TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Part-Of-Speech Tagging	ARK	ACE	Acc	93.8	# 1
Chunking	CoNLL 2000	ACE	Exact Span F1	97.0	# 1
Named Entity Recognition	CoNLL 2002 (Dutch)	ACE + document-context	F1	95.5	# 1
Named Entity Recognition	CoNLL 2002 (Dutch)	ACE	F1	94.6	# 2
Named Entity Recognition	CoNLL 2002 (Spanish)	ACE	F1	91.7	# 2
Named Entity Recognition	CoNLL 2002 (Spanish)	ACE + document-context	F1	95.6	# 1
Chunking	CoNLL 2003 (English)	ACE	F1	92.5	# 1
Named Entity Recognition	CoNLL 2003 (English)	ACE + document-context	F1	94.14	# 2
Named Entity Recognition	CoNLL 2003 (English)	ACE	F1	93.64	# 4
Named Entity Recognition	CoNLL 2003 (German)	ACE	F1	87.0	# 3
Named Entity Recognition	CoNLL 2003 (German)	ACE + document-context	F1	88.0	# 1
Chunking	CoNLL 2003 (German)	ACE	F1	95.0	# 1
Named Entity Recognition	CoNLL 2003 (German) Revised	ACE + document-context	F1	91.4	# 1
Named Entity Recognition	CoNLL 2003 (German) Revised	ACE	F1	90.5	# 2
Semantic Dependency Parsing	DM	ACE	In-domain	95.3	# 1
Semantic Dependency Parsing	DM	ACE	Out-of-domain	92.6	# 1
Semantic Dependency Parsing	PAS	ACE	In-domain	95.3	# 1
Semantic Dependency Parsing	PAS	ACE	Out-of-domain	93.9	# 1
Dependency Parsing	Penn Treebank	ACE	UAS	97.2	# 1
Dependency Parsing	Penn Treebank	ACE	LAS	95.7	# 1
Chunking	Penn Treebank	ACE	F1 score	96.9	# 1
Semantic Dependency Parsing	PSD	ACE	In-domain	83.6	# 1
Semantic Dependency Parsing	PSD	ACE	Out-of-domain	83.2	# 1
Part-Of-Speech Tagging	Ritter	ACE	Acc	93.4	# 1
Aspect Extraction	SemEval 2014 Task 4 Sub Task 2	ACE	Laptop (F1)	85.0	# 3
Aspect Extraction	SemEval 2014 Task 4 Sub Task 2	ACE	Restaurant (F1)	89.8	# 1
Aspect Extraction	SemEval 2015 Task 12	ACE	Restaurant (F1)	78.5	# 1
Aspect Extraction	SemEval-2016 Task 5 Subtask 1	ACE	F1	81.2	# 1
Aspect Extraction	SemEval-2016 Task 5 Subtask 1 (Dutch)	ACE	F1	76.7	# 1
Aspect Extraction	SemEval-2016 Task 5 Subtask 1 (Russian)	ACE	F1	76.7	# 1
Aspect Extraction	SemEval-2016 Task 5 Subtask 1 (Spanish)	ACE	F1	78.8	# 1
Aspect Extraction	SemEval-2016 Task 5 Subtask 1 (Turkish)	ACE	F1	77.7	# 1
Part-Of-Speech Tagging	Tweebank	ACE	Acc	95.6	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/part-of-speech-tagging-on-ark)](https://paperswithcode.com/sota/part-of-speech-tagging-on-ark?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/chunking-on-conll-2000)](https://paperswithcode.com/sota/chunking-on-conll-2000?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/named-entity-recognition-on-conll-2002-dutch)](https://paperswithcode.com/sota/named-entity-recognition-on-conll-2002-dutch?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/named-entity-recognition-on-conll-2002)](https://paperswithcode.com/sota/named-entity-recognition-on-conll-2002?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/chunking-on-conll-2003-english)](https://paperswithcode.com/sota/chunking-on-conll-2003-english?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/named-entity-recognition-on-conll-2003-german)](https://paperswithcode.com/sota/named-entity-recognition-on-conll-2003-german?