From 63db20f4f676df369a70aa3de44ba46bf333ddf3 Mon Sep 17 00:00:00 2001
From: acl-pwc-bot <94475230+acl-pwc-bot@users.noreply.github.com>
Date: Thu, 7 Mar 2024 02:05:14 +0100
Subject: [PATCH] Update metadata from Papers with Code
---
data/xml/2016.iwslt.xml | 1 +
data/xml/2018.iwslt.xml | 1 +
data/xml/2019.iwslt.xml | 2 +-
data/xml/2020.acl.xml | 9 +++++++++
data/xml/2020.bea.xml | 1 +
data/xml/2020.coling.xml | 1 +
data/xml/2020.emnlp.xml | 5 +++++
data/xml/2020.findings.xml | 3 +++
data/xml/2020.iwslt.xml | 2 +-
data/xml/2020.lrec.xml | 1 +
data/xml/2020.repl4nlp.xml | 1 +
data/xml/2021.acl.xml | 7 +++++++
data/xml/2021.eacl.xml | 1 +
data/xml/2021.emnlp.xml | 7 ++++++-
data/xml/2021.findings.xml | 4 ++++
data/xml/2021.iwslt.xml | 3 +--
data/xml/2021.naacl.xml | 1 +
data/xml/2021.ranlp.xml | 1 +
data/xml/2022.acl.xml | 4 ++++
data/xml/2022.coling.xml | 2 ++
data/xml/2022.findings.xml | 1 +
data/xml/2022.iwslt.xml | 4 +---
data/xml/2022.lrec.xml | 1 +
data/xml/2022.naacl.xml | 5 ++++-
data/xml/2022.rocling.xml | 2 +-
data/xml/C18.xml | 4 ++++
data/xml/D11.xml | 1 +
data/xml/D14.xml | 1 +
data/xml/D17.xml | 6 +++++-
data/xml/D18.xml | 10 ++++++++++
data/xml/D19.xml | 12 ++++++++++++
data/xml/E17.xml | 1 +
data/xml/K16.xml | 1 +
data/xml/K18.xml | 1 +
data/xml/K19.xml | 3 +++
data/xml/L16.xml | 2 +-
data/xml/N16.xml | 1 +
data/xml/N18.xml | 8 ++++++++
data/xml/N19.xml | 3 +++
data/xml/P16.xml | 4 ++++
data/xml/P17.xml | 5 +++++
data/xml/P18.xml | 12 ++++++++++++
data/xml/P19.xml | 11 +++++++++++
data/xml/Q16.xml | 1 +
data/xml/Q17.xml | 1 +
data/xml/S14.xml | 2 +-
data/xml/W12.xml | 1 -
data/xml/W14.xml | 2 +-
data/xml/W17.xml | 2 ++
data/xml/W18.xml | 2 +-
data/xml/W19.xml | 1 +
51 files changed, 152 insertions(+), 16 deletions(-)
diff --git a/data/xml/2016.iwslt.xml b/data/xml/2016.iwslt.xml
index e9b7eb89e2..55ce6b8121 100644
--- a/data/xml/2016.iwslt.xml
+++ b/data/xml/2016.iwslt.xml
@@ -96,6 +96,7 @@
2016.iwslt-1.8
lazaridis-etal-2016-investigating
LibriSpeech
+ TED-LIUM
Towards Improving Low-Resource Speech Recognition Using Articulatory and Language Features
diff --git a/data/xml/2018.iwslt.xml b/data/xml/2018.iwslt.xml
index a33f3adc49..be2b5c991e 100644
--- a/data/xml/2018.iwslt.xml
+++ b/data/xml/2018.iwslt.xml
@@ -167,6 +167,7 @@
This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former, with three contrastive systems. We tried also the latter, but were not able to finish our end-to-end model in time. All of our systems start by transcribing the audio into text through an automatic speech recognition (ASR) model trained on the TED-LIUM English Speech Recognition Corpus (TED-LIUM). Afterwards, we feed the transcripts into English-German text-based neural machine translation (NMT) models. Our systems employ three different translation models trained on separate training sets compiled from the English-German part of the TED Speech Translation Corpus (TED-TRANS) and the OPENSUBTITLES2018 section of the OPUS collection. In this paper, we also describe the experiments leading up to our final systems. Our experiments indicate that using OPENSUBTITLES2018 in training significantly improves translation performance. We also experimented with various preand postprocessing routines for the NMT module, but we did not have much success with these. Our best-scoring system attains a BLEU score of 16.45 on the test set for this year’s task.
2018.iwslt-1.13
sulubacak-etal-2018-memad
+ TED-LIUM
Prompsit’s Submission to the <fixed-case>IWSLT</fixed-case> 2018 Low Resource Machine Translation Task
diff --git a/data/xml/2019.iwslt.xml b/data/xml/2019.iwslt.xml
index 2e0f94d663..c3c8fa0e3b 100644
--- a/data/xml/2019.iwslt.xml
+++ b/data/xml/2019.iwslt.xml
@@ -74,6 +74,7 @@
inaguma-etal-2019-espnet
LibriSpeech
MuST-C
+ TED-LIUM
<fixed-case>ON</fixed-case>-<fixed-case>TRAC</fixed-case> Consortium End-to-End Speech Translation Systems for the <fixed-case>IWSLT</fixed-case> 2019 Shared Task
@@ -82,7 +83,6 @@
2019.iwslt-1.5
nguyen-2019-trac
MuST-C
- TED-LIUM 3
Transformer-based Cascaded Multimodal Speech Translation
diff --git a/data/xml/2020.acl.xml b/data/xml/2020.acl.xml
index 6b9bcea021..39a0430720 100644
--- a/data/xml/2020.acl.xml
+++ b/data/xml/2020.acl.xml
@@ -673,6 +673,7 @@
li-etal-2020-dice
ShannonAI/dice_loss_for_NLP
+ CoNLL
CoNLL 2003
MSRA CN NER
OntoNotes 4.0
@@ -2819,6 +2820,7 @@
jiang-etal-2020-generalizing
jzbjyb/SpanRel
+ CoNLL
CoNLL 2003
CoNLL-2012
OIE2016
@@ -4469,6 +4471,7 @@
zhang-etal-2020-efficient
yzhangcs/crfpar
+ CoNLL
CoNLL-2009
Penn Treebank
Universal Dependencies
@@ -5764,6 +5767,7 @@
kaneko-etal-2020-encoder
kanekomasahiro/bert-gec
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
JFLEG
WI-LOCNESS
@@ -7705,6 +7709,7 @@
ShannonAI/mrc-for-flat-nested-ner
ACE 2004
ACE 2005
+ CoNLL
CoNLL 2003
GENIA
MSRA CN NER
@@ -8575,6 +8580,7 @@
juntaoy/biaffine-ner
ACE 2004
ACE 2005
+ CoNLL
CoNLL 2002
CoNLL 2003
