From 9872f39ebd9b511f9532a813c19d03320ee2ebf6 Mon Sep 17 00:00:00 2001 From: xinru1414 Date: Wed, 3 Nov 2021 15:00:05 -0700 Subject: [PATCH] Oct 2021 Correction (#1611) * meta data author name correction for 2021.mtsummit-up.17, request submitted via email * pdf revision for 2021.acl-long.429 closes #1610 * pdf correction for 2021.wat-1.22 closes #1608 * correction message type fix for 2021.acl-long.429 * name merge for Miruna Clinciu closes #1598 * added editor name for W19-4600 closes #1597 * added editor for W17-13 closes #1596 * re-ingested correction pdf for N19-1129 see #1399 (since the pdfs are missing), closes #1605 * mtsummit 2021 ingestion (#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 * updated pdf for 2021.splurobonlp-1.0 and 2021.splurobonlp-1.1, updated their checksum * Ingested rocling 2021, closes #1413 (#1602) * corrected author listing for 2021.mtsummit-up.19 and 2021.mtsummit-up.20 * corrected WiNLP name, closes #1615 * corrected revision for 2021.eacl-main.310, added dataset link as an additional resource, closes #1321 * added missing SIGDIAL 2020 PDF, closes #1416 * correction for paper 2021.konvens-1.26 closes #1620 * fixed repeated is_toplevel in yaml * fixed yaml again Co-authored-by: Matt Post --- data/xml/2020.sigdial.xml | 1 + data/xml/2021.acl.xml | 3 ++- data/xml/2021.eacl.xml | 3 +-- data/xml/2021.konvens.xml | 4 +++- data/xml/2021.mtsummit.xml | 22 +++++++++++----------- data/xml/2021.wat.xml | 4 +++- data/xml/N19.xml | 4 ++-- data/xml/W17.xml | 1 + data/xml/W19.xml | 1 + data/yaml/name_variants.yaml | 3 +++ data/yaml/venues.yaml | 2 +- 11 files changed, 29 insertions(+), 19 deletions(-) diff --git a/data/xml/2020.sigdial.xml b/data/xml/2020.sigdial.xml index f4f293be3f..c1f3e9a055 100644 --- a/data/xml/2020.sigdial.xml +++ b/data/xml/2020.sigdial.xml @@ -16,6 +16,7 @@
1st virtual meeting
July 2020 + 2020.sigdial-1 2020.sigdial-1.0 diff --git a/data/xml/2021.acl.xml b/data/xml/2021.acl.xml index 127a95f9b6..25cec23471 100644 --- a/data/xml/2021.acl.xml +++ b/data/xml/2021.acl.xml @@ -5566,11 +5566,12 @@ KatsuhikoHayashi 5517–5531 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. - 2021.acl-long.429 + 2021.acl-long.429 10.18653/v1/2021.acl-long.429 kamigaito-hayashi-2021-unified Fixed typos + Added detailed explanations for the divergence of the SCE and NS loss functions De-Confounded Variational Encoder-Decoder for Logical Table-to-Text Generation diff --git a/data/xml/2021.eacl.xml b/data/xml/2021.eacl.xml index 81ed825aed..c038a9987e 100644 --- a/data/xml/2021.eacl.xml +++ b/data/xml/2021.eacl.xml @@ -3713,8 +3713,7 @@ 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 2021.eacl-main.310 2021.eacl-main.310.Software.zip - - Added copyright info and script to download dataset + 2021.eacl-main.310.Dataset.zip garcia-etal-2021-probing 10.18653/v1/2021.eacl-main.310 diff --git a/data/xml/2021.konvens.xml b/data/xml/2021.konvens.xml index 8888012cb6..c219ae1271 100644 --- a/data/xml/2021.konvens.xml +++ b/data/xml/2021.konvens.xml @@ -252,8 +252,10 @@ SvenjaRäther GeorgGroh 247–252 - 2021.konvens-1.26 + 2021.konvens-1.26 wich-etal-2021-german + + Added references in tables and corrected an error in a table Comparing Contextual and Static Word Embeddings with Small Data diff --git