QuickEdit: Editing Text & Translations by Crossing Words Out
By David Grangier, Michael Auli. 2017
33 citations recorded by the source corpus.
We propose a framework for computer-assisted text editing. It applies to translation post-editing and to paraphrasing. Our proposal relies on very simple interactions: a human editor modifies a sentence by marking tokens they would like the system to change. Our model then generates a new sentence which reformulates the initial sentence by avoiding marked words. The approach builds upon neural sequence-to-sequence modeling and introduces a neural network which takes as input a sentence along with change markers. Our model is trained on translation bitext by simulating post-edits. We demonstrate the advantage of our approach for translation post-editing through simulated post-edits. We also evaluate our model for paraphrasing through a user study.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Graham Neubig
- Jason Aaron Edward Weston
- Jiatao Gu
- Mohit Bansal
- Kyunghyun Cho
- Emily Dinan
- Luke S. Zettlemoyer
- Jianfeng Gao
In Natural Language Processing
- Graham Neubig
- Jason Aaron Edward Weston
- Emily Dinan
- Jiatao Gu
- Kyunghyun Cho
- Mohit Bansal
- Alexander H. Miller
- Luke S. Zettlemoyer
Citations in the corpus
- Retrieve and Refine: Improved Sequence Generation Models For Dialogue (2018, background): “…either for refinement of initial predictions (Junczys-Dowmunt and Grundkiewicz, 2017; Niehues et al., 2016; Novak et al., 2016; Xia et al., 2017; Grangier and Auli, 2017) or combining with retrieval (Gu et al., 2017; Cao et al., 2018), as well as for sentence correction or refinement without…”
- Levenshtein Transformer (2019, methodology): “Dataset We follow a normal protocol in the synthetic APE experiments (Grangier and Auli, 2017): we first train the input MT system on half of the dataset.”
- Control Prefixes for Text Generation (2021, background): “, 2016) or highlighted phrases (Grangier and Auli, 2018) beyond the input text into the generation model.”
- Control Prefixes for Parameter-Efficient Text Generation (2021, background): “, 2016) or highlighted phrases (Grangier and Auli, 2018)) beyond the input text into the generation model.”
- Learning to Model Editing Processes (2022, background): “This has two benefits: 1) it allows the model to scale well with respect to input sequence length, and 2) allows us to make substantial changes with fewer actions (Grangier and Auli, 2018).”