GENIA
@@ -8637,6 +8643,7 @@
wu-etal-2020-single
microsoft/vert-papers
+ CoNLL
CoNLL 2002
CoNLL 2003
@@ -9263,6 +9270,7 @@
wu-etal-2020-corefqa
ShannonAI/CorefQA
+ CoNLL
CoNLL-2012
@@ -11523,6 +11531,7 @@
10.18653/v1/2020.acl-main.777
chen-etal-2020-seqvat
+ CoNLL
CoNLL-2000
diff --git a/data/xml/2020.bea.xml b/data/xml/2020.bea.xml
index 4fcc362477..bee05c222a 100644
--- a/data/xml/2020.bea.xml
+++ b/data/xml/2020.bea.xml
@@ -222,6 +222,7 @@
10.18653/v1/2020.bea-1.16
omelianchuk-etal-2020-gector
grammarly/gector
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
FCE
WI-LOCNESS
diff --git a/data/xml/2020.coling.xml b/data/xml/2020.coling.xml
index 715eb2bf3b..bde3738e4e 100644
--- a/data/xml/2020.coling.xml
+++ b/data/xml/2020.coling.xml
@@ -1051,6 +1051,7 @@
10.18653/v1/2020.coling-main.78
luoma-pyysalo-2020-exploring
jouniluoma/bert-ner-cmv
+ CoNLL
CoNLL 2002
CoNLL 2003
diff --git a/data/xml/2020.emnlp.xml b/data/xml/2020.emnlp.xml
index b7a1791463..7bd13acca5 100644
--- a/data/xml/2020.emnlp.xml
+++ b/data/xml/2020.emnlp.xml
@@ -2042,6 +2042,7 @@
ACE 2004
ACE 2005
Adverse Drug Events (ADE) Corpus
+ CoNLL
CoNLL04
FewRel
Wiki-ZSL
@@ -7329,6 +7330,7 @@
wang-etal-2020-ain
Alibaba-NLP/AIN
ATIS
+ CoNLL
CoNLL 2003
@@ -7903,6 +7905,7 @@
yamada-etal-2020-luke
studio-ousia/luke
+ CoNLL
CoNLL 2003
Open Entity
ReCoRD
@@ -10400,6 +10403,7 @@
toshniwal-etal-2020-learning
shtoshni92/long-doc-coref
+ CoNLL
CoNLL-2012
OntoNotes 5.0
@@ -10414,6 +10418,7 @@
xu-choi-2020-revealing
lxucs/coref-hoi
+ CoNLL
CoNLL-2012
diff --git a/data/xml/2020.findings.xml b/data/xml/2020.findings.xml
index a2a5c5b77e..9c25e740aa 100644
--- a/data/xml/2020.findings.xml
+++ b/data/xml/2020.findings.xml
@@ -417,6 +417,7 @@
10.18653/v1/2020.findings-emnlp.28
chen-etal-2020-enhance
+ CoNLL
CoNLL 2003
CoNLL-2000
@@ -4408,6 +4409,7 @@
szymanski-etal-2020-wer
LibriSpeech
+ TED-LIUM
Detecting Stance in Media On Global Warming
@@ -5278,6 +5280,7 @@
2020.findings-emnlp.356
10.18653/v1/2020.findings-emnlp.356
wang-etal-2020-embeddings
+ CoNLL
CoNLL 2003
diff --git a/data/xml/2020.iwslt.xml b/data/xml/2020.iwslt.xml
index ecc137ab20..3e3ed98b70 100644
--- a/data/xml/2020.iwslt.xml
+++ b/data/xml/2020.iwslt.xml
@@ -75,7 +75,6 @@
elbayad-etal-2020-trac
How2
MuST-C
- TED-LIUM 3
Start-Before-End and End-to-End: Neural Speech Translation by <fixed-case>A</fixed-case>pp<fixed-case>T</fixed-case>ek and <fixed-case>RWTH</fixed-case> <fixed-case>A</fixed-case>achen <fixed-case>U</fixed-case>niversity
@@ -393,6 +392,7 @@
10.18653/v1/2020.iwslt-1.25
machacek-etal-2020-elitr
+ TED-LIUM
Is 42 the Answer to Everything in Subtitling-oriented Speech Translation?
diff --git a/data/xml/2020.lrec.xml b/data/xml/2020.lrec.xml
index 49fc8e8a0c..6cfa06cf53 100644
--- a/data/xml/2020.lrec.xml
+++ b/data/xml/2020.lrec.xml
@@ -52,6 +52,7 @@
eng
yu-etal-2020-cluster
juntaoy/dali-full-anaphora
+ CoNLL
CoNLL-2012
diff --git a/data/xml/2020.repl4nlp.xml b/data/xml/2020.repl4nlp.xml
index 9e278c20f0..ad843b81bd 100644
--- a/data/xml/2020.repl4nlp.xml
+++ b/data/xml/2020.repl4nlp.xml
@@ -33,6 +33,7 @@
10.18653/v1/2020.repl4nlp-1.1
liu-etal-2020-zero
+ CoNLL
CoNLL04
diff --git a/data/xml/2021.acl.xml b/data/xml/2021.acl.xml
index 4756787fb9..8b6ebe1041 100644
--- a/data/xml/2021.acl.xml
+++ b/data/xml/2021.acl.xml
@@ -2301,6 +2301,7 @@
modelscope/adaseq
BC5CDR
CMeEE
+ CoNLL
CoNLL 2003
CoNLL++
CoNLL-2000
@@ -3366,6 +3367,7 @@
wang-etal-2021-automated
Alibaba-NLP/ACE
+ CoNLL
CoNLL 2002
CoNLL 2003
CoNLL-2000
@@ -3527,6 +3529,7 @@
tricktreat/locate-and-label
ACE 2004
ACE 2005
+ CoNLL
CoNLL 2003
GENIA
Weibo NER
@@ -7340,6 +7343,7 @@
yhcc/BARTNER
ACE 2004
ACE 2005
+ CoNLL
CoNLL 2003
GENIA
OntoNotes 5.0
@@ -8330,6 +8334,7 @@
10.18653/v1/2021.acl-long.511
colombo-etal-2021-novel
+ Yelp
Determinantal Beam Search
@@ -9368,6 +9373,7 @@
kirstain-etal-2021-coreference
yuvalkirstain/s2e-coref
+ CoNLL
CoNLL-2012
GAP Coreference Dataset
@@ -10628,6 +10634,7 @@
google-research-datasets/clang8
AKCES-GEC
C4
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
FCE
mC4
diff --git a/data/xml/2021.eacl.xml b/data/xml/2021.eacl.xml
index 4147a71fd3..81b3e04927 100644
--- a/data/xml/2021.eacl.xml
+++ b/data/xml/2021.eacl.xml
@@ -584,6 +584,7 @@
10.18653/v1/2021.eacl-main.40
ManojPrabhakar/CHOLAN
AIDA CoNLL-YAGO
+ CoNLL
DBpedia
T-REx
diff --git a/data/xml/2021.emnlp.xml b/data/xml/2021.emnlp.xml
index c9b76fc9d2..d93d349157 100644
--- a/data/xml/2021.emnlp.xml
+++ b/data/xml/2021.emnlp.xml
@@ -4067,7 +4067,7 @@
zheng-etal-2021-allocating
10.18653/v1/2021.emnlp-main.257
- bozheng-hit/vocapxlm
+ bozheng-hit/vocapxlm
MLQA
PAWS-X
TyDiQA
@@ -6894,6 +6894,7 @@
10.18653/v1/2021.emnlp-main.437
wzhouad/NLL-IE
+ CoNLL
CoNLL 2003
CoNLL++
TACRED
@@ -9557,6 +9558,7 @@
nicola-decao/efficient-autoregressive-EL
AIDA CoNLL-YAGO
+ CoNLL
Word-Level Coreference Resolution
@@ -9568,6 +9570,7 @@
10.18653/v1/2021.emnlp-main.605
vdobrovolskii/wl-coref