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/chunking-on-conll-2003-german)](https://paperswithcode.com/sota/chunking-on-conll-2003-german?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/named-entity-recognition-on-conll-2003-german-1)](https://paperswithcode.com/sota/named-entity-recognition-on-conll-2003-german-1?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/semantic-dependency-parsing-on-dm)](https://paperswithcode.com/sota/semantic-dependency-parsing-on-dm?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/semantic-dependency-parsing-on-pas)](https://paperswithcode.com/sota/semantic-dependency-parsing-on-pas?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/dependency-parsing-on-penn-treebank)](https://paperswithcode.com/sota/dependency-parsing-on-penn-treebank?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/chunking-on-penn-treebank)](https://paperswithcode.com/sota/chunking-on-penn-treebank?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/semantic-dependency-parsing-on-psd)](https://paperswithcode.com/sota/semantic-dependency-parsing-on-psd?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/part-of-speech-tagging-on-ritter)](https://paperswithcode.com/sota/part-of-speech-tagging-on-ritter?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/aspect-extraction-on-semeval-2015-task-12)](https://paperswithcode.com/sota/aspect-extraction-on-semeval-2015-task-12?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/aspect-extraction-on-semeval-2016-task-5)](https://paperswithcode.com/sota/aspect-extraction-on-semeval-2016-task-5?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/aspect-extraction-on-semeval-2016-task-5-2)](https://paperswithcode.com/sota/aspect-extraction-on-semeval-2016-task-5-2?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/aspect-extraction-on-semeval-2016-task-5-3)](https://paperswithcode.com/sota/aspect-extraction-on-semeval-2016-task-5-3?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/aspect-extraction-on-semeval-2016-task-5-1)](https://paperswithcode.com/sota/aspect-extraction-on-semeval-2016-task-5-1?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/aspect-extraction-on-semeval-2016-task-5-4)](https://paperswithcode.com/sota/aspect-extraction-on-semeval-2016-task-5-4?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/part-of-speech-tagging-on-tweebank)](https://paperswithcode.com/sota/part-of-speech-tagging-on-tweebank?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/named-entity-recognition-ner-on-conll-2003)](https://paperswithcode.com/sota/named-entity-recognition-ner-on-conll-2003?p=automated-concatenation-of-embeddings-for-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automated-concatenation-of-embeddings-for-1/aspect-extraction-on-semeval-2014-task-4-sub-1)](https://paperswithcode.com/sota/aspect-extraction-on-semeval-2014-task-4-sub-1?p=automated-concatenation-of-embeddings-for-1)`

