@inproceedings{basu-roy-chowdhury-etal-2019-instance,
title = "Instance-based Inductive Deep Transfer Learning by Cross-Dataset Querying with Locality Sensitive Hashing",
author = "Basu Roy Chowdhury, Somnath and
M, Annervaz and
Dukkipati, Ambedkar",
editor = "Cherry, Colin and
Durrett, Greg and
Foster, George and
Haffari, Reza and
Khadivi, Shahram and
Peng, Nanyun and
Ren, Xiang and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6120",
doi = "10.18653/v1/D19-6120",
pages = "183--191",
abstract = "Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset i.e., the amount of data available with ground truth. Learning algorithms try to generalize solely based on the data that it is presented with during the training. In this work, we propose an inductive transfer learning method that can augment learning models by infusing similar instances from different learning tasks in Natural Language Processing (NLP) domain. We propose to use instance representations from a source dataset, without inheriting anything else from the source learning model. Representations of the instances of source and target datasets are learned, retrieval of relevant source instances is performed using soft-attention mechanism and locality sensitive hashing and then augmented into the model during training on the target dataset. Therefore, while learning from a training data, we also simultaneously exploit and infuse relevant local instance-level information from an external data. Using this approach we have shown significant improvements over the baseline for three major news classification datasets. Experimental evaluations also show that the proposed approach reduces dependency on labeled data by a significant margin for comparable performance. With our proposed cross dataset learning procedure we show that one can achieve competitive/better performance than learning from a single dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basu-roy-chowdhury-etal-2019-instance">
<titleInfo>
<title>Instance-based Inductive Deep Transfer Learning by Cross-Dataset Querying with Locality Sensitive Hashing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Somnath</namePart>
<namePart type="family">Basu Roy Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annervaz</namePart>
<namePart type="family">M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ambedkar</namePart>
<namePart type="family">Dukkipati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset i.e., the amount of data available with ground truth. Learning algorithms try to generalize solely based on the data that it is presented with during the training. In this work, we propose an inductive transfer learning method that can augment learning models by infusing similar instances from different learning tasks in Natural Language Processing (NLP) domain. We propose to use instance representations from a source dataset, without inheriting anything else from the source learning model. Representations of the instances of source and target datasets are learned, retrieval of relevant source instances is performed using soft-attention mechanism and locality sensitive hashing and then augmented into the model during training on the target dataset. Therefore, while learning from a training data, we also simultaneously exploit and infuse relevant local instance-level information from an external data. Using this approach we have shown significant improvements over the baseline for three major news classification datasets. Experimental evaluations also show that the proposed approach reduces dependency on labeled data by a significant margin for comparable performance. With our proposed cross dataset learning procedure we show that one can achieve competitive/better performance than learning from a single dataset.</abstract>
<identifier type="citekey">basu-roy-chowdhury-etal-2019-instance</identifier>
<identifier type="doi">10.18653/v1/D19-6120</identifier>
<location>
<url>https://aclanthology.org/D19-6120</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>183</start>
<end>191</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Instance-based Inductive Deep Transfer Learning by Cross-Dataset Querying with Locality Sensitive Hashing
%A Basu Roy Chowdhury, Somnath
%A M, Annervaz
%A Dukkipati, Ambedkar
%Y Cherry, Colin
%Y Durrett, Greg
%Y Foster, George
%Y Haffari, Reza
%Y Khadivi, Shahram
%Y Peng, Nanyun
%Y Ren, Xiang
%Y Swayamdipta, Swabha
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F basu-roy-chowdhury-etal-2019-instance
%X Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset i.e., the amount of data available with ground truth. Learning algorithms try to generalize solely based on the data that it is presented with during the training. In this work, we propose an inductive transfer learning method that can augment learning models by infusing similar instances from different learning tasks in Natural Language Processing (NLP) domain. We propose to use instance representations from a source dataset, without inheriting anything else from the source learning model. Representations of the instances of source and target datasets are learned, retrieval of relevant source instances is performed using soft-attention mechanism and locality sensitive hashing and then augmented into the model during training on the target dataset. Therefore, while learning from a training data, we also simultaneously exploit and infuse relevant local instance-level information from an external data. Using this approach we have shown significant improvements over the baseline for three major news classification datasets. Experimental evaluations also show that the proposed approach reduces dependency on labeled data by a significant margin for comparable performance. With our proposed cross dataset learning procedure we show that one can achieve competitive/better performance than learning from a single dataset.
%R 10.18653/v1/D19-6120
%U https://aclanthology.org/D19-6120
%U https://doi.org/10.18653/v1/D19-6120
%P 183-191
Markdown (Informal)
[Instance-based Inductive Deep Transfer Learning by Cross-Dataset Querying with Locality Sensitive Hashing](https://aclanthology.org/D19-6120) (Basu Roy Chowdhury et al., 2019)
ACL