@inproceedings{manandise-de-peuter-2020-mitigating,
title = "Mitigating Silence in Compliance Terminology during Parsing of Utterances",
author = "Manandise, Esme and
de Peuter, Conrad",
editor = "El-Haj, Dr Mahmoud and
Athanasakou, Dr Vasiliki and
Ferradans, Dr Sira and
Salzedo, Dr Catherine and
Elhag, Dr Ans and
Bouamor, Dr Houda and
Litvak, Dr Marina and
Rayson, Dr Paul and
Giannakopoulos, Dr George and
Pittaras, Nikiforos",
booktitle = "Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "COLING",
url = "https://aclanthology.org/2020.fnp-1.33",
pages = "204--212",
abstract = "This paper reports on an approach to increase multi-token-term recall in a parsing task. We use a compliance-domain parser to extract, during the process of parsing raw text, terms that are unlisted in the terminology. The parser uses a similarity measure (Generalized Dice Coefficient) between listed terms and unlisted term candidates to (i) determine term status, (ii) serve putative terms to the parser, (iii) decrease parsing complexity by glomming multi-tokens as lexical singletons, and (iv) automatically augment the terminology after parsing of an utterance completes. We illustrate a small experiment with examples from the tax-and-regulations domain. Bootstrapping the parsing process to detect out- of-vocabulary terms at runtime increases parsing accuracy in addition to producing other benefits to a natural-language-processing pipeline, which translates arithmetic calculations written in English into computer-executable operations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manandise-de-peuter-2020-mitigating">
<titleInfo>
<title>Mitigating Silence in Compliance Terminology during Parsing of Utterances</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esme</namePart>
<namePart type="family">Manandise</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Conrad</namePart>
<namePart type="family">de Peuter</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 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dr</namePart>
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr</namePart>
<namePart type="given">Vasiliki</namePart>
<namePart type="family">Athanasakou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr</namePart>
<namePart type="given">Sira</namePart>
<namePart type="family">Ferradans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr</namePart>
<namePart type="given">Catherine</namePart>
<namePart type="family">Salzedo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr</namePart>
<namePart type="given">Ans</namePart>
<namePart type="family">Elhag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr</namePart>
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr</namePart>
<namePart type="given">Marina</namePart>
<namePart type="family">Litvak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr</namePart>
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr</namePart>
<namePart type="given">George</namePart>
<namePart type="family">Giannakopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikiforos</namePart>
<namePart type="family">Pittaras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>COLING</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper reports on an approach to increase multi-token-term recall in a parsing task. We use a compliance-domain parser to extract, during the process of parsing raw text, terms that are unlisted in the terminology. The parser uses a similarity measure (Generalized Dice Coefficient) between listed terms and unlisted term candidates to (i) determine term status, (ii) serve putative terms to the parser, (iii) decrease parsing complexity by glomming multi-tokens as lexical singletons, and (iv) automatically augment the terminology after parsing of an utterance completes. We illustrate a small experiment with examples from the tax-and-regulations domain. Bootstrapping the parsing process to detect out- of-vocabulary terms at runtime increases parsing accuracy in addition to producing other benefits to a natural-language-processing pipeline, which translates arithmetic calculations written in English into computer-executable operations.</abstract>
<identifier type="citekey">manandise-de-peuter-2020-mitigating</identifier>
<location>
<url>https://aclanthology.org/2020.fnp-1.33</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>204</start>
<end>212</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating Silence in Compliance Terminology during Parsing of Utterances
%A Manandise, Esme
%A de Peuter, Conrad
%Y El-Haj, Dr Mahmoud
%Y Athanasakou, Dr Vasiliki
%Y Ferradans, Dr Sira
%Y Salzedo, Dr Catherine
%Y Elhag, Dr Ans
%Y Bouamor, Dr Houda
%Y Litvak, Dr Marina
%Y Rayson, Dr Paul
%Y Giannakopoulos, Dr George
%Y Pittaras, Nikiforos
%S Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation
%D 2020
%8 December
%I COLING
%C Barcelona, Spain (Online)
%F manandise-de-peuter-2020-mitigating
%X This paper reports on an approach to increase multi-token-term recall in a parsing task. We use a compliance-domain parser to extract, during the process of parsing raw text, terms that are unlisted in the terminology. The parser uses a similarity measure (Generalized Dice Coefficient) between listed terms and unlisted term candidates to (i) determine term status, (ii) serve putative terms to the parser, (iii) decrease parsing complexity by glomming multi-tokens as lexical singletons, and (iv) automatically augment the terminology after parsing of an utterance completes. We illustrate a small experiment with examples from the tax-and-regulations domain. Bootstrapping the parsing process to detect out- of-vocabulary terms at runtime increases parsing accuracy in addition to producing other benefits to a natural-language-processing pipeline, which translates arithmetic calculations written in English into computer-executable operations.
%U https://aclanthology.org/2020.fnp-1.33
%P 204-212
Markdown (Informal)
[Mitigating Silence in Compliance Terminology during Parsing of Utterances](https://aclanthology.org/2020.fnp-1.33) (Manandise & de Peuter, FNP 2020)
ACL