@inproceedings{orlanski-gittens-2021-reading,
title = "Reading {S}tack{O}verflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation",
author = "Orlanski, Gabriel and
Gittens, Alex",
editor = "Lachmy, Royi and
Yao, Ziyu and
Durrett, Greg and
Gligoric, Milos and
Li, Junyi Jessy and
Mooney, Ray and
Neubig, Graham and
Su, Yu and
Sun, Huan and
Tsarfaty, Reut",
booktitle = "Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlp4prog-1.8",
doi = "10.18653/v1/2021.nlp4prog-1.8",
pages = "65--76",
abstract = "Answering a programming question with only its title is difficult as salient contextual information is left out. To address this, we present a corpus of over 40,000 StackOverflow question texts to be used in conjunction with the corresponding intents from the CoNaLa dataset (Yin et al., 2018). Using both the intent and the question body, we use BART to establish a baseline BLEU score of 34.35 for this new task. We then find further improvements of 2.8{\%} by combining the mined CoNaLa data with the labeled data to achieve a 35.32 BLEU score. We then evaluate the prior state-of-the-art CoNaLa models with this additional data. We find that our proposed method of using the body and mined data beats that of the previous state-of-the-art by a 71.96{\%} BLEU score. Finally, we perform ablations that prove that BART is an unsupervised multimodal learner and examine its extractive behavior.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="orlanski-gittens-2021-reading">
<titleInfo>
<title>Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Orlanski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Gittens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Royi</namePart>
<namePart type="family">Lachmy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyu</namePart>
<namePart type="family">Yao</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">Milos</namePart>
<namePart type="family">Gligoric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ray</namePart>
<namePart type="family">Mooney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</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>Answering a programming question with only its title is difficult as salient contextual information is left out. To address this, we present a corpus of over 40,000 StackOverflow question texts to be used in conjunction with the corresponding intents from the CoNaLa dataset (Yin et al., 2018). Using both the intent and the question body, we use BART to establish a baseline BLEU score of 34.35 for this new task. We then find further improvements of 2.8% by combining the mined CoNaLa data with the labeled data to achieve a 35.32 BLEU score. We then evaluate the prior state-of-the-art CoNaLa models with this additional data. We find that our proposed method of using the body and mined data beats that of the previous state-of-the-art by a 71.96% BLEU score. Finally, we perform ablations that prove that BART is an unsupervised multimodal learner and examine its extractive behavior.</abstract>
<identifier type="citekey">orlanski-gittens-2021-reading</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4prog-1.8</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4prog-1.8</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>65</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation
%A Orlanski, Gabriel
%A Gittens, Alex
%Y Lachmy, Royi
%Y Yao, Ziyu
%Y Durrett, Greg
%Y Gligoric, Milos
%Y Li, Junyi Jessy
%Y Mooney, Ray
%Y Neubig, Graham
%Y Su, Yu
%Y Sun, Huan
%Y Tsarfaty, Reut
%S Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F orlanski-gittens-2021-reading
%X Answering a programming question with only its title is difficult as salient contextual information is left out. To address this, we present a corpus of over 40,000 StackOverflow question texts to be used in conjunction with the corresponding intents from the CoNaLa dataset (Yin et al., 2018). Using both the intent and the question body, we use BART to establish a baseline BLEU score of 34.35 for this new task. We then find further improvements of 2.8% by combining the mined CoNaLa data with the labeled data to achieve a 35.32 BLEU score. We then evaluate the prior state-of-the-art CoNaLa models with this additional data. We find that our proposed method of using the body and mined data beats that of the previous state-of-the-art by a 71.96% BLEU score. Finally, we perform ablations that prove that BART is an unsupervised multimodal learner and examine its extractive behavior.
%R 10.18653/v1/2021.nlp4prog-1.8
%U https://aclanthology.org/2021.nlp4prog-1.8
%U https://doi.org/10.18653/v1/2021.nlp4prog-1.8
%P 65-76
Markdown (Informal)
[Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation](https://aclanthology.org/2021.nlp4prog-1.8) (Orlanski & Gittens, NLP4Prog 2021)
ACL