ACL 2022

1,486 papers

Top Research Directions

Research directions most represented by ACL 2022 papers.

Zero-Shot Cross-Lingual Transfer in Multilingual Language Models 31
Mitigating Data Scarcity in Low Resource Language Processing 31
Why Transformers Struggle with Code Mixed Social Media Text 28
Iterative Retrieval Augmented Generation for Multi Hop Reasoning 17
The Geometry of Embedding Anisotropy 15
Recognizing Nested and Overlapping Named Entities 15
Statistical Term Weighting for Text Vectorization 15
Replacing Abstract Labels with Natural Language Descriptions 15
The Performance Advantage of Localized Language Pretraining 14
Learning from Noisy Distantly Supervised Labels 13
Pointer Generator Mechanisms for Grounded Text Generation 12
The Text to Text Paradigm for Task Unification 12
Enforcing Structural Constraints on Language Model Outputs 12
Compressing Large Foundation Models via Knowledge Distillation 12
Mitigating Cascading Errors in Sequential Processing Pipelines 12

Top Authors

AuthorPapers
Zhiyuan Liu18
Maosong Sun16
Jie Zhou15
Qun Liu12
Chitta Baral9
Daxin Jiang9
Graham Neubig9
Lifeng Shang9
Yue Zhang9
Furu Wei8
Min Zhang8
Xiang Ren8
Yankai Lin8
Anders Søgaard7
Baobao Chang7
Caiming Xiong7
Chenguang Zhu7
Diyi Yang7
Dongyan Zhao7
Ivan Vulić7

Impactful Papers

Papers from ACL 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems
The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study
The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking
The patient is more dead than alive: exploring the current state of the multi-document summarisation of the biomedical literature
The Power of Prompt Tuning for Low-Resource Semantic Parsing
The Pure Poet: How Good is the Subjective Credibility and Stylistic Quality of Literary Short Texts Written with an Artificial Intelligence Tool as Compared to Texts Written by Human Authors?
There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory
There's a Time and Place for Reasoning Beyond the Image
The Trade-offs of Domain Adaptation for Neural Language Models
The USTC-NELSLIP Offline Speech Translation Systems for IWSLT 2022
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption
Things not Written in Text: Exploring Spatial Commonsense from Visual Signals
Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation
TimeLMs: Diachronic Language Models from Twitter
To be or not to be an Integer? Encoding Variables for Mathematical Text
To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo
Token Dropping for Efficient BERT Pretraining
TopWORDS-Seg: Simultaneous Text Segmentation and Word Discovery for Open-Domain Chinese Texts via Bayesian Inference
Toward Annotator Group Bias in Crowdsourcing
Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning
Toward More Effective Human Evaluation for Machine Translation
Toward More Meaningful Resources for Lower-resourced Languages
Towards Abstractive Grounded Summarization of Podcast Transcripts
Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples
Towards Afrocentric NLP for African Languages: Where We Are and Where We Can Go
Towards Better Characterization of Paraphrases
Towards Collaborative Neural-Symbolic Graph Semantic Parsing via Uncertainty
Towards Comprehensive Patent Approval Predictions: Beyond Traditional Document Classification
Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference Resolution
Towards Detecting Political Bias in Hindi News Articles
Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances
Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework
Towards Fine-grained Classification of Climate Change related Social Media Text
Towards Generalizable Methods for Automating Risk Score Calculation
Towards Generalizeable Semantic Product Search by Text Similarity Pre-training on Search Click Logs
Towards Human Evaluation of Mutual Understanding in Human-Computer Spontaneous Conversation: An Empirical Study of Word Sense Disambiguation for Naturalistic Social Dialogs in American English
Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts
Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation
Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding
Towards Reproducible Machine Learning Research in Natural Language Processing
Towards Responsible Natural Language Annotation for the Varieties of Arabic
Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation
Towards Stronger Adversarial Baselines Through Human-AI Collaboration
Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction
Towards Unification of Discourse Annotation Frameworks
Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
Tracing Origins: Coreference-aware Machine Reading Comprehension
Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data

« prev Page 27/30 next »