+ CoNLL
CoNLL-2012
OntoNotes 5.0
@@ -9669,6 +9672,7 @@
10.18653/v1/2021.emnlp-main.611
michiyasunaga/LM-Critic
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
GMEG-wiki
GMEG-yahoo
@@ -11394,6 +11398,7 @@
IBM/yaso-tsa
YASO
SST
+ Yelp
An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction
diff --git a/data/xml/2021.findings.xml b/data/xml/2021.findings.xml
index 341626a997..46523985a2 100644
--- a/data/xml/2021.findings.xml
+++ b/data/xml/2021.findings.xml
@@ -735,6 +735,7 @@
10.18653/v1/2021.findings-acl.49
fei-etal-2021-better
scofield7419/hesyfu
+ CoNLL
CoNLL-2012
OntoNotes 5.0
@@ -9588,6 +9589,7 @@
10.18653/v1/2021.findings-emnlp.204
Adverse Drug Events (ADE) Corpus
+ CoNLL
CoNLL04
DocRED
New York Times Annotated Corpus
@@ -9822,6 +9824,7 @@
ACE 2004
AIDA CoNLL-YAGO
AQUAINT
+ CoNLL
KILT
YAGO
@@ -11433,6 +11436,7 @@
10.18653/v1/2021.findings-emnlp.328
megagonlabs/coop
+ Yelp
Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
diff --git a/data/xml/2021.iwslt.xml b/data/xml/2021.iwslt.xml
index 2232a8db99..a38c70e558 100644
--- a/data/xml/2021.iwslt.xml
+++ b/data/xml/2021.iwslt.xml
@@ -122,7 +122,6 @@
bytedance/neurst
LibriSpeech
MuST-C
- TED-LIUM 3
<fixed-case>THE</fixed-case> <fixed-case>IWSLT</fixed-case> 2021 <fixed-case>BUT</fixed-case> <fixed-case>SPEECH</fixed-case> <fixed-case>TRANSLATION</fixed-case> <fixed-case>SYSTEMS</fixed-case>
@@ -183,6 +182,7 @@
inaguma-etal-2021-espnet
LibriSpeech
MuST-C
+ TED-LIUM
End-to-End Speech Translation with Pre-trained Models and Adapters: <fixed-case>UPC</fixed-case> at <fixed-case>IWSLT</fixed-case> 2021
@@ -235,7 +235,6 @@
How2
LibriSpeech
MuST-C
- TED-LIUM 3
<fixed-case>FST</fixed-case>: the <fixed-case>FAIR</fixed-case> Speech Translation System for the <fixed-case>IWSLT</fixed-case>21 Multilingual Shared Task
diff --git a/data/xml/2021.naacl.xml b/data/xml/2021.naacl.xml
index 48ad8a8d91..e285a0f27e 100644
--- a/data/xml/2021.naacl.xml
+++ b/data/xml/2021.naacl.xml
@@ -6603,6 +6603,7 @@
liu-etal-2021-neural
thunlp/VERNet
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
FCE
JFLEG
diff --git a/data/xml/2021.ranlp.xml b/data/xml/2021.ranlp.xml
index bb7d9cb690..f8b59a27dd 100644
--- a/data/xml/2021.ranlp.xml
+++ b/data/xml/2021.ranlp.xml
@@ -1884,6 +1884,7 @@
Nowadays, social media platforms use classification models to cope with hate speech and abusive language. The problem of these models is their vulnerability to bias. A prevalent form of bias in hate speech and abusive language datasets is annotator bias caused by the annotator’s subjective perception and the complexity of the annotation task. In our paper, we develop a set of methods to measure annotator bias in abusive language datasets and to identify different perspectives on abusive language. We apply these methods to four different abusive language datasets. Our proposed approach supports annotation processes of such datasets and future research addressing different perspectives on the perception of abusive language.
2021.ranlp-1.170
wich-etal-2021-investigating
+ mawic/annotator-bias-abusive-language
Rules Ruling Neural Networks - Neural vs. Rule-Based Grammar Checking for a Low Resource Language
diff --git a/data/xml/2022.acl.xml b/data/xml/2022.acl.xml
index d8964b9bd7..0b2ef6ad26 100644
--- a/data/xml/2022.acl.xml
+++ b/data/xml/2022.acl.xml
@@ -1103,6 +1103,7 @@
tricktreat/piqn
ACE 2004
ACE 2005
+ CoNLL
CoNLL 2003
Few-NERD
GENIA
@@ -5442,6 +5443,7 @@ in the Case of Unambiguous Gender
thunlp/pl-marker
ACE 2004
ACE 2005
+ CoNLL
CoNLL 2003
Few-NERD
OntoNotes 5.0
@@ -6891,6 +6893,7 @@ in the Case of Unambiguous Gender
JiachengLi1995/UCTopic
BC5CDR
CoNLL 2003
+ Google Local review
KP20k
KPTimes
WNUT 2017
@@ -7903,6 +7906,7 @@ in the Case of Unambiguous Gender
syuoni/eznlp
ACE 2004
ACE 2005
+ CoNLL
CoNLL 2003
CoNLL++
MSRA CN NER
diff --git a/data/xml/2022.coling.xml b/data/xml/2022.coling.xml
index c88dee98e8..77caed8c06 100644
--- a/data/xml/2022.coling.xml
+++ b/data/xml/2022.coling.xml
@@ -2548,6 +2548,7 @@
2022.coling-1.191
wang-etal-2022-mrc
shannonai/mrc-srl
+ CoNLL
OntoNotes 5.0
@@ -4948,6 +4949,7 @@
2022.coling-1.370
zhang-etal-2022-semantic
yzhangcs/crfsrl
+ CoNLL
CoNLL-2012
OntoNotes 5.0
diff --git a/data/xml/2022.findings.xml b/data/xml/2022.findings.xml
index ad968a6154..8ce376c705 100644
--- a/data/xml/2022.findings.xml
+++ b/data/xml/2022.findings.xml
@@ -1066,6 +1066,7 @@
cgraywang/deepstruct
ACE 2005
ATIS
+ CoNLL
CoNLL 2003
CoNLL++
CoNLL04
diff --git a/data/xml/2022.iwslt.xml b/data/xml/2022.iwslt.xml
index 28d386c363..136e4f4886 100644
--- a/data/xml/2022.iwslt.xml
+++ b/data/xml/2022.iwslt.xml
@@ -199,6 +199,7 @@
LibriSpeech
MuST-C
OpenSubtitles
+ TED-LIUM
VoxPopuli
@@ -358,7 +359,6 @@
wang-etal-2022-hw
10.18653/v1/2022.iwslt-1.20
LibriSpeech
- TED-LIUM 3
The <fixed-case>HW</fixed-case>-<fixed-case>TSC</fixed-case>’s Simultaneous Speech Translation System for <fixed-case>IWSLT</fixed-case> 2022 Evaluation
