@inproceedings{natarajan-etal-2020-semantic,
title = "Semantic Slot Prediction on low corpus data using finite user defined list",
author = "Natarajan, Bharatram and
Simma, Dharani and
Singh, Chirag and
Nediyanchath, Anish and
Sengupta, Sreoshi",
editor = "Bhattacharyya, Pushpak and
Sharma, Dipti Misra and
Sangal, Rajeev",
booktitle = "Proceedings of the 17th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2020",
address = "Indian Institute of Technology Patna, Patna, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2020.icon-main.44",
pages = "329--333",
abstract = "Semantic slot prediction is one of the important task for natural language understanding (NLU). They depend on the quality and quantity of the human crafted training data, which affects model generalization. With the advent of voice assistants exposing AI platforms to third party developers, training data quality and quantity matters for any machine learning algorithm to learn and generalize properly.AI platforms provides provision to add custom external plist defined by the developers for the training data. Hence we are exploring dataset, called LowCorpusSlotData, containing low corpus training data with larger number of slots and significant test data. We also use external plist for the above dataset to aid in slot identification. We experimented using state of the art architectures like Bi-directional Encoder Representations from Transformers (BERT) with variants and Bi-directional Encoder with Custom Decoder. To address the low corpus problem, we propose a pipeline approach where we extract candidate slot information using the external plist extractor module and feed as input along with utterance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="natarajan-etal-2020-semantic">
<titleInfo>
<title>Semantic Slot Prediction on low corpus data using finite user defined list</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">Dharani</namePart>
<namePart type="family">Simma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chirag</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anish</namePart>
<namePart type="family">Nediyanchath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sreoshi</namePart>
<namePart type="family">Sengupta</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 17th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajeev</namePart>
<namePart type="family">Sangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Indian Institute of Technology Patna, Patna, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Semantic slot prediction is one of the important task for natural language understanding (NLU). They depend on the quality and quantity of the human crafted training data, which affects model generalization. With the advent of voice assistants exposing AI platforms to third party developers, training data quality and quantity matters for any machine learning algorithm to learn and generalize properly.AI platforms provides provision to add custom external plist defined by the developers for the training data. Hence we are exploring dataset, called LowCorpusSlotData, containing low corpus training data with larger number of slots and significant test data. We also use external plist for the above dataset to aid in slot identification. We experimented using state of the art architectures like Bi-directional Encoder Representations from Transformers (BERT) with variants and Bi-directional Encoder with Custom Decoder. To address the low corpus problem, we propose a pipeline approach where we extract candidate slot information using the external plist extractor module and feed as input along with utterance.</abstract>
<identifier type="citekey">natarajan-etal-2020-semantic</identifier>
<location>
<url>https://aclanthology.org/2020.icon-main.44</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>329</start>
<end>333</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Slot Prediction on low corpus data using finite user defined list
%A Natarajan, Bharatram
%A Simma, Dharani
%A Singh, Chirag
%A Nediyanchath, Anish
%A Sengupta, Sreoshi
%Y Bhattacharyya, Pushpak
%Y Sharma, Dipti Misra
%Y Sangal, Rajeev
%S Proceedings of the 17th International Conference on Natural Language Processing (ICON)
%D 2020
%8 December
%I NLP Association of India (NLPAI)
%C Indian Institute of Technology Patna, Patna, India
%F natarajan-etal-2020-semantic
%X Semantic slot prediction is one of the important task for natural language understanding (NLU). They depend on the quality and quantity of the human crafted training data, which affects model generalization. With the advent of voice assistants exposing AI platforms to third party developers, training data quality and quantity matters for any machine learning algorithm to learn and generalize properly.AI platforms provides provision to add custom external plist defined by the developers for the training data. Hence we are exploring dataset, called LowCorpusSlotData, containing low corpus training data with larger number of slots and significant test data. We also use external plist for the above dataset to aid in slot identification. We experimented using state of the art architectures like Bi-directional Encoder Representations from Transformers (BERT) with variants and Bi-directional Encoder with Custom Decoder. To address the low corpus problem, we propose a pipeline approach where we extract candidate slot information using the external plist extractor module and feed as input along with utterance.
%U https://aclanthology.org/2020.icon-main.44
%P 329-333
Markdown (Informal)
[Semantic Slot Prediction on low corpus data using finite user defined list](https://aclanthology.org/2020.icon-main.44) (Natarajan et al., ICON 2020)
ACL