Oct 2021 Correction (acl-org#1611)

* meta data author name correction for 2021.mtsummit-up.17, request submitted via email

* pdf revision for 2021.acl-long.429 closes acl-org#1610

* pdf correction for 2021.wat-1.22 closes acl-org#1608

* correction message type fix for 2021.acl-long.429

* name merge for Miruna Clinciu closes acl-org#1598

* added editor name for W19-4600 closes acl-org#1597

* added editor for W17-13 closes acl-org#1596

* re-ingested correction pdf for N19-1129 see acl-org#1399 (since the pdfs are missing), closes acl-org#1605

* mtsummit 2021 ingestion (acl-org#1590)

* ingested amta 2021; ingested bibkey using write_bibkeys_to_xml.py

* previous ingestion doesn't contain the url field; re-ingested, and added bibkey field by using write_bibkeys_to_xml.py

* updated the ingestion date, renamed amta to mtsummit

* updated the date, renamed volumes

* reingested to the correct volume id, reingested since the name of the conference has changed on the pdf

* ingested ASLTRW workshop

* ingested at4ssl workshop

* ingested mtsummit 2021 UP and LoResMT

* reingested loresmt 2021

* updated author names per conference request

* 2021.mtsummit-up.0 correction

* updated mtsummit research track title, added mtsummit events under Non-ACL Events

* added pdf for 2021.mtsummit-up.27

Co-authored-by: Matt Post <[email protected]>

* updated pdf for 2021.splurobonlp-1.0 and 2021.splurobonlp-1.1, updated their checksum

* Ingested rocling 2021, closes acl-org#1413 (acl-org#1602)

* corrected author listing for 2021.mtsummit-up.19 and 2021.mtsummit-up.20

* corrected WiNLP name, closes acl-org#1615

* corrected revision for 2021.eacl-main.310, added dataset link as an additional resource, closes acl-org#1321

* added missing SIGDIAL 2020 PDF, closes acl-org#1416

* correction for paper 2021.konvens-1.26 closes acl-org#1620

* fixed repeated is_toplevel in yaml

* fixed yaml again

Co-authored-by: Matt Post <[email protected]>

data/xml/2020.sigdial.xml

@@ -16,6 +16,7 @@
       <address>1st virtual meeting</address>
       <month>July</month>
       <year>2020</year>
+      <url hash="0fec3bb3">2020.sigdial-1</url>
     </meta>
     <frontmatter>
       <url hash="37c3ed2c">2020.sigdial-1.0</url>

data/xml/2021.acl.xml

@@ -5566,11 +5566,12 @@
       <author><first>Katsuhiko</first><last>Hayashi</last></author>
       <pages>5517–5531</pages>
       <abstract>In knowledge graph embedding, the theoretical relationship between the softmax cross-entropy and negative sampling loss functions has not been investigated. This makes it difficult to fairly compare the results of the two different loss functions. We attempted to solve this problem by using the Bregman divergence to provide a unified interpretation of the softmax cross-entropy and negative sampling loss functions. Under this interpretation, we can derive theoretical findings for fair comparison. Experimental results on the FB15k-237 and WN18RR datasets show that the theoretical findings are valid in practical settings.</abstract>
-      <url hash="36b178df">2021.acl-long.429</url>
+      <url hash="7037f4d9">2021.acl-long.429</url>
       <doi>10.18653/v1/2021.acl-long.429</doi>
       <bibkey>kamigaito-hayashi-2021-unified</bibkey>
       <revision id="1" href="2021.acl-long.429v1" hash="4ac070e5"/>
       <revision id="2" href="2021.acl-long.429v2" hash="36b178df" date="2021-08-12">Fixed typos</revision>
+      <revision id="3" href="2021.acl-long.429v3" hash="7037f4d9" date="2021-10-11">Added detailed explanations for the divergence of the SCE and NS loss functions</revision>
     </paper>
     <paper id="430">
       <title>De-Confounded Variational Encoder-Decoder for Logical Table-to-Text Generation</title>

