An error analysis framework for shallow surface realization
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10439970" target="_blank" >RIV/00216208:11320/21:10439970 - isvavai.cz</a>
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=ruEsPbkDUv" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=ruEsPbkDUv</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1162/tacl_a_00376" target="_blank" >10.1162/tacl_a_00376</a>
Alternative languages
Result language
angličtina
Original language name
An error analysis framework for shallow surface realization
Original language description
The metrics standardly used to evaluate Natural Language Generation (NLG) models, such as BLEU or METEOR, fail to provide information on which linguistic factors impact performance. Focusing on Surface Realization (SR), the task of converting an unordered dependency tree into a well-formed sentence, we propose a framework for error analysis which permits identifying which features of the input affect the models' results. This framework consists of two main components: (i) correlation analyses between a wide range of syntactic metrics and standard performance metrics and (ii) a set of techniques to automatically identify syntactic constructs that often co-occur with low performance scores. We demonstrate the advantages of our framework by performing error analysis on the results of 174 system runs submitted to the Multilingual SR shared tasks; we show that dependency edge accuracy correlate with automatic metrics thereby providing a more interpretable basis for evaluation; and we suggest ways in which our framework could be used to improve models and data. The framework is available in the form of a toolkit which can be used both by campaign organizers to provide detailed, linguistically interpretable feedback on the state of the art in multilingual SR, and by individual researchers to improve models and datasets.1
Czech name
—
Czech description
—
Classification
Type
J<sub>SC</sub> - Article in a specialist periodical, which is included in the SCOPUS database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Transactions of the Association for Computational Linguistics
ISSN
2307-387X
e-ISSN
—
Volume of the periodical
9
Issue of the periodical within the volume
01.02.2021
Country of publishing house
US - UNITED STATES
Number of pages
18
Pages from-to
429-446
UT code for WoS article
—
EID of the result in the Scopus database
2-s2.0-85110453412