Search Results for author: Xuansong Li

Found 6 papers, 0 papers with code

Uzbek-English and Turkish-English Morpheme Alignment Corpora

no code implementations LREC 2016 Xuansong Li, Jennifer Tracey, Stephen Grimes, Stephanie Strassel

Morphologically-rich languages pose problems for machine translation (MT) systems, including word-alignment errors, data sparsity and multiple affixes.

Machine Translation Translation +1

Automatic word alignment tools to scale production of manually aligned parallel texts

no code implementations LREC 2012 Stephen Grimes, Katherine Peterson, Xuansong Li

We have been creating large-scale manual word alignment corpora for Arabic-English and Chinese-English language pairs in genres such as newsire, broadcast news and conversation, and web blogs.

Machine Translation Semantic Role Labeling +2

Parallel Aligned Treebanks at LDC: New Challenges Interfacing Existing Infrastructures

no code implementations LREC 2012 Xuansong Li, Stephanie Strassel, Stephen Grimes, Safa Ismael, Mohamed Maamouri, Ann Bies, Nianwen Xue

Parallel aligned treebanks (PAT) are linguistic corpora annotated with morphological and syntactic structures that are aligned at sentence as well as sub-sentence levels.

Machine Translation Sentence +2

Linguistic Resources for Entity Linking Evaluation: from Monolingual to Cross-lingual

no code implementations LREC 2012 Xuansong Li, Stephanie Strassel, Heng Ji, Kira Griffitt, Joe Ellis

To advance information extraction and question answering technologies toward a more realistic path, the U. S. NIST (National Institute of Standards and Technology) initiated the KBP (Knowledge Base Population) task as one of the TAC (Text Analysis Conference) evaluation tracks.

Cross-Lingual Entity Linking Entity Linking +5

Cannot find the paper you are looking for? You can Submit a new open access paper.