data/xml/2021.eacl.xml

@@ -3713,8 +3713,7 @@
       <abstract>Contextualised word representation models have been successfully used for capturing different word usages and they may be an attractive alternative for representing idiomaticity in language. In this paper, we propose probing measures to assess if some of the expected linguistic properties of noun compounds, especially those related to idiomatic meanings, and their dependence on context and sensitivity to lexical choice, are readily available in some standard and widely used representations. For that, we constructed the Noun Compound Senses Dataset, which contains noun compounds and their paraphrases, in context neutral and context informative naturalistic sentences, in two languages: English and Portuguese. Results obtained using four types of probing measures with models like ELMo, BERT and some of its variants, indicate that idiomaticity is not yet accurately represented by contextualised models</abstract>
       <url hash="74cce4ec">2021.eacl-main.310</url>
       <attachment type="Software" hash="0b7f396a">2021.eacl-main.310.Software.zip</attachment>
-      <revision id="1" href="2021.eacl-main.310v1" hash="74cce4ec"/>
-      <revision id="2" href="2021.eacl-main.310v2" hash="74cce4ec" date="2021-06-03">Added copyright info and script to download dataset</revision>
+      <attachment type="Dataset" hash="0294929f">2021.eacl-main.310.Dataset.zip</attachment>
       <bibkey>garcia-etal-2021-probing</bibkey>
       <doi>10.18653/v1/2021.eacl-main.310</doi>
     </paper>

data/xml/2021.konvens.xml

@@ -252,8 +252,10 @@
       <author><first>Svenja</first><last>Räther</last></author>
       <author><first>Georg</first><last>Groh</last></author>
       <pages>247–252</pages>
-      <url hash="ec5fb607">2021.konvens-1.26</url>
+      <url hash="16c8ac64">2021.konvens-1.26</url>
       <bibkey>wich-etal-2021-german</bibkey>
+      <revision id="1" href="2021.konvens-1.26v1" hash="ec5fb607"/>
+      <revision id="2" href="2021.konvens-1.26v2" hash="16c8ac64" date="2021-10-21">Added references in tables and corrected an error in a table</revision>
     </paper>
     <paper id="27">
       <title>Comparing Contextual and Static Word Embeddings with Small Data</title>

