@inproceedings{ramo-leppanen-2021-using,
title = "Using contextual and cross-lingual word embeddings to improve variety in template-based {NLG} for automated journalism",
author = {R{\"a}m{\"o}, Miia and
Lepp{\"a}nen, Leo},
editor = "Toivonen, Hannu and
Boggia, Michele",
booktitle = "Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.hackashop-1.9",
pages = "62--70",
abstract = "In this work, we describe our efforts in improving the variety of language generated from a rule-based NLG system for automated journalism. We present two approaches: one based on inserting completely new words into sentences generated from templates, and another based on replacing words with synonyms. Our initial results from a human evaluation conducted in English indicate that these approaches successfully improve the variety of the language without significantly modifying sentence meaning. We also present variations of the methods applicable to low-resource languages, simulated here using Finnish, where cross-lingual aligned embeddings are harnessed to make use of linguistic resources in a high-resource language. A human evaluation indicates that while proposed methods show potential in the low-resource case, additional work is needed to improve their performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramo-leppanen-2021-using">
<titleInfo>
<title>Using contextual and cross-lingual word embeddings to improve variety in template-based NLG for automated journalism</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miia</namePart>
<namePart type="family">Rämö</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Leppänen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hannu</namePart>
<namePart type="family">Toivonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Boggia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we describe our efforts in improving the variety of language generated from a rule-based NLG system for automated journalism. We present two approaches: one based on inserting completely new words into sentences generated from templates, and another based on replacing words with synonyms. Our initial results from a human evaluation conducted in English indicate that these approaches successfully improve the variety of the language without significantly modifying sentence meaning. We also present variations of the methods applicable to low-resource languages, simulated here using Finnish, where cross-lingual aligned embeddings are harnessed to make use of linguistic resources in a high-resource language. A human evaluation indicates that while proposed methods show potential in the low-resource case, additional work is needed to improve their performance.</abstract>
<identifier type="citekey">ramo-leppanen-2021-using</identifier>
<location>
<url>https://aclanthology.org/2021.hackashop-1.9</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>62</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using contextual and cross-lingual word embeddings to improve variety in template-based NLG for automated journalism
%A Rämö, Miia
%A Leppänen, Leo
%Y Toivonen, Hannu
%Y Boggia, Michele
%S Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F ramo-leppanen-2021-using
%X In this work, we describe our efforts in improving the variety of language generated from a rule-based NLG system for automated journalism. We present two approaches: one based on inserting completely new words into sentences generated from templates, and another based on replacing words with synonyms. Our initial results from a human evaluation conducted in English indicate that these approaches successfully improve the variety of the language without significantly modifying sentence meaning. We also present variations of the methods applicable to low-resource languages, simulated here using Finnish, where cross-lingual aligned embeddings are harnessed to make use of linguistic resources in a high-resource language. A human evaluation indicates that while proposed methods show potential in the low-resource case, additional work is needed to improve their performance.
%U https://aclanthology.org/2021.hackashop-1.9
%P 62-70
Markdown (Informal)
[Using contextual and cross-lingual word embeddings to improve variety in template-based NLG for automated journalism](https://aclanthology.org/2021.hackashop-1.9) (Rämö & Leppänen, Hackashop 2021)
ACL