@inproceedings{natarajan-etal-2020-unified,
title = "Unified Multi Intent Order and Slot Prediction using Selective Learning Propagation",
author = "Natarajan, Bharatram and
Chhipa, Priyank and
Yadav, Kritika and
Gogoi, Divya Verma",
editor = "S, Praveen Kumar G and
Mukherjee, Siddhartha and
Samal, Ranjan",
booktitle = "Proceedings of the Workshop on Joint NLP Modelling for Conversational AI @ ICON 2020",
month = dec,
year = "2020",
address = "Patna, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2020.icon-workshop.2",
pages = "10--18",
abstract = "Natural Language Understanding (NLU) involves two important task namely Intent Determination(ID) and Slot Filling (SF). With recent advancements in Intent Determination and Slot Filling tasks, explorations on handling of multiple intent information in a single utterance is increasing to make the NLU more conversation-based rather than command execution-based. Many have proven this task with huge multi-intent training data. In addition, lots of research have addressed multi intent problem only. The problem of multi intent also poses the challenge of addressing the order of execution of intents found. Hence, we are proposing a unified architecture to address multi-intent detection, associated slotsdetection and order of execution of found intents using low proportion multi-intent corpusin the training data. This architecture consists of Multi Word Importance relation propagator using Multi-Head GRU and Importance learner propagator module using self-attention. This architecture has beaten state-of-the-art by 2.58{\%} on the MultiIntentData dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="natarajan-etal-2020-unified">
<titleInfo>
<title>Unified Multi Intent Order and Slot Prediction using Selective Learning Propagation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharatram</namePart>
<namePart type="family">Natarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyank</namePart>
<namePart type="family">Chhipa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kritika</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Divya</namePart>
<namePart type="given">Verma</namePart>
<namePart type="family">Gogoi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Joint NLP Modelling for Conversational AI @ ICON 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Praveen</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="given">G</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddhartha</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ranjan</namePart>
<namePart type="family">Samal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Patna, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural Language Understanding (NLU) involves two important task namely Intent Determination(ID) and Slot Filling (SF). With recent advancements in Intent Determination and Slot Filling tasks, explorations on handling of multiple intent information in a single utterance is increasing to make the NLU more conversation-based rather than command execution-based. Many have proven this task with huge multi-intent training data. In addition, lots of research have addressed multi intent problem only. The problem of multi intent also poses the challenge of addressing the order of execution of intents found. Hence, we are proposing a unified architecture to address multi-intent detection, associated slotsdetection and order of execution of found intents using low proportion multi-intent corpusin the training data. This architecture consists of Multi Word Importance relation propagator using Multi-Head GRU and Importance learner propagator module using self-attention. This architecture has beaten state-of-the-art by 2.58% on the MultiIntentData dataset.</abstract>
<identifier type="citekey">natarajan-etal-2020-unified</identifier>
<location>
<url>https://aclanthology.org/2020.icon-workshop.2</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>10</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unified Multi Intent Order and Slot Prediction using Selective Learning Propagation
%A Natarajan, Bharatram
%A Chhipa, Priyank
%A Yadav, Kritika
%A Gogoi, Divya Verma
%Y S, Praveen Kumar G.
%Y Mukherjee, Siddhartha
%Y Samal, Ranjan
%S Proceedings of the Workshop on Joint NLP Modelling for Conversational AI @ ICON 2020
%D 2020
%8 December
%I NLP Association of India (NLPAI)
%C Patna, India
%F natarajan-etal-2020-unified
%X Natural Language Understanding (NLU) involves two important task namely Intent Determination(ID) and Slot Filling (SF). With recent advancements in Intent Determination and Slot Filling tasks, explorations on handling of multiple intent information in a single utterance is increasing to make the NLU more conversation-based rather than command execution-based. Many have proven this task with huge multi-intent training data. In addition, lots of research have addressed multi intent problem only. The problem of multi intent also poses the challenge of addressing the order of execution of intents found. Hence, we are proposing a unified architecture to address multi-intent detection, associated slotsdetection and order of execution of found intents using low proportion multi-intent corpusin the training data. This architecture consists of Multi Word Importance relation propagator using Multi-Head GRU and Importance learner propagator module using self-attention. This architecture has beaten state-of-the-art by 2.58% on the MultiIntentData dataset.
%U https://aclanthology.org/2020.icon-workshop.2
%P 10-18
Markdown (Informal)
[Unified Multi Intent Order and Slot Prediction using Selective Learning Propagation](https://aclanthology.org/2020.icon-workshop.2) (Natarajan et al., ICON 2020)
ACL