data/xml/2021.mtsummit.xml

@@ -664,7 +664,7 @@ Our models outperform massively multilingual models such as Google (<tex-math>+8
       <title>Field Experiments of Real Time Foreign News Distribution Powered by <fixed-case>MT</fixed-case></title>
       <author><first>Keiji</first><last>Yasuda</last></author>
       <author><first>Ichiro</first><last>Yamada</last></author>
-      <author><first>Naoaki</first><last>Okazak</last></author>
+      <author><first>Naoaki</first><last>Okazaki</last></author>
       <author><first>Hideki</first><last>Tanaka</last></author>
       <author><first>Hidehiro</first><last>Asaka</last></author>
       <author><first>Takeshi</first><last>Anzai</last></author>
@@ -684,23 +684,23 @@ Our models outperform massively multilingual models such as Google (<tex-math>+8
     </paper>
     <paper id="19">
       <title>Preserving high <fixed-case>MT</fixed-case> quality for content with inline tags</title>
-      <author><first>Dimitar</first><last>Shterionov</last></author>
-      <author><first>John</first><last>J O’Flaherty</last></author>
-      <author><first>Edward</first><last>Keane</last></author>
-      <author><first>Connor</first><last>O’Reilly</last></author>
-      <author><first>Marcello</first><last>Paolo Scipioni</last></author>
-      <author><first>Marco</first><last>Giovanelli</last></author>
-      <author><first>Matteo</first><last>Villa</last></author>
+      <author><first>Konstantin</first><last>Savenkov</last></author>
+      <author><first>Grigory</first><last>Sapunov</last></author>
+      <author><first>Pavel</first><last>Stepachev</last></author>
       <pages>246-276</pages>
       <abstract>Attendees will learn about how we use machine translation to provide targeted, high MT quality for content with inline tags. We offer a new and innovative approach to inserting tags into the translated text in a way that reliably preserves their quality. This process can achieve better MT quality and lower costs, as it is MT-independent, and can be used for all languages, MT engines, and use cases.</abstract>
       <attachment type="presentation" hash="6b879691">2021.mtsummit-up.19.Presentation.pdf</attachment>
       <bibkey>savenkov-2021-preserving</bibkey>
     </paper>
     <paper id="20">
       <title>Early-stage development of the <fixed-case>S</fixed-case>ign<fixed-case>ON</fixed-case> application and open framework – challenges and opportunities</title>
-      <author><first>Konstantin</first><last>Savenkov</last></author>
-      <author><first>Grigory</first><last>Sapunov</last></author>
-      <author><first>Pavel</first><last>Stepachev</last></author>
+      <author><first>Dimitar</first><last>Shterionov</last></author>
+      <author><first>John</first><last>J O’Flaherty</last></author>
+      <author><first>Edward</first><last>Keane</last></author>
+      <author><first>Connor</first><last>O’Reilly</last></author>
+      <author><first>Marcello</first><last>Paolo Scipioni</last></author>
+      <author><first>Marco</first><last>Giovanelli</last></author>
+      <author><first>Matteo</first><last>Villa</last></author>
       <pages>277-290</pages>
       <abstract>SignON is an EU Horizon 2020 Research and Innovation project, that is developing a smartphone application and an open framework to facilitate translation between different European sign, spoken and text languages. The framework will incorporate state of the art sign language recognition and presentation, speech processing technologies and, in its core, multi-modal, cross-language machine translation. The framework, dedicated to the computationally heavy tasks and distributed on the cloud powers the application – a lightweight app running on a standard mobile device. The application and framework are being researched, designed and developed through a co-creation user-centric approach with the European deaf and hard of hearing communities. In this session, the speakers will detail their progress, challenges and lessons learned in the early-stage development of the application and framework. They will also present their Agile DevOps approach and the next steps in the evolution of the SignON project.</abstract>
       <attachment type="presentation" hash="0a80bb8f">2021.mtsummit-up.20.Presentation.pdf</attachment>

data/xml/2021.wat.xml

@@ -312,9 +312,11 @@
       <author><first>Anders</first><last>Søgaard</last></author>
       <pages>191–197</pages>
       <abstract>This work introduces Itihasa, a large-scale translation dataset containing 93,000 pairs of Sanskrit shlokas and their English translations. The shlokas are extracted from two Indian epics viz., The Ramayana and The Mahabharata. We first describe the motivation behind the curation of such a dataset and follow up with empirical analysis to bring out its nuances. We then benchmark the performance of standard translation models on this corpus and show that even state-of-the-art transformer architectures perform poorly, emphasizing the complexity of the dataset.</abstract>
-      <url hash="9f1bffa5">2021.wat-1.22</url>
+      <url hash="544fabc2">2021.wat-1.22</url>
       <doi>10.18653/v1/2021.wat-1.22</doi>
       <bibkey>aralikatte-etal-2021-itihasa</bibkey>
+      <revision id="1" href="2021.wat-1.22v1" hash="9f1bffa5"/>
+      <revision id="2" href="2021.wat-1.22v2" hash="544fabc2" date="2021-10-11">Fixed typo</revision>
     </paper>
     <paper id="23">
       <title><fixed-case>NICT</fixed-case>-5’s Submission To <fixed-case>WAT</fixed-case> 2021: <fixed-case>MBART</fixed-case> Pre-training And In-Domain Fine Tuning For Indic Languages</title>

