L
Liling Tan
Researcher at Saarland University
Publications - 40
Citations - 674
Liling Tan is an academic researcher from Saarland University. The author has contributed to research in topics: Machine translation & Task (project management). The author has an hindex of 13, co-authored 40 publications receiving 553 citations. Previous affiliations of Liling Tan include Nanyang Technological University.
Papers
More filters
Proceedings ArticleDOI
A Report on the DSL Shared Task 2014
TL;DR: This paper summarizes the methods, results and findings of the Discriminating between Similar Languages (DSL) shared task 2014, where the best system obtained 95.7% average accuracy.
Overview of the DSL Shared Task 2015
TL;DR: The results of the 2 nd edition of the Discriminating between Similar Languages (DSL) shared task, which was organized as part of the LT4VarDial’2015 workshop and focused on the identification of very similar languages and language varieties, are presented.
Posted Content
Lexically Constrained Neural Machine Translation with Levenshtein Transformer
TL;DR: A simple and effective algorithm for incorporating lexical constraints in neural machine translation that leverages the flexibility and speed of a recently proposed Levenshtein Transformer model and injects terminology constraints at inference time without any impact on decoding speed.
Building and Annotating the Linguistically Diverse NTU-MC (NTU - Multilingual Corpus).
Liling Tan,Francis Bond +1 more
TL;DR: The NTU-MC compilation taps on the linguistic diversity of multilingual texts available within Singapore to provide valuable information on linguistic diversity for traditional linguistic research as well as natural language processing tasks.
Proceedings ArticleDOI
Lexically Constrained Neural Machine Translation with Levenshtein Transformer
TL;DR: The authors proposed a simple and effective algorithm for incorporating lexical constraints in neural machine translation, which does not require any modification to the training procedure and can be easily applied at runtime with custom dictionaries.