@inproceedings{chen-bunescu-2019-context,
title = "Context Dependent Semantic Parsing over Temporally Structured Data",
author = "Chen, Charles and
Bunescu, Razvan",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1360",
doi = "10.18653/v1/N19-1360",
pages = "3576--3585",
abstract = "We describe a new semantic parsing setting that allows users to query the system using both natural language questions and actions within a graphical user interface. Multiple time series belonging to an entity of interest are stored in a database and the user interacts with the system to obtain a better understanding of the entity{'}s state and behavior, entailing sequences of actions and questions whose answers may depend on previous factual or navigational interactions. We design an LSTM-based encoder-decoder architecture that models context dependency through copying mechanisms and multiple levels of attention over inputs and previous outputs. When trained to predict tokens using supervised learning, the proposed architecture substantially outperforms standard sequence generation baselines. Training the architecture using policy gradient leads to further improvements in performance, reaching a sequence-level accuracy of 88.7{\%} on artificial data and 74.8{\%} on real data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-bunescu-2019-context">
<titleInfo>
<title>Context Dependent Semantic Parsing over Temporally Structured Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Razvan</namePart>
<namePart type="family">Bunescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe a new semantic parsing setting that allows users to query the system using both natural language questions and actions within a graphical user interface. Multiple time series belonging to an entity of interest are stored in a database and the user interacts with the system to obtain a better understanding of the entity’s state and behavior, entailing sequences of actions and questions whose answers may depend on previous factual or navigational interactions. We design an LSTM-based encoder-decoder architecture that models context dependency through copying mechanisms and multiple levels of attention over inputs and previous outputs. When trained to predict tokens using supervised learning, the proposed architecture substantially outperforms standard sequence generation baselines. Training the architecture using policy gradient leads to further improvements in performance, reaching a sequence-level accuracy of 88.7% on artificial data and 74.8% on real data.</abstract>
<identifier type="citekey">chen-bunescu-2019-context</identifier>
<identifier type="doi">10.18653/v1/N19-1360</identifier>
<location>
<url>https://aclanthology.org/N19-1360</url>
</location>
<part>
<date>2019-jun</date>
<extent unit="page">
<start>3576</start>
<end>3585</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Context Dependent Semantic Parsing over Temporally Structured Data
%A Chen, Charles
%A Bunescu, Razvan
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 jun
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F chen-bunescu-2019-context
%X We describe a new semantic parsing setting that allows users to query the system using both natural language questions and actions within a graphical user interface. Multiple time series belonging to an entity of interest are stored in a database and the user interacts with the system to obtain a better understanding of the entity’s state and behavior, entailing sequences of actions and questions whose answers may depend on previous factual or navigational interactions. We design an LSTM-based encoder-decoder architecture that models context dependency through copying mechanisms and multiple levels of attention over inputs and previous outputs. When trained to predict tokens using supervised learning, the proposed architecture substantially outperforms standard sequence generation baselines. Training the architecture using policy gradient leads to further improvements in performance, reaching a sequence-level accuracy of 88.7% on artificial data and 74.8% on real data.
%R 10.18653/v1/N19-1360
%U https://aclanthology.org/N19-1360
%U https://doi.org/10.18653/v1/N19-1360
%P 3576-3585
Markdown (Informal)
[Context Dependent Semantic Parsing over Temporally Structured Data](https://aclanthology.org/N19-1360) (Chen & Bunescu, NAACL 2019)
ACL
- Charles Chen and Razvan Bunescu. 2019. Context Dependent Semantic Parsing over Temporally Structured Data. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3576–3585, Minneapolis, Minnesota. Association for Computational Linguistics.