Semantic role labeling in conversational chat using deep bi-directional long short-term memory networks with attention mechanism

Valdi Rachman; Rahmad Mahendra; Alfan Farizki Wicaksono; Ahmad Rizqi Meydiarso; Fariz Ikhwantri

Semantic role labeling in conversational chat using deep bi-directional long short-term memory networks with attention mechanism

Valdi Rachman, Rahmad Mahendra, Alfan Farizki Wicaksono, Ahmad Rizqi Meydiarso, Fariz Ikhwantri

Department of Computer Science

Research output: Contribution to conference › Paper › peer-review

3 Citations (Scopus)

Abstract

Semantic Role Labeling (SRL) has been extensively studied, mostly for understandingEnglish formal language. However, only a fewreports exist for informal conversational text,especially for language being used in the chatbot system. The challenges of informal textinglanguage include a wide variety of slangs andabbreviations, short sentences, as well as disorganized grammars. In this work, we proposean attention mechanism on top of Long ShortTerm Memory Networks architecture for solving SRL task on informal conversations. Thetask is evaluated on informal language usedon an Indonesian chatting platform. Our proposed model achieves F1 score of 82.68%.

Original language	English
Pages	558-566
Number of pages	9
Publication status	Published - 2018
Event	32nd Pacific Asia Conference on Language, Information and Computation, PACLIC 2018 - Hong Kong, Hong Kong Duration: 1 Dec 2018 → 3 Dec 2018

Conference

Conference	32nd Pacific Asia Conference on Language, Information and Computation, PACLIC 2018
Country/Territory	Hong Kong
City	Hong Kong
Period	1/12/18 → 3/12/18

Cite this

@conference{56430f3342424c6d9c110fd20b9681ab,

title = "Semantic role labeling in conversational chat using deep bi-directional long short-term memory networks with attention mechanism",

abstract = "Semantic Role Labeling (SRL) has been extensively studied, mostly for understandingEnglish formal language. However, only a fewreports exist for informal conversational text,especially for language being used in the chatbot system. The challenges of informal textinglanguage include a wide variety of slangs andabbreviations, short sentences, as well as disorganized grammars. In this work, we proposean attention mechanism on top of Long ShortTerm Memory Networks architecture for solving SRL task on informal conversations. Thetask is evaluated on informal language usedon an Indonesian chatting platform. Our proposed model achieves F1 score of 82.68%.",

author = "Valdi Rachman and Rahmad Mahendra and Wicaksono, {Alfan Farizki} and Meydiarso, {Ahmad Rizqi} and Fariz Ikhwantri",

note = "Publisher Copyright: {\textcopyright} 2018 by the authors.; 32nd Pacific Asia Conference on Language, Information and Computation, PACLIC 2018 ; Conference date: 01-12-2018 Through 03-12-2018",

year = "2018",

language = "English",

pages = "558--566",

}

Semantic role labeling in conversational chat using deep bi-directional long short-term memory networks with attention mechanism. / Rachman, Valdi; Mahendra, Rahmad; Wicaksono, Alfan Farizki et al.
2018. 558-566 Paper presented at 32nd Pacific Asia Conference on Language, Information and Computation, PACLIC 2018, Hong Kong, Hong Kong.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Semantic role labeling in conversational chat using deep bi-directional long short-term memory networks with attention mechanism

AU - Rachman, Valdi

AU - Mahendra, Rahmad

AU - Wicaksono, Alfan Farizki

AU - Meydiarso, Ahmad Rizqi

AU - Ikhwantri, Fariz

PY - 2018

Y1 - 2018

N2 - Semantic Role Labeling (SRL) has been extensively studied, mostly for understandingEnglish formal language. However, only a fewreports exist for informal conversational text,especially for language being used in the chatbot system. The challenges of informal textinglanguage include a wide variety of slangs andabbreviations, short sentences, as well as disorganized grammars. In this work, we proposean attention mechanism on top of Long ShortTerm Memory Networks architecture for solving SRL task on informal conversations. Thetask is evaluated on informal language usedon an Indonesian chatting platform. Our proposed model achieves F1 score of 82.68%.

AB - Semantic Role Labeling (SRL) has been extensively studied, mostly for understandingEnglish formal language. However, only a fewreports exist for informal conversational text,especially for language being used in the chatbot system. The challenges of informal textinglanguage include a wide variety of slangs andabbreviations, short sentences, as well as disorganized grammars. In this work, we proposean attention mechanism on top of Long ShortTerm Memory Networks architecture for solving SRL task on informal conversations. Thetask is evaluated on informal language usedon an Indonesian chatting platform. Our proposed model achieves F1 score of 82.68%.

UR - http://www.scopus.com/inward/record.url?scp=85090200709&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85090200709

SP - 558

EP - 566

T2 - 32nd Pacific Asia Conference on Language, Information and Computation, PACLIC 2018

Y2 - 1 December 2018 through 3 December 2018

ER -

Semantic role labeling in conversational chat using deep bi-directional long short-term memory networks with attention mechanism

Abstract

Conference

Other files and links

Fingerprint

Cite this