@@ -380,7 +380,6 @@
wang-etal-2022-hw-tscs
10.18653/v1/2022.iwslt-1.21
LibriSpeech
- TED-LIUM 3
<fixed-case>MLLP</fixed-case>-<fixed-case>VRAIN</fixed-case> <fixed-case>UPV</fixed-case> systems for the <fixed-case>IWSLT</fixed-case> 2022 Simultaneous Speech Translation and Speech-to-Speech Translation tasks
@@ -472,7 +471,6 @@
guo-etal-2022-hw
10.18653/v1/2022.iwslt-1.26
LibriSpeech
- TED-LIUM 3
<fixed-case>CMU</fixed-case>’s <fixed-case>IWSLT</fixed-case> 2022 Dialect Speech Translation System
diff --git a/data/xml/2022.lrec.xml b/data/xml/2022.lrec.xml
index 3b170fcff8..31c02f361e 100644
--- a/data/xml/2022.lrec.xml
+++ b/data/xml/2022.lrec.xml
@@ -9553,6 +9553,7 @@
2022.lrec-1.772
tian-etal-2022-syntax
synlp/srl-mm
+ CoNLL
OntoNotes 5.0
diff --git a/data/xml/2022.naacl.xml b/data/xml/2022.naacl.xml
index e4bc0a1e5e..d2d2d3891b 100644
--- a/data/xml/2022.naacl.xml
+++ b/data/xml/2022.naacl.xml
@@ -3383,6 +3383,7 @@
ACE 2004
AIDA CoNLL-YAGO
AQUAINT
+ CoNLL
DocRED
@@ -3870,6 +3871,7 @@
ACE 2004
AIDA CoNLL-YAGO
AQUAINT
+ CoNLL
Clues Before Answers: Generation-Enhanced Multiple-Choice <fixed-case>QA</fixed-case>
@@ -5463,7 +5465,7 @@
2022.naacl-main.332
verma-etal-2022-chai
10.18653/v1/2022.naacl-main.332
- siddharthverma314/chai-naacl-2022
+ siddharthverma314/chai-naacl-2022
Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer
@@ -8409,6 +8411,7 @@
ACE 2004
AIDA CoNLL-YAGO
AQUAINT
+ CoNLL
IPM NEL
WebQuestionsSP
diff --git a/data/xml/2022.rocling.xml b/data/xml/2022.rocling.xml
index 61c860874f..4eb324047b 100644
--- a/data/xml/2022.rocling.xml
+++ b/data/xml/2022.rocling.xml
@@ -290,7 +290,6 @@
wu-etal-2022-preliminary
zho
LibriSpeech
- TED-LIUM 3
Clustering Issues in Civil Judgments for Recommending Similar Cases
@@ -522,6 +521,7 @@
2022.rocling-1.42
luo-etal-2022-ynu
zho
+ suntea233/ROCLING-2022
<fixed-case>NERVE</fixed-case> at <fixed-case>ROCLING</fixed-case> 2022 Shared Task: A Comparison of Three Named Entity Recognition Frameworks Based on Language Model and Lexicon Approach
diff --git a/data/xml/C18.xml b/data/xml/C18.xml
index c44572fb27..d8741c2bc9 100644
--- a/data/xml/C18.xml
+++ b/data/xml/C18.xml
@@ -1577,6 +1577,7 @@
Recent advances in language modeling using recurrent neural networks have made it viable to model language as distributions over characters. By learning to predict the next character on the basis of previous characters, such models have been shown to automatically internalize linguistic concepts such as words, sentences, subclauses and even sentiment. In this paper, we propose to leverage the internal states of a trained character language model to produce a novel type of word embedding which we refer to as contextual string embeddings. Our proposed embeddings have the distinct properties that they (a) are trained without any explicit notion of words and thus fundamentally model words as sequences of characters, and (b) are contextualized by their surrounding text, meaning that the same word will have different embeddings depending on its contextual use. We conduct a comparative evaluation against previous embeddings and find that our embeddings are highly useful for downstream tasks: across four classic sequence labeling tasks we consistently outperform the previous state-of-the-art. In particular, we significantly outperform previous work on English and German named entity recognition (NER), allowing us to report new state-of-the-art F1-scores on the CoNLL03 shared task. We release all code and pre-trained language models in a simple-to-use framework to the research community, to enable reproduction of these experiments and application of our proposed embeddings to other tasks: https://github.com/zalandoresearch/flair
C18-1139
akbik-etal-2018-contextual
+ CoNLL
CoNLL 2003
CoNLL-2000
Penn Treebank
@@ -1762,6 +1763,7 @@
lukecq1231/generalized-pooling
MultiNLI
SNLI
+ Yelp
Treat us like the sequences we are: Prepositional Paraphrasing of Noun Compounds using <fixed-case>LSTM</fixed-case>
@@ -1841,6 +1843,7 @@
Neural network approaches to Named-Entity Recognition reduce the need for carefully hand-crafted features. While some features do remain in state-of-the-art systems, lexical features have been mostly discarded, with the exception of gazetteers. In this work, we show that this is unfair: lexical features are actually quite useful. We propose to embed words and entity types into a low-dimensional vector space we train from annotated data produced by distant supervision thanks to Wikipedia. From this, we compute — offline — a feature vector representing each word. When used with a vanilla recurrent neural network model, this representation yields substantial improvements. We establish a new state-of-the-art F1 score of 87.95 on ONTONOTES 5.0, while matching state-of-the-art performance with a F1 score of 91.73 on the over-studied CONLL-2003 dataset.