Automated Concatenation of Embeddings for Structured Prediction

10 Oct 2020 • Xinyu Wang • Yong Jiang • Nguyen Bach • Tao Wang • Zhongqiang Huang • Fei Huang • Kewei Tu

Pretrained contextualized embeddings are powerful word representations for structured prediction tasks. Recent work found that better word representations can be obtained by concatenating different types of embeddings... (read more)

PDF Abstract

Code

Add Remove Mark official

Alibaba-NLP/ACE official

Tasks

Add Remove

ASPECT EXTRACTION

CHUNKING

DEPENDENCY PARSING

NAMED ENTITY RECOGNITION

NEURAL ARCHITECTURE SEARCH

PART-OF-SPEECH TAGGING

SEMANTIC DEPENDENCY PARSING

STRUCTURED PREDICTION

Results from the Paper

Add Remove

Ranked #1 on Named Entity Recognition on CoNLL 2003 (German) Revised

Get a GitHub badge

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	BENCHMARK
Part-Of-Speech Tagging	ARK	ACE	Acc	93.8	# 1	Compare
Chunking	CoNLL 2000	ACE	Exact Span F1	97.0	# 1	Compare
Named Entity Recognition	CoNLL 2002 (Dutch)	ACE + document-context	F1	95.5	# 1	Compare
Named Entity Recognition	CoNLL 2002 (Dutch)	ACE	F1	94.6	# 2	Compare
Named Entity Recognition	CoNLL 2002 (Spanish)	ACE	F1	91.7	# 2	Compare
Named Entity Recognition	CoNLL 2002 (Spanish)	ACE + document-context	F1	95.6	# 1	Compare
Chunking	CoNLL 2003 (English)	ACE	F1	92.5	# 1	Compare
Named Entity Recognition	CoNLL 2003 (English)	ACE + document-context	F1	94.14	# 2	Compare
Named Entity Recognition	CoNLL 2003 (English)	ACE	F1	93.64	# 4	Compare
Named Entity Recognition	CoNLL 2003 (German)	ACE	F1	87.0	# 3	Compare
Named Entity Recognition	CoNLL 2003 (German)	ACE + document-context	F1	88.0	# 1	Compare
Chunking	CoNLL 2003 (German)	ACE	F1	95.0	# 1	Compare
Named Entity Recognition	CoNLL 2003 (German) Revised	ACE + document-context	F1	91.4	# 1	Compare
Named Entity Recognition	CoNLL 2003 (German) Revised	ACE	F1	90.5	# 2	Compare
Semantic Dependency Parsing	DM	ACE	In-domain	95.3	# 1	Compare
Semantic Dependency Parsing	DM	ACE	Out-of-domain	92.6	# 1	Compare
Semantic Dependency Parsing	PAS	ACE	In-domain	95.3	# 1	Compare
Semantic Dependency Parsing	PAS	ACE	Out-of-domain	93.9	# 1	Compare
Dependency Parsing	Penn Treebank	ACE	UAS	97.2	# 1	Compare
Dependency Parsing	Penn Treebank	ACE	LAS	95.7	# 1	Compare
Chunking	Penn Treebank	ACE	F1 score	96.9	# 1	Compare
Semantic Dependency Parsing	PSD	ACE	In-domain	83.6	# 1	Compare
Semantic Dependency Parsing	PSD	ACE	Out-of-domain	83.2	# 1	Compare
Part-Of-Speech Tagging	Ritter	ACE	Acc	93.4	# 1	Compare
Aspect Extraction	SemEval 2014 Task 4 Sub Task 2	ACE	Laptop (F1)	85.0	# 3	Compare
Aspect Extraction	SemEval 2014 Task 4 Sub Task 2	ACE	Restaurant (F1)	89.8	# 1	Compare
Aspect Extraction	SemEval 2015 Task 12	ACE	Restaurant (F1)	78.5	# 1	Compare
Aspect Extraction	SemEval-2016 Task 5 Subtask 1	ACE	F1	81.2	# 1	Compare
Aspect Extraction	SemEval-2016 Task 5 Subtask 1 (Dutch)	ACE	F1	76.7	# 1	Compare
Aspect Extraction	SemEval-2016 Task 5 Subtask 1 (Russian)	ACE	F1	76.7	# 1	Compare
Aspect Extraction	SemEval-2016 Task 5 Subtask 1 (Spanish)	ACE	F1	78.8	# 1	Compare
Aspect Extraction	SemEval-2016 Task 5 Subtask 1 (Turkish)	ACE	F1	77.7	# 1	Compare
Part-Of-Speech Tagging	Tweebank	ACE	Acc	95.6	# 1	Compare

Methods used in the Paper

Add Remove

METHOD	TYPE
Tanh Activation	Activation Functions
Sigmoid Activation	Activation Functions
Entropy Regularization	Regularization
BPE	Subword Segmentation
SentencePiece	Tokenizers
XLNet	Transformers
CRF	Structured Prediction
Residual Connection	Skip Connections
Weight Decay	Regularization
Attention Dropout	Regularization
Linear Warmup With Linear Decay	Learning Rate Schedules
WordPiece	Subword Segmentation
Adam	Stochastic Optimization
Dropout	Regularization
Dense Connections	Feedforward Networks
GELU	Activation Functions
Multi-Head Attention	Attention Modules
Layer Normalization	Normalization
Scaled Dot-Product Attention	Attention Mechanisms
BERT	Language Models
PPO	Policy Gradient Methods
Softmax	Output Functions
LSTM	Recurrent Neural Networks
Neural Architecture Search	Neural Architecture Search

Automated Concatenation of Embeddings for Structured Prediction

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Results from the Paper Edit Add Remove

Methods used in the Paper Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Results from the Paper

Add Remove

Methods used in the Paper

Add Remove