LREC 2020
230 papers
The 2020 edition of the Language Resources and Evaluation Conference (LREC) featured 241 papers focusing on expanding natural language processing capabilities to underserved languages and specialized domains. A primary theme was addressing linguistic inequality, with research dedicated to neural machine translation for low-resource languages and scaling models to the global long tail. Other prominent topics included subword representations for robust language understanding, language-specific pretraining to capture local linguistic nuances, and the development of neural representations for morphologically rich languages.
Contributions included the release of specialized datasets and toolkits, such as MultiWOZ 2.1 for multi-domain dialogue, the ParaPat parallel corpus of patent abstracts, and Seq2SeqPy for sequence-to-sequence modeling. Research also explored orthographic normalization for non-standardized dialects and the processing of physically degraded historical documents. Prolific contributors to this year’s proceedings included Benoît Sagot, Nizar Habash, and Rada Mihalcea. The year's work reflected a trend toward cross-domain sentiment analysis and the creation of domain-specific resources for fields like archaeology and pedagogy.
Top Research Directions
Research directions most represented by LREC 2020 papers.
Top Authors
Impactful Papers
Papers from LREC 2020 that shaped research clusters.
Foundational
Automated Fact-Checking of Claims from Wikipedia
foundational
Decontextualizing Claims for Automated F
The FISKMÖ Project: Resources and Tools for Finnish-Swedish Machine Translation and Cross-Linguistic
foundational
Local CPU Inference for Private Machine
FlauBERT: Unsupervised Language Model Pre-training for French
foundational
Streamlining Pretraining by Removing Nex
Give your Text Representation Models some Love: the Case for Basque
foundational
Overcoming Parameter Dilution with Monol
Give your Text Representation Models some Love: the Case for Basque
foundational
Whole Word Masking for Language Pretrain
Ciron: a New Benchmark Dataset for Chinese Irony Detection
foundational
Benchmarking Deep Learning Against Tradi
The Connection between the Text and Images of News Articles: New Insights for Multimedia Analysis
foundational
Natural Language as a Shared Multimodal
Understanding Spatial Relations through Multiple Modalities
foundational
Specializing Language Models for Spatial
Influential
Building a Multimodal Entity Linking Dataset From Tweets
influential
Synthetic Ambiguity Generation via Monos
A Major Wordnet for a Minority Language: Scottish Gaelic
influential
Representing and Bridging Cross-Lingual
Word Sense Disambiguation for 158 Languages using Word Embeddings Only
influential
Resolving Excessive Granularity in Word
The rJokes Dataset: a Large Scale Humor Collection
influential
Demographic Skew in Platform Sourced Dat
Spatial Multi-Arrangement for Clustering and Multi-way Similarity Dataset Construction
influential
Why Semantic Models Struggle to Process
A Resource for Computational Experiments on Mapudungun
influential
Natural Language Processing for Polysynt
Best Student Forcing: A Simple Training Mechanism in Adversarial Language Generation
influential
Evaluating Text Generation via Distribut
Language-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Predicti
influential
Optimizing Subword Vocabulary Size in La
Cairo Student Code-Switch (CSCS) Corpus: An Annotated Egyptian Arabic-English Corpus
influential
Orthographic Inconsistency in Low Resour
Papers
« prev Page 5/5