C18-1161
ghaddar-langlais-2018-robust
+ CoNLL
CoNLL 2003
DBpedia
OntoNotes 5.0
@@ -2887,6 +2890,7 @@
C18-1250
yu-liu-2018-sliced
zepingyu0512/srnn
+ Yelp
Multi-Task Learning for Sequence Tagging: An Empirical Study
diff --git a/data/xml/D11.xml b/data/xml/D11.xml
index 3f3ab018e1..bfaf60b1cd 100644
--- a/data/xml/D11.xml
+++ b/data/xml/D11.xml
@@ -691,6 +691,7 @@
D11-1072
hoffart-etal-2011-robust
AIDA CoNLL-YAGO
+ CoNLL
A Cascaded Classification Approach to Semantic Head Recognition
diff --git a/data/xml/D14.xml b/data/xml/D14.xml
index 502596948b..4ade3a66a9 100644
--- a/data/xml/D14.xml
+++ b/data/xml/D14.xml
@@ -2126,6 +2126,7 @@
D14-1200
10.3115/v1/D14-1200
miwa-sasaki-2014-modeling
+ CoNLL
CoNLL04
diff --git a/data/xml/D17.xml b/data/xml/D17.xml
index 905c0f53f8..3b1d2d0053 100644
--- a/data/xml/D17.xml
+++ b/data/xml/D17.xml
@@ -266,6 +266,7 @@
lee-etal-2017-end
kentonl/e2e-coref
+ CoNLL
CoNLL-2012
OntoNotes 5.0
@@ -2052,6 +2053,7 @@ and the code is available at https://github.com/qizhex/RACE_AR_baselines
marcheggiani-titov-2017-encoding
diegma/neural-dep-srl
+ CoNLL
CoNLL-2009
@@ -2335,6 +2337,7 @@ and the code is available at https://github.com/qizhex/RACE_AR_baselinesNeural networks have shown promising results for relation extraction. State-of-the-art models cast the task as an end-to-end problem, solved incrementally using a local classifier. Yet previous work using statistical models have demonstrated that global optimization can achieve better performances compared to local classification. We build a globally optimized neural model for end-to-end relation extraction, proposing novel LSTM features in order to better learn context representations. In addition, we present a novel method to integrate syntactic information to facilitate global learning, yet requiring little background on syntactic grammars thus being easy to extend. Experimental results show that our proposed model is highly effective, achieving the best performances on two standard benchmarks.
zhang-etal-2017-end
ACE 2005
+ CoNLL
CoNLL04
@@ -3551,6 +3554,7 @@ and efficiency of on-line policy optimization compared to other companion
ACE 2004
AIDA CoNLL-YAGO
AQUAINT
+ CoNLL
<fixed-case>M</fixed-case>in<fixed-case>IE</fixed-case>: Minimizing Facts in Open Information Extraction
@@ -3587,8 +3591,8 @@ and efficiency of on-line policy optimization compared to other companion
10.18653/v1/D17-1280
In domain-specific NER, due to insufficient labeled training data, deep models usually fail to behave normally. In this paper, we proposed a novel Neural Inductive TEaching framework (NITE) to transfer knowledge from existing domain-specific NER models into an arbitrary deep neural network in a teacher-student training manner. NITE is a general framework that builds upon transfer learning and multiple instance learning, which collaboratively not only transfers knowledge to a deep student network but also reduces the noise from teachers. NITE can help deep learning methods to effectively utilize existing resources (i.e., models, labeled and unlabeled data) in a small domain. The experiment resulted on Disease NER proved that without using any labeled data, NITE can significantly boost the performance of a CNN-bidirectional LSTM-CRF NER neural network nearly over 30% in terms of F1-score.
tang-etal-2017-nite
+ NCBI Datasets
NCBI Disease
- NCBI Disease Corpus
Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods
diff --git a/data/xml/D18.xml b/data/xml/D18.xml
index 1aaa19c42a..2d06a8d265 100644
--- a/data/xml/D18.xml
+++ b/data/xml/D18.xml
@@ -326,6 +326,7 @@
10.18653/v1/D18-1020
chen-etal-2018-variational
mingdachen/vsl
+ CoNLL
CoNLL 2003
@@ -2077,6 +2078,7 @@
10.18653/v1/D18-1153
liu-etal-2018-efficient
LiyuanLucasLiu/LD-Net
+ CoNLL
CoNLL 2003
@@ -2627,6 +2629,7 @@
10.18653/v1/D18-1191
ouchi-etal-2018-span
hiroki13/span-based-srl
+ CoNLL
OntoNotes 5.0
@@ -2891,6 +2894,7 @@
shen-etal-2018-learning
DBpedia
WikiQA
+ Yelp
Deep Relevance Ranking Using Enhanced Document-Query Interactions
@@ -2983,6 +2987,7 @@
clark-etal-2018-semi
CCGbank
+ CoNLL
CoNLL 2003
OntoNotes 5.0
Penn Treebank
@@ -3831,6 +3836,7 @@
10.18653/v1/D18-1274
chollampatt-ng-2018-neural
nusnlp/neuqe
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
FCE
JFLEG
@@ -3902,6 +3908,7 @@
Character-based neural models have recently proven very useful for many NLP tasks. However, there is a gap of sophistication between methods for learning representations of sentences and words. While, most character models for learning representations of sentences are deep and complex, models for learning representations of words are shallow and simple. Also, in spite of considerable research on learning character embeddings, it is still not clear which kind of architecture is the best for capturing character-to-word representations. To address these questions, we first investigate the gaps between methods for learning word and sentence representations. We conduct detailed experiments and comparisons on different state-of-the-art convolutional models, and also investigate the advantages and disadvantages of their constituents. Furthermore, we propose IntNet, a funnel-shaped wide convolutional neural architecture with no down-sampling for learning representations of the internal structure of words by composing their characters from limited, supervised training corpora. We evaluate our proposed model on six sequence labeling datasets, including named entity recognition, part-of-speech tagging, and syntactic chunking. Our in-depth analysis shows that IntNet significantly outperforms other character embedding models and obtains new state-of-the-art performance without relying on any external knowledge or resources.
