A pointer network architecture for context-dependent semantic parsing

Xuanli He, Quan Huang Tran, Reza Haffari

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch


Semantic parsing targets at mapping human
utterances into structured meaning representations,
such as logical forms, programming
snippets, SQL queries etc. In this work, we
focus on logical form generation, which is extracted
from an automated email assistant system.
Since this task is dialogue-oriented, information
across utterances must be well handled.
Furthermore, certain inputs from users
are used as arguments for the logical form,
which requires a parser to distinguish the functional
words and content words. Hence, an
intelligent parser should be able to switch between
generation mode and copy mode. In order
to address the aforementioned issues, we
equip the vanilla seq2seq model with a pointer
network and a context-dependent architecture
to generate more accurate logical forms. Our
model achieves state-of-the-art performance
on the email assistant task.
Original languageEnglish
Title of host publicationProceedings of the The 17th Annual Workshop of the Australasian Language Technology Association
EditorsMeladel Mistica
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Number of pages6
Publication statusPublished - 2019
EventAustralasian Language Technology Association Workshop 2019 - Sydney, Australia
Duration: 4 Nov 20196 Nov 2019
Conference number: 17th
https://aclanthology.org/volumes/U19-1/ (Proceedings)


ConferenceAustralasian Language Technology Association Workshop 2019
Abbreviated titleALTA 2019
Internet address

Cite this