https://www.2022.aclweb.org/_files/ugd/705d57_a48dbdbe56ec4951a2a050193090adec.pdf
一、命名实体识别
1、An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity Recognition
2、Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks
3、Boundary Smoothing for Named Entity Recognition
4、CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
5、Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning
6、Few-Shot Class-Incremental Learning for Named Entity Recognition
7、Few-shot Named Entity Recognition with Self-describing Networks
8、MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective
9、Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing
10、Nested Named Entity Recognition with Span-level Graphs
11、Parallel Instance Query Network for Named Entity Recognition
12、Cross-domain Named Entity Recognition via Graph Matching
13、Cross-Lingual UMLS Named Entity Linking using UMLS Dictionary Fine-Tuning
14、Decomposed Meta-Learning for Few-Shot Named Entity Recognition
15、Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training
16、Extracting Person Names from User Generated Text: Named-Entity Recognition for Combating Human Trafficking
17、Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition
18、Label Semantics for Few Shot Named Entity Recognition
19、Learn and Review: Enhancing Continual Named Entity Recognition via Reviewing Synthetic Samples
20、Thai Nested Named Entity Recognition Corpus
21、Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition
21、De-Bias for Generative Extraction in Unified NER Task
22、Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
23、MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER
二、关系抽取
1、Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction
2、Packed Levitated Marker for Entity and Relation Extraction
3、Pre-training to Match for Unified Low-shot Relation Extraction
4、DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction
5、Event-Event Relation Extraction using Probabilistic Box Embedding
6、PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction
7、Consistent Representation Learning for Continual Relation Extraction
8、Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation
9、Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion
10、HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction
11、Improving Relation Extraction through Syntax-induced Pre-training with Dependency Masking
12、A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction
13、Encoding and Fusing Semantic Connection and Linguistic Evidence for Implicit Discourse Relation Recognition
14、RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction
三、知识图谱
1、CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion
2、Efficient Hyper-parameter Search for Knowledge Graph Embedding
3、Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs
4、KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering
5、Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment
6、RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion
7、Sequence-to-Sequence Knowledge Graph Completion and Question Answering
8、SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models
9、Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning
10、C3KG: A Chinese Commonsense Conversation Knowledge Graph
11、Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts
12、Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach
13、Fact-Tree Reasoning for N-ary Question Answering over Knowledge Graphs
14、Implicit Relation Linking for Question Answering over Knowledge Graph
15、Knowledge Graph Embedding by Adaptive Limit Scoring Loss Using Dynamic Weighting Strategy
16、Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference
17、Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems
四、BERT
1、A Closer Look at How Fine-tuning Changes BERT
2、AlephBERT: Language Model Pre-training and Evaluation from Sub-Word to Sentence Leve
3、BERT Learns to Teach: Knowledge Distillation with Meta Learning
4、bert2BERT: Towards Reusable Pretrained Language Models
5、Distributionally Robust Finetuning BERT for Covariate Drift in Spoken Language Understanding
6、Finding Structural Knowledge in Multimodal-BERT
7、Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT
8、Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning
9、KinyaBERT: a Morphology-aware Kinyarwanda Language Model
10、Language-agnostic BERT Sentence Embedding
11、Life after BERT: What do Other Muppets Understand about Language?
12、LinkBERT: Pretraining Language Models with Document Links
13、Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection
14、RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining
15、SkipBERT: Efficient Inference with Shallow Layer Skipping
16、Token Dropping for Efficient BERT Pretraining
17、What does the sea say to the shore? A BERT based DST style approach for speaker to dialogue attribution in novels
18、A Flexible Multi-Task Model for BERT Serving
19、Does BERT Know that the IS-A Relation Is Transitive?
20、When classifying grammatical role, BERT doesn’t care about word order…except when it matters
21、XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding
22、A Graph Enhanced BERT Model for Event Prediction
23、Discontinuous Constituency and BERT: A Case Study of Dutch
24、From BERT’s Point of View: Revealing the Prevailing Contextual Differences
25、Probing BERT’s priors with serial reproduction chains
26、An Isotropy Analysis in the Multilingual BERT Embedding Space
27、Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task
28、Is Whole Word Masking Always Better for Chinese BERT?: Probing on Chinese Grammatical Error Correction
29、MTRec: Multi-Task Learning over BERT for News Recommendation
30、Unsupervised Chinese Word Segmentation with BERT Oriented Probing and Transformation