Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks

ICLR 2019 Kun XuLingfei WuZhiguo WangYansong FengMichael WitbrockVadim Sheinin

The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form to the appropriate sequence... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
SQL-to-Text WikiSQL Graph2Seq-PGE BLEU-4 38.97 # 1