data/xml/N19.xml

@@ -1633,9 +1633,9 @@
       <abstract>Peer review is a core element of the scientific process, particularly in conference-centered fields such as ML and NLP. However, only few studies have evaluated its properties empirically. Aiming to fill this gap, we present a corpus that contains over 4k reviews and 1.2k author responses from ACL-2018. We quantitatively and qualitatively assess the corpus. This includes a pilot study on paper weaknesses given by reviewers and on quality of author responses. We then focus on the role of the rebuttal phase, and propose a novel task to predict after-rebuttal (i.e., final) scores from initial reviews and author responses. Although author responses do have a marginal (and statistically significant) influence on the final scores, especially for borderline papers, our results suggest that a reviewer’s final score is largely determined by her initial score and the distance to the other reviewers’ initial scores. In this context, we discuss the conformity bias inherent to peer reviewing, a bias that has largely been overlooked in previous research. We hope our analyses will help better assess the usefulness of the rebuttal phase in NLP conferences.</abstract>
       <doi>10.18653/v1/N19-1129</doi>
       <url hash="6e122537">N19-1129</url>
-      <revision id="1" href="N19-1129v1" hash="fca1c505"/>
-      <revision id="2" href="N19-1129v2" hash="6e122537" date="2021-07-22">Added abbreviation explanation, clarified the use of a term</revision>
       <bibkey>gao-etal-2019-rebuttal</bibkey>
+      <revision id="1" href="N19-1129v1" hash="fca1c505"/>
+      <revision id="2" href="N19-1129v2" hash="6e122537" date="2021-10-12">Added abbreviation explanation, clarified the use of a term</revision>
     </paper>
     <paper id="130">
       <title><fixed-case>C</fixed-case>asting <fixed-case>L</fixed-case>ight on <fixed-case>I</fixed-case>nvisible <fixed-case>C</fixed-case>ities: <fixed-case>C</fixed-case>omputationally <fixed-case>E</fixed-case>ngaging with <fixed-case>L</fixed-case>iterary <fixed-case>C</fixed-case>riticism</title>

data/xml/W17.xml

@@ -2090,6 +2090,7 @@
       <editor><first>Houda</first><last>Bouamor</last></editor>
       <editor><first>Nadi</first><last>Tomeh</last></editor>
       <editor><first>Mahmoud</first><last>El-Haj</last></editor>
+      <editor><first>Wajdi</first><last>Zaghouani</last></editor>
       <doi>10.18653/v1/W17-13</doi>
       <publisher>Association for Computational Linguistics</publisher>
       <address>Valencia, Spain</address>

data/xml/W19.xml

@@ -8692,6 +8692,7 @@ One of the references was wrong therefore it is corrected to cite the appropriat
       <editor><first>Imed</first><last>Zitouni</last></editor>
       <editor><first>Nadi</first><last>Tomeh</last></editor>
       <editor><first>Mahmoud</first><last>El-Haj</last></editor>
+      <editor><first>Wajdi</first><last>Zaghouani</last></editor>
       <publisher>Association for Computational Linguistics</publisher>
       <address>Florence, Italy</address>
       <month>August</month>

data/yaml/name_variants.yaml

@@ -5456,6 +5456,9 @@
 - canonical: {first: Yang, last: Liu}
   comment: Georgetown University
   id: yang-liu-gt
+- canonical: {first: Miruna, last: Clinciu}
+  variants:
+  - {first: Miruna-Adriana, last: Clinciu}
 - canonical: {first: Yang, last: Liu}
   comment: May refer to several people
   id: yang-liu

data/yaml/venues.yaml

@@ -1067,7 +1067,7 @@ wildre:
 winlp:
   acronym: WiNLP
   is_acl: true
-  name: Women and Underrepresented Minorities in Natural Language Processing
+  name: Widening Natural Language Processing
 wmt:
   acronym: WMT
   is_acl: true