ACL 2021 主会571篇长文分类汇总（补充）
-
语音与多模态
PhotoChat: A Human-Human Dialogue Dataset With Photo Sharing Behavior For Joint Image-Text Modeling
Control Image Captioning Spatially and Temporally
Hierarchical Context-aware Network for Dense Video Event Captioning
LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding
Text-Free Image-to-Speech Synthesis Using Learned Segmental Units
A Large-Scale Chinese Multimodal NER Dataset with Speech Clues
MultiMET: A Multimodal Dataset for Metaphor Understanding
HateCheck: Functional Tests for Hate Speech Detection Models
Multi-stage Pre-training over Simplified Multimodal Pre-training Models
CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders
Multimodal Sentiment Detection Based on Multi-channel Graph Neural Networks
Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation
Beyond Sentence-Level End-to-End Speech Translation: Context Helps
Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?
KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation
Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task
Multilingual Speech Translation from Efficient Finetuning of Pretrained Models
E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Self-Supervised Multimodal Opinion Summarization
PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World
QASR: QCRI Aljazeera Speech Resource A Large Scale Annotated Arabic Speech Corpus文本摘要
Improving Factual Consistency of Abstractive Summarization via Question Answering
Long-Span Summarization via Local Attention and Content Selection
RepSum: Unsupervised Dialogue Summarization based on Replacement Strategy
Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization
BASS: Boosting Abstractive Summarization with Unified Semantic Graph
Focus Attention: Promoting Faithfulness and Diversity in Summarization
Deep Differential Amplifier for Extractive Summarization
Generating Query Focused Summaries from Query-Free Resources
PASS: Perturb-and-Select Summarizer for Product Reviews
Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text
Accelerating Text Communication via Abbreviated Sentence Input
ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining
Multi-TimeLine Summarization (MTLS): Improving Timeline Summarization by Generating Multiple Summaries
Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification
EmailSum: Abstractive Email Thread Summarization
Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution语法、标记和解析
How is BERT surprised? Layerwise detection of linguistic anomalies
Syntax-Enhanced Pre-trained Model
PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction
Coreference Reasoning in Machine Reading Comprehension
A Conditional Splitting Framework for Efficient Constituency Parsing
COSY: COunterfactual SYntax for Cross-Lingual Understanding
The Limitations of Limited Context for Constituency Parsing
End-to-End AMR Corefencence Resolution
Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment
Adapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing
ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences
Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models
Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments
Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution
Factuality Assessment as Modal Dependency Parsing
Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding
Benchmarking Scalable Methods for Streaming Cross Document Entity Coreference
Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP
Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction
PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check文本分类
Semi-Supervised Text Classification with Balanced Deep Representation Distributions
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification
Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification
OoMMix: Out-of-manifold Regularization in Contextual Embedding Space for Text Classification
Counterfactual Inference for Text Classification Debiasing
BanditMTL: Bandit-based Multi-task Learning for Text Classification
Label-Specific Dual Graph Neural Network for Multi-Label Text Classification
Optimizing Deeper Transformers on Small Datasets
Hierarchy-aware Label Semantics Matching Network for Hierarchical Text Classification
Supporting Land Reuse of Former Open Pit Mining Sites using Text Classification and Active Learning
Enhancing the generalization for Intent Classification and Out-of-Domain Detection in SLU
Exploring Discourse Structures for Argument Impact Classification
More Identifiable yet Equally Performant Transformers for Text Classification其他
Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach
What is Your Article Based On? Inferring Fine-grained Provenance
Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction