LREC 2018

166 papers
The 2018 edition of the Language Resources and Evaluation Conference (LREC) featured 173 papers covering a broad spectrum of natural language processing and resource creation. Key research directions included the dynamic evaluation of large language models, multimodal behavioral and linguistic fusion for social analysis, and the detection of implicit toxicity and propaganda. There was also a focus on scientific literature, specifically regarding automated curation into structured databases and overcoming bottlenecks in scientific language modeling. Notable contributions involved the development of specialized datasets and tools, such as the T-REx alignment of natural language with knowledge base triples and the CATS tool for text simplification corpora. Research also addressed multilingualism and cultural heritage, including the multi-layer annotation of the Rigveda and the coordination of language resources for European public sectors. Prolific contributors to the conference included Nizar Habash, Simone Paolo Ponzetto, and Salam Khalifa. Other prominent themes included stylometric fingerprinting for text attribution and precise span boundary detection in information extraction, reflecting an emphasis on both structural linguistic analysis and practical application in social and educational contexts.

Top Research Directions

Research directions most represented by LREC 2018 papers.

Hybrid Integration of Statistical and Neural Translation Models 1
The Sequential Arrangement of Arguments in Persuasion 1
Quantifying Cognitive States Through Gaze Dynamics 1
Stylometric Deception Detection 1
Real-Time Feedback Loops for Digital Learning 1
Representing Multiword Expressions as Atomic Tokens 1
Multi-Layered Representation of Linguistic Data 1
Fine Grained Semantic Typing for Entity Recognition 1
Extrinsic Data Validation via Downstream Task Benchmarking 1
Iterative Guideline Refinement for Data Annotation 1
Scaling Cross-Lingual Document and Sentence Alignment 1
Harmonizing Syntax with Universal Dependencies Treebanks 1
Joint Sequence Labeling for Pipeline Error Mitigation 1
The Single Annotator Bias in Machine Learning Benchmarks 1
Resolving Zero Anaphora in Pro Drop Languages 1

Top Authors

AuthorPapers
Nizar Habash8
Simone Paolo Ponzetto6
Alexander Panchenko4
Chris Biemann4
Salam Khalifa4
Ahmed Abdelali3
Benoît Sagot3
Danushka Bollegala3
German Rigau3
Lilja Øvrelid3
Rodrigo Agerri3
Wajdi Zaghouani3
Arianna Bisazza2
Ashutosh Modi2
Chengqing Zong2
Christof Monz2
Dan Jurafsky2
David R. Mortensen2
Deniz Zeyrek2
Dima Taji2

Impactful Papers

Papers from LREC 2018 that shaped research clusters.

Influential

Papers

Title
Transfer Learning for Named-Entity Recognition with Neural Networks
Transforming Wikipedia into a Large-Scale Fine-Grained Entity Type Corpus
T-REx: A Large Scale Alignment of Natural Language with Knowledge Base Triples
TSix: A Human-involved-creation Dataset for Tweet Summarization
Unfolding the External Behavior and Inner Affective State of Teammates through Ensemble Learning: Experimental Evidence from a Dyadic Team Corpus
Unified Guidelines and Resources for Arabic Dialect Orthography
UniMorph 2.0: Universal Morphology
Universal Dependencies for Amharic
Universal Dependencies Version 2 for Japanese
Upping the Ante: Towards a Better Benchmark for Chinese-to-English Machine Translation
Visual Choice of Plausible Alternatives: An Evaluation of Image-based Commonsense Causal Reasoning
WASA: A Web Application for Sequence Annotation
When ACE met KBP: End-to-End Evaluation of Knowledge Base Population with Component-level Annotation
Word Embedding Evaluation Datasets and Wikipedia Title Embedding for Chinese
World Knowledge for Abstract Meaning Representation Parsing
WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-hop Inference

« prev Page 4/4