EMNLP 2018

869 papers

Top Research Directions

Research directions most represented by EMNLP 2018 papers.

Bidirectional Sequence Modeling with Recurrent Neural Networks 20
Filtering Noisy Parallel Corpora for Machine Translation 19
Pointer Generator Mechanisms for Grounded Text Generation 17
Hierarchical Sequence Encoding for Multi Level Text Modeling 15
Parallelizing Recurrent Models via Linear State Transitions 14
Decomposing Context into Multi-Level Attention Hierarchies 14
Inferring Emotional States from Situational Context 14
Back-Translation for Synthetic Data Augmentation 14
Shared Representation Learning via Simultaneous Multi-Task Training 13
Multi-Granular Representation Fusion in Language Models 12
Convolutional Feature Extraction for Text Classification 11
Bridging the Lexical Gap in Information Retrieval 11
Machine Translation Without Massive Parallel Corpora 11
Structural Divergence in Cross-Lingual Embedding Spaces 10
Overcoming Vocabulary Sparsity in Morphologically Rich Languages 10

Top Authors

AuthorPapers
Maosong Sun11
Graham Neubig10
Zhiyuan Liu9
Xu Sun8
Xu Sun8
Kyunghyun Cho7
Chengqing Zong6
Dan Roth6
Heng Ji6
Iryna Gurevych6
Luke Zettlemoyer6
Jiajun Zhang5
Mirella Lapata5
Mohit Bansal5
Wei Lu5
Alexander M Rush4
Anders Søgaard4
Anh Tuan Luu4
Christopher D Manning4
Hao Zhu4

Impactful Papers

Papers from EMNLP 2018 that shaped research clusters.

Foundational

Influential

Papers

Title
Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts
The AFRL-Ohio State WMT18 Multimodal System: Combining Visual with Traditional
The AFRL WMT18 Systems: Ensembling, Continuation and Combination
The Benefit of Pseudo-Reference Translations in Quality Estimation of MT Output
The BQ Corpus: A Large-scale Domain-specific Chinese Corpus For Sentence Semantic Equivalence Identification
The Coptic Universal Dependency Treebank
The Data Challenge in Misinformation Detection: Source Reputation vs. Content Veracity
The Effects of User Features on Twitter Hate Speech Detection
The First Komi-Zyrian Universal Dependencies Treebanks
The glass ceiling in NLP
The Hebrew Universal Dependency Treebank: Past Present and Future
The ILSP/ARC submission to the WMT 2018 Parallel Corpus Filtering Shared Task
The importance of Being Recurrent for Modeling Hierarchical Structure
The Importance of Generation Order in Language Modeling
The Lazy Encoder: A Fine-Grained Analysis of the Role of Morphology in Neural Machine Translation
The Linguistic Ideologies of Deep Abusive Language Classification
The MLLP-UPV German-English Machine Translation System for WMT18
The Remarkable Benefit of User-Level Aggregation for Lexical-based Population-Level Predictions
The Role of Emotions in Native Language Identification
The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task
The Speechmatics Parallel Corpus Filtering System for WMT18
The TALP-UPC Machine Translation Systems for WMT18 News Shared Translation Task
The WMT’18 Morpheval test suites for English-Czech, English-German, English-Finnish and Turkish-English
The Word Sense Disambiguation Test Suite at WMT18
Thread Popularity Prediction and Tracking with a Permutation-invariant Model
Three Strategies to Improve One-to-Many Multilingual Translation
Thumbs Up and Down: Sentiment Analysis of Medical Online Forums
Tilde’s Machine Translation Systems for WMT 2018
Tilde’s Parallel Corpus Filtering Methods for WMT 2018
Time Expressions in Mental Health Records for Symptom Onset Extraction
Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing
Topic Intrusion for Automatic Topic Model Evaluation
Topic Memory Networks for Short Text Classification
Toward Fast and Accurate Neural Discourse Segmentation
Towards a Better Metric for Evaluating Question Generation Systems
Towards Dynamic Computation Graphs via Sparse Latent Structure
Towards Exploiting Background Knowledge for Building Conversation Systems
Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method
Towards Semi-Supervised Learning for Deep Semantic Role Labeling
Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation
Towards Universal Dialogue State Tracking
Toward Universal Dependencies for Shipibo-Konibo
Training and Prediction Data Discrepancies: Challenges of Text Classification with Noisy, Historical Data
Training Deeper Neural Machine Translation Models with Transparent Attention
Training for Diversity in Image Paragraph Captioning
Transfer and Multi-Task Learning for Noun-Noun Compound Interpretation
Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging
Transition-based Parsing with Lighter Feed-Forward Networks
Translating a Math Word Problem to a Expression Tree
Translating Math Word Problem to Expression Tree

« prev Page 16/18 next »