - Conference contribution
AN - SCOPUS:85056479283
T3 - Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018
SP - 330
EP - 336
BT - Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018
A2 - Howard, Newton
A2 - Kwong, Sam
A2 - Wang, Yingxu
A2 - Feldman, Jerome
A2 - Widrow, Bernard
A2 - Sheu, Phillip
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018
Y2 - 16 July 2018 through 18 July 2018
ER -