10.18653/v1/D18-1279
xin-etal-2018-learning
+ CoNLL
CoNLL 2003
Penn Treebank
@@ -4277,6 +4284,7 @@
bekou/multihead_joint_entity_relation_extraction
ACE 2004
Adverse Drug Events (ADE) Corpus
+ CoNLL
CoNLL04
@@ -4319,6 +4327,7 @@
10.18653/v1/D18-1310
wu-etal-2018-evaluating
minghao-wu/CRF-AE
+ CoNLL
CoNLL 2003
@@ -7575,6 +7584,7 @@
10.18653/v1/D18-1548
strubell-etal-2018-linguistically
strubell/LISA
+ CoNLL
CoNLL-2012
diff --git a/data/xml/D19.xml b/data/xml/D19.xml
index 3b0a80a8a8..bf538d90f9 100644
--- a/data/xml/D19.xml
+++ b/data/xml/D19.xml
@@ -88,6 +88,7 @@
peters-etal-2019-knowledge
allenai/kb
AIDA CoNLL-YAGO
+ CoNLL
SemEval-2010 Task-8
TACRED
WiC
@@ -401,6 +402,7 @@
yang-etal-2019-learning
YoungXiyuan/DCA
AIDA CoNLL-YAGO
+ CoNLL
Open Event Extraction from Online Text using a Generative Adversarial Network
@@ -1089,6 +1091,7 @@
10.18653/v1/D19-1077
wu-dredze-2019-beto
shijie-wu/crosslingual-nlp
+ CoNLL
CoNLL 2002
MLDoc
XNLI
@@ -1672,6 +1675,7 @@
10.18653/v1/D19-1119
kiyono-etal-2019-empirical
butsugiri/gec-pseudodata
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
JFLEG
WI-LOCNESS
@@ -5090,6 +5094,7 @@
10.18653/v1/D19-1367
jiang-etal-2019-improved
jiangyingjunn/i-darts
+ CoNLL
CoNLL 2003
PTB Diagnostic ECG Database
@@ -5527,6 +5532,7 @@
10.18653/v1/D19-1399
jie-lu-2019-dependency
allanj/ner_with_dependency
+ CoNLL
CoNLL 2003
OntoNotes 5.0
@@ -5620,6 +5626,7 @@
D19-1406
10.18653/v1/D19-1406
tikhonov-etal-2019-style
+ Yelp
Yelp Review Polarity
@@ -5769,6 +5776,7 @@
AG News
DBpedia
Yahoo! Answers
+ Yelp
Don’t Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases
@@ -6029,6 +6037,7 @@
D19-1435.Attachment.pdf
10.18653/v1/D19-1435
awasthi-etal-2019-parallel
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
JFLEG
@@ -7189,6 +7198,7 @@
wang-etal-2019-crossweigh
ZihanWangKi/CrossWeigh
CoNLL++
+ CoNLL
CoNLL 2003
WNUT 2017
@@ -7482,6 +7492,7 @@
D19-1539
10.18653/v1/D19-1539
baevski-etal-2019-cloze
+ CoNLL
CoNLL 2003
GLUE
MRPC
@@ -8161,6 +8172,7 @@
10.18653/v1/D19-1588
joshi-etal-2019-bert
mandarjoshi90/coref
+ CoNLL
CoNLL-2012
GAP Coreference Dataset
OntoNotes 5.0
diff --git a/data/xml/E17.xml b/data/xml/E17.xml
index 169fb1720d..7f30040ccb 100644
--- a/data/xml/E17.xml
+++ b/data/xml/E17.xml
@@ -2076,6 +2076,7 @@
DBpedia
YFCC100M
Yahoo! Answers
+ Yelp
Pulling Out the Stops: Rethinking Stopword Removal for Topic Models
diff --git a/data/xml/K16.xml b/data/xml/K16.xml
index 374436a831..7b0a012cfc 100644
--- a/data/xml/K16.xml
+++ b/data/xml/K16.xml
@@ -284,6 +284,7 @@
10.18653/v1/K16-1025
yamada-etal-2016-joint
AIDA CoNLL-YAGO
+ CoNLL
TAC 2010
diff --git a/data/xml/K18.xml b/data/xml/K18.xml
index eea5560d7a..e95b12d41e 100644
--- a/data/xml/K18.xml
+++ b/data/xml/K18.xml
@@ -635,6 +635,7 @@
kolitsas-etal-2018-end
dalab/end2end_neural_el
AIDA CoNLL-YAGO
+ CoNLL
IPM NEL
diff --git a/data/xml/K19.xml b/data/xml/K19.xml
index 85cf92a38c..8c8d8caf0c 100644
--- a/data/xml/K19.xml
+++ b/data/xml/K19.xml
@@ -835,6 +835,7 @@
broscheit-2019-investigating
samuelbroscheit/entity_knowledge_in_bert
AIDA CoNLL-YAGO
+ CoNLL
GLUE
SWAG
@@ -1345,6 +1346,7 @@
K19-2002.Attachment.zip
10.18653/v1/K19-2002
hershcovich-arviv-2019-tupa
+ CoNLL
The <fixed-case>ERG</fixed-case> at <fixed-case>MRP</fixed-case> 2019: Radically Compositional Semantic Dependencies
@@ -1414,6 +1416,7 @@
K19-2007.Attachment.pdf
10.18653/v1/K19-2007
che-etal-2019-hit
+ CoNLL
<fixed-case>SJTU</fixed-case> at <fixed-case>MRP</fixed-case> 2019: A Transition-Based Multi-Task Parser for Cross-Framework Meaning Representation Parsing
diff --git a/data/xml/L16.xml b/data/xml/L16.xml
index 397ff95d1c..e21d23cab4 100644
--- a/data/xml/L16.xml
+++ b/data/xml/L16.xml
@@ -6376,7 +6376,7 @@
We present the first version of a corpus annotated for psychiatric disorders and their etiological factors. The paper describes the choice of text, annotated entities and events/relations as well as the annotation scheme and procedure applied. The corpus is featuring a selection of focus psychiatric disorders including depressive disorder, anxiety disorder, obsessive-compulsive disorder, phobic disorders and panic disorder. Etiological factors for these focus disorders are widespread and include genetic, physiological, sociological and environmental factors among others. Etiological events, including annotated evidence text, represent the interactions between their focus disorders and their etiological factors. Additionally to these core events, symptomatic and treatment events have been annotated. The current version of the corpus includes 175 scientific abstracts. All entities and events/relations have been manually annotated by domain experts and scores of inter-annotator agreement are presented. The aim of the corpus is to provide a first gold standard to support the development of biomedical text mining applications for the specific area of mental disorders which belong to the main contributors to the contemporary burden of disease.
