OOIR: Observatory of International Research

Papers

(The H4-Index of Transactions of the Association for Computational Linguistics is 33. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2020-11-01 to 2024-11-01.)

Article	Citations
SpanBERT: Improving Pre-training by Representing and Predicting Spans	641
A Primer in BERTology: What We Know About How BERT Works	441
Multilingual Denoising Pre-training for Neural Machine Translation	348
Topic Modeling in Embedding Spaces	326
How Can We Know What Language Models Know?	313
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation	212
Efficient Content-Based Sparse Attention with Routing Transformers	169
Leveraging Pre-trained Checkpoints for Sequence Generation Tasks	131
What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models	126
SummEval: Re-evaluating Summarization Evaluation	112
Sparse, Dense, and Attentional Representations for Text Retrieval	108
A Survey on Automated Fact-Checking	97
TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages	88
A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation	81
Compressing Large-Scale Transformer-Based Models: A Case Study on BERT	61
Nested Named Entity Recognition via Second-best Sequence Learning and Decoding	61
ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models	59
Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages	51
Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations	50
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond	49
BLiMP: The Benchmark of Linguistic Minimal Pairs for English	47
oLMpics-On What Language Model Pre-training Captures	46
Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP	42
Lost in the Middle: How Language Models Use Long Contexts	42
Measuring and Improving Consistency in Pretrained Language Models	42

Machine Learning–Driven Language Assessment	41
Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation	41
Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs	40
Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers	39
How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering	38
SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization	37
The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation	36
Gender Bias in Machine Translation	35