We propose Seq2Edits, an open-vocabulary approach to sequence editing for
natural language processing (NLP) tasks with a high degree of overlap between
input and output texts. In this approach, each sequence-to-sequence
transduction is represented as a sequence of edit operations, where each
operation either replaces an entire source span with target tokens or keeps it
unchanged. We evaluate our method on five NLP tasks (text normalization,
sentence fusion, sentence splitting & rephrasing, text simplification, and
grammatical error correction) and report competitive results across the board.
For grammatical error correction, our method speeds up inference by up to 5.2x
compared to full sequence models because inference time depends on the number
of edits rather than the number of target tokens. For text normalization,
sentence fusion, and grammatical error correction, our approach improves
explainability by associating each edit operation with a human-readable tag.

Seq2Edits 是一种基于开放词汇的序列编辑方法，适用于自然语言处理 (NLP) 任务，其中每个序列到序列转换表示为一系列编辑操作，用于替换源跨度或保持其不变。该方法在五个 NLP 任务上进行了评估，并在各个方面都取得了有竞争力的结果。其中在语法错误修正方面，与完整序列模型相比，该方法提高了推理速度达 5.2 倍，而推理时间取决于编辑数而不是目标标记数。