L16-1590
ellendorff-etal-2016-psymine
- NCBI Disease Corpus
+ NCBI Datasets
An Empirical Exploration of Moral Foundations Theory in Partisan News Sources
diff --git a/data/xml/N16.xml b/data/xml/N16.xml
index a345f0aaf5..aa20ca43a4 100644
--- a/data/xml/N16.xml
+++ b/data/xml/N16.xml
@@ -356,6 +356,7 @@
10.18653/v1/N16-1030
lample-etal-2016-neural
glample/tagger
+ CoNLL
CoNLL 2003
CoNLL++
diff --git a/data/xml/N18.xml b/data/xml/N18.xml
index d469910e03..fa3c74be44 100644
--- a/data/xml/N18.xml
+++ b/data/xml/N18.xml
@@ -761,6 +761,7 @@
junczys-dowmunt-etal-2018-approaching
grammatical/neural-naacl2018
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
FCE
JFLEG
@@ -1224,6 +1225,7 @@
10.18653/v1/N18-1089
yasunaga-etal-2018-robust
michiyasunaga/pos_adv
+ CoNLL
CoNLL 2003
CoNLL-2000
Penn Treebank
@@ -2271,6 +2273,7 @@
radhakrishnan-etal-2018-elden
AIDA CoNLL-YAGO
+ CoNLL
Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions
@@ -2301,6 +2304,7 @@
li-etal-2018-delete
lijuncen/Sentiment-and-Style-Transfer
GYAFC
+ Yelp
Yelp2018
@@ -2735,6 +2739,7 @@
peters-etal-2018-deep
ACL ARC
+ CoNLL
CoNLL 2003
CoNLL++
OCW
@@ -3370,6 +3375,7 @@
10.18653/v1/N18-2046
grundkiewicz-junczys-dowmunt-2018-near
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
JFLEG
@@ -4169,6 +4175,7 @@
lee-etal-2018-higher
kentonl/e2e-coref
+ CoNLL
CoNLL-2012
OntoNotes 5.0
@@ -4280,6 +4287,7 @@
N18-2117
10.18653/v1/N18-2117
al-hanai-etal-2018-role
+ TED-LIUM
Slot-Gated Modeling for Joint Slot Filling and Intent Prediction
diff --git a/data/xml/N19.xml b/data/xml/N19.xml
index fb0bb93939..9ac30aa2a4 100644
--- a/data/xml/N19.xml
+++ b/data/xml/N19.xml
@@ -205,6 +205,7 @@
zhao-etal-2019-improving
zhawe01/fairseq-gec
Billion Word Benchmark
+ CoNLL
CoNLL-2014 Shared Task: Grammatical Error Correction
FCE
JFLEG
@@ -5556,6 +5557,7 @@
adhikari-etal-2019-rethinking
IMDB-MULTI
Reuters-21578
+ Yelp
Pre-trained language model representations for language generation
@@ -5777,6 +5779,7 @@
google-research/bert
CPED
CoLA
+ CoNLL
CoNLL 2003
CoQA
DBpedia
diff --git a/data/xml/P16.xml b/data/xml/P16.xml
index 45cd71b02e..8c0b12fd3e 100644
--- a/data/xml/P16.xml
+++ b/data/xml/P16.xml
@@ -1139,6 +1139,7 @@
10.18653/v1/P16-1101
ma-hovy-2016-end
+ CoNLL
CoNLL 2003
CoNLL++
Penn Treebank
@@ -1260,6 +1261,7 @@
P16-1112
10.18653/v1/P16-1112
rei-yannakoudakis-2016-compositional
+ CoNLL
FCE
@@ -1271,6 +1273,7 @@
10.18653/v1/P16-1113
roth-lapata-2016-neural
microth/PathLSTM
+ CoNLL
CoNLL-2009
@@ -2586,6 +2589,7 @@
P16-1228.Notes.pdf
hu-etal-2016-harnessing
+ CoNLL
CoNLL 2003
SST
SST-2
diff --git a/data/xml/P17.xml b/data/xml/P17.xml
index dae14c93c3..afa964dff4 100644
--- a/data/xml/P17.xml
+++ b/data/xml/P17.xml
@@ -628,6 +628,7 @@ two word-vectors results in a vector that is only a small angle away from the ve
he-etal-2017-deep
luheng/deep_srl
+ CoNLL
OntoNotes 5.0
@@ -744,6 +745,7 @@ two word-vectors results in a vector that is only a small angle away from the ve
johnson-zhang-2017-deep
AG News
DBpedia
+ Yelp
Improved Neural Relation Detection for Knowledge Base Question Answering
@@ -1292,6 +1294,7 @@ two word-vectors results in a vector that is only a small angle away from the ve
iyer-etal-2017-learning
ATIS
IMDb Movie Reviews
+ Yelp
Joint Modeling of Content and Discourse Relations in Dialogues
@@ -2253,6 +2256,7 @@ two word-vectors results in a vector that is only a small angle away from the ve
Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representations to produce context sensitive representations is trained on relatively little labeled data. In this paper, we demonstrate a general semi-supervised approach for adding pretrained context embeddings from bidirectional language models to NLP systems and apply it to sequence labeling tasks. We evaluate our model on two standard datasets for named entity recognition (NER) and chunking, and in both cases achieve state of the art results, surpassing previous systems that use other forms of transfer or joint learning with additional labeled data and task specific gazetteers.
peters-etal-2017-semi
+ CoNLL
CoNLL 2003
@@ -2716,6 +2720,7 @@ two word-vectors results in a vector that is only a small angle away from the ve
We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset. This language modeling objective incentivises the system to learn general-purpose patterns of semantic and syntactic composition, which are also useful for improving accuracy on different sequence labeling tasks. The architecture was evaluated on a range of datasets, covering the tasks of error detection in learner texts, named entity recognition, chunking and POS-tagging. The novel language modeling objective provided consistent performance improvements on every benchmark, without requiring any additional annotated or unannotated data.
rei-2017-semi
marekrei/sequence-labeler
+ CoNLL
CoNLL 2003
FCE
Penn Treebank
diff --git a/data/xml/P18.xml b/data/xml/P18.xml
index 88205c5934..30390d5d12 100644
--- a/data/xml/P18.xml
+++ b/data/xml/P18.xml
@@ -483,6 +483,7 @@
P18-1030.Poster.pdf
10.18653/v1/P18-1030
zhang-etal-2018-sentence
+ CoNLL
CoNLL 2003
IMDb Movie Reviews
MR
@@ -504,6 +505,7 @@
IMDb Movie Reviews
WikiText-103
WikiText-2
+ Yelp
Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement
@@ -538,6 +540,7 @@
ATIS
IMDb Movie Reviews
WikiSQL
+ Yelp
Semantic Parsing with Syntax- and Table-Aware <fixed-case>SQL</fixed-case> Generation
@@ -664,6 +667,7 @@
shen-etal-2018-baseline
dinghanshen/SWEM
AG News
+ CoNLL
CoNLL 2003
CoNLL-2000
DBpedia
@@ -677,6 +681,7 @@
SUBJ
WikiQA
Yahoo! Answers
+ Yelp
<fixed-case>P</fixed-case>ara<fixed-case>NMT</fixed-case>-50<fixed-case>M</fixed-case>: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations
@@ -1219,6 +1224,7 @@
prabhumoye-etal-2018-style
shrimai/Style-Transfer-Through-Back-Translation
GYAFC
+ Yelp
Generating Fine-Grained Open Vocabulary Entity Type Descriptions
@@ -1375,6 +1381,7 @@
xu-etal-2018-unpaired
lancopku/unpaired-sentiment-translation
