Encode, Tag, Realize: High-Precision Text Editing

IJCNLP 2019 Eric MalmiSebastian KrauseSascha RotheDaniil MirylenkaAliaksei Severyn

We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task. Target texts are reconstructed from the inputs using three main edit operations: keeping a token, deleting it, and adding a phrase before the token... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Sentence Fusion DiscoFuse LaserTaggerAR Exact 53.8 # 1
SARI 85.5 # 1
Split and Rephrase WikiSplit1.0 LaserTaggerAR BLEU score 76.3 # 1
Exact 15.2 # 1
SARI 61.7 # 1