a/data/xml/2021.mtsummit.xml b/data/xml/2021.mtsummit.xml index 1c43ed3379..fe244ccf59 100644 --- a/data/xml/2021.mtsummit.xml +++ b/data/xml/2021.mtsummit.xml @@ -664,7 +664,7 @@ Our models outperform massively multilingual models such as Google (+8 Field Experiments of Real Time Foreign News Distribution Powered by <fixed-case>MT</fixed-case> KeijiYasuda IchiroYamada - NaoakiOkazak + NaoakiOkazaki HidekiTanaka HidehiroAsaka TakeshiAnzai @@ -684,13 +684,9 @@ Our models outperform massively multilingual models such as Google (+8 Preserving high <fixed-case>MT</fixed-case> quality for content with inline tags - DimitarShterionov - JohnJ O’Flaherty - EdwardKeane - ConnorO’Reilly - MarcelloPaolo Scipioni - MarcoGiovanelli - MatteoVilla + KonstantinSavenkov + GrigorySapunov + PavelStepachev 246-276 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. 2021.mtsummit-up.19.Presentation.pdf @@ -698,9 +694,13 @@ Our models outperform massively multilingual models such as Google (+8 Early-stage development of the <fixed-case>S</fixed-case>ign<fixed-case>ON</fixed-case> application and open framework – challenges and opportunities - KonstantinSavenkov - GrigorySapunov - PavelStepachev + DimitarShterionov + JohnJ O’Flaherty + EdwardKeane + ConnorO’Reilly + MarcelloPaolo Scipioni + MarcoGiovanelli + MatteoVilla 277-290 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. 2021.mtsummit-up.20.Presentation.pdf diff --git a/data/xml/2021.wat.xml b/data/xml/2021.wat.xml index e7dc745823..767fdcfa08 100644 --- a/data/xml/2021.wat.xml +++ b/data/xml/2021.wat.xml @@ -312,9 +312,11 @@ AndersSøgaard 191–197 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. - 2021.wat-1.22 + 2021.wat-1.22 10.18653/v1/2021.wat-1.22 aralikatte-etal-2021-itihasa + + Fixed typo <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 diff --git a/data/xml/N19.xml b/data/xml/N19.xml index cb2ea41522..cad1ad013d 100644 --- a/data/xml/N19.xml +++ b/data/xml/N19.xml @@ -1633,9 +1633,9 @@ 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. 10.18653/v1/N19-1129 N19-1129 - - Added abbreviation explanation, clarified the use of a term gao-etal-2019-rebuttal + + Added abbreviation explanation, clarified the use of a term <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 diff --git a/data/xml/W17.xml b/data/xml/W17.xml index 26146c4790..e287c3c166 100644 --- a/data/xml/W17.xml +++ b/data/xml/W17.xml @@ -2090,6 +2090,7 @@ HoudaBouamor NadiTomeh MahmoudEl-Haj + WajdiZaghouani 10.18653/v1/W17-13 Association for Computational Linguistics
Valencia, Spain
diff --git a/data/xml/W19.xml b/data/xml/W19.xml index bf98bdf0be..e3f3aa1dec 100644 --- a/data/xml/W19.xml +++ b/data/xml/W19.xml @@ -8692,6 +8692,7 @@ One of the references was wrong therefore it is corrected to cite the appropriat ImedZitouni NadiTomeh MahmoudEl-Haj + WajdiZaghouani Association for Computational Linguistics
Florence, Italy
August diff --git a/data/yaml/name_variants.yaml b/data/yaml/name_variants.yaml index 44b101a685..d0b12edd9b 100644 --- a/data/yaml/name_variants.yaml +++ b/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 diff --git a/data/yaml/venues.yaml b/data/yaml/venues.yaml index 6095966a0c..5d383bea30 100644 --- a/data/yaml/venues.yaml +++ b/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