GYAFC
+ Yelp
Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference
@@ -3253,6 +3260,7 @@
AG News
DBpedia
Yahoo! Answers
+ Yelp
Joint Embedding of Words and Labels for Text Classification
@@ -3274,6 +3282,7 @@
AG News
DBpedia
Yahoo! Answers
+ Yelp
Neural Sparse Topical Coding
@@ -4397,6 +4406,7 @@
10.18653/v1/P18-2038
ye-ling-2018-hybrid
ZhixiuYe/HSCRF-pytorch
+ CoNLL
CoNLL 2003
@@ -4665,6 +4675,7 @@
10.18653/v1/P18-2058
he-etal-2018-jointly
luheng/lsgn
+ CoNLL
CoNLL-2012
OntoNotes 5.0
@@ -6047,6 +6058,7 @@
10.18653/v1/P18-4013
yang-zhang-2018-ncrf
jiesutd/NCRFpp
+ CoNLL
CoNLL 2003
Penn Treebank
diff --git a/data/xml/P19.xml b/data/xml/P19.xml
index 7df677e1ea..b17c8aab5d 100644
--- a/data/xml/P19.xml
+++ b/data/xml/P19.xml
@@ -877,6 +877,7 @@
P19-1064
10.18653/v1/P19-1064
fei-etal-2019-end
+ CoNLL
CoNLL-2012
OntoNotes 5.0
@@ -904,6 +905,7 @@
P19-1066
10.18653/v1/P19-1066
kantor-globerson-2019-coreference
+ CoNLL
CoNLL-2012
OntoNotes 5.0
@@ -1819,6 +1821,7 @@
li-etal-2019-entity
ACE 2004
ACE 2005
+ CoNLL
CoNLL04
@@ -1955,6 +1958,7 @@
xia-etal-2019-multi
ACE 2004
ACE 2005
+ CoNLL
CoNLL 2003
@@ -2667,6 +2671,7 @@
le-titov-2019-boosting
lephong/wnel
AIDA CoNLL-YAGO
+ CoNLL
Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following
@@ -3344,6 +3349,7 @@
10.18653/v1/P19-1233
liu-etal-2019-gcdt
Adaxry/GCDT
+ CoNLL
CoNLL 2003
@@ -4256,6 +4262,7 @@
10.18653/v1/P19-1299
chen-etal-2019-multi-source
microsoft/Multilingual-Model-Transfer
+ CoNLL
Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models
@@ -7440,6 +7447,7 @@
10.18653/v1/P19-1524
liu-etal-2019-towards
lyutyuh/acl19_subtagger
+ CoNLL
CoNLL 2003
OntoNotes 5.0
@@ -7478,6 +7486,7 @@
strakova-etal-2019-neural
ACE 2004
ACE 2005
+ CoNLL
CoNLL 2002
CoNLL 2003
GENIA
@@ -7545,6 +7554,7 @@
P19-1532
10.18653/v1/P19-1532
liu-etal-2019-prism
+ CoNLL
CoNLL 2003
@@ -9611,6 +9621,7 @@
10.18653/v1/P19-2026
martins-etal-2019-joint
AIDA CoNLL-YAGO
+ CoNLL
CoNLL 2003
diff --git a/data/xml/Q16.xml b/data/xml/Q16.xml
index dd1f84fb1f..eec0a814ad 100644
--- a/data/xml/Q16.xml
+++ b/data/xml/Q16.xml
@@ -327,6 +327,7 @@
Q16-1026
chiu-nichols-2016-named
+ CoNLL
CoNLL 2003
DBpedia
OntoNotes 5.0
diff --git a/data/xml/Q17.xml b/data/xml/Q17.xml
index af092ee261..5608fcd500 100644
--- a/data/xml/Q17.xml
+++ b/data/xml/Q17.xml
@@ -392,6 +392,7 @@
yamada-etal-2017-learning
studio-ousia/ntee
AIDA CoNLL-YAGO
+ CoNLL
SICK
TAC 2010
diff --git a/data/xml/S14.xml b/data/xml/S14.xml
index bd5db1a7ab..3708e5a45b 100644
--- a/data/xml/S14.xml
+++ b/data/xml/S14.xml
@@ -469,7 +469,7 @@
S14-2019
10.3115/v1/S14-2019
matos-etal-2014-bioinformaticsua
- NCBI Disease Corpus
+ NCBI Datasets
<fixed-case>B</fixed-case>linov: Distributed Representations of Words for Aspect-Based Sentiment Analysis at <fixed-case>S</fixed-case>em<fixed-case>E</fixed-case>val 2014
diff --git a/data/xml/W12.xml b/data/xml/W12.xml
index 2ef3347f30..aee10efe94 100644
--- a/data/xml/W12.xml
+++ b/data/xml/W12.xml
@@ -3437,7 +3437,6 @@
91–99
W12-2411
islamaj-dogan-lu-2012-improved
- NCBI Disease Corpus
New Resources and Perspectives for Biomedical Event Extraction
diff --git a/data/xml/W14.xml b/data/xml/W14.xml
index 2bafba5936..ce6666d790 100644
--- a/data/xml/W14.xml
+++ b/data/xml/W14.xml
@@ -6029,8 +6029,8 @@
W14-3404
10.3115/v1/W14-3404
leaman-lu-2014-automated
+ NCBI Datasets
NCBI Disease
- NCBI Disease Corpus
Decomposing Consumer Health Questions
diff --git a/data/xml/W17.xml b/data/xml/W17.xml
index bf834b9796..c30c213c61 100644
--- a/data/xml/W17.xml
+++ b/data/xml/W17.xml
@@ -9875,6 +9875,7 @@ is able to handle phenomena related to scope by means of an higher-order type th
10.18653/v1/W17-5004
We investigate the utility of different auxiliary objectives and training strategies within a neural sequence labeling approach to error detection in learner writing. Auxiliary costs provide the model with additional linguistic information, allowing it to learn general-purpose compositional features that can then be exploited for other objectives. Our experiments show that a joint learning approach trained with parallel labels on in-domain data improves performance over the previous best error detection system. While the resulting model has the same number of parameters, the additional objectives allow it to be optimised more efficiently and achieve better performance.
rei-yannakoudakis-2017-auxiliary
+ CoNLL
CoNLL 2003
FCE
@@ -10206,6 +10207,7 @@ is able to handle phenomena related to scope by means of an higher-order type th
10.18653/v1/W17-5032
Shortage of available training data is holding back progress in the area of automated error detection. This paper investigates two alternative methods for artificially generating writing errors, in order to create additional resources. We propose treating error generation as a machine translation task, where grammatically correct text is translated to contain errors. In addition, we explore a system for extracting textual patterns from an annotated corpus, which can then be used to insert errors into grammatically correct sentences. Our experiments show that the inclusion of artificially generated errors significantly improves error detection accuracy on both FCE and CoNLL 2014 datasets.
rei-etal-2017-artificial
+ CoNLL
FCE
diff --git a/data/xml/W18.xml b/data/xml/W18.xml
index 780f93653c..b1383c162a 100644
--- a/data/xml/W18.xml
+++ b/data/xml/W18.xml
@@ -10969,7 +10969,7 @@
tourille-etal-2018-evaluation
strayMat/bio-medical_ner
CoNLL 2003
- NCBI Disease Corpus
+ NCBI Datasets
Learning to Summarize Radiology Findings
diff --git a/data/xml/W19.xml b/data/xml/W19.xml
index 70071e390d..e15fa497a6 100644
--- a/data/xml/W19.xml
+++ b/data/xml/W19.xml
@@ -14138,6 +14138,7 @@ One of the references was wrong therefore it is corrected to cite the appropriat
W19-5945
10.18653/v1/W19-5945
keizer-etal-2019-user
+ skeizer/madrigal
Dialogue Act Classification in Team Communication for Robot Assisted Disaster Response