Concept · 1 paper · updated 2026-11-15
Text style transfer
Rewrites a sentence into another style while keeping its meaning. Only one card so far: a tag-and-generate method that adds polite phrases to neutral requests. A tagger marks where phrases go, then a generator fills them in. Its politeness BLEU-self is 70.44 against 11.83 for DRG, at 89.50 against 90.25 accuracy. Author-reported.
style-transferpolitenesstaggingtext-generation
Markdown4 min read
AI-compiled overview, updated 2026-11-15, not yet reviewed by a human. Every claim cites its source; check it when a detail matters.
Overview
The task is to take a sentence written in one style and produce a sentence in a target style with the same content. Classic benchmarks use two opposite poles, such as positive and negative reviews 2004.14257 §1. Politeness is harder, because the source side is neutral: it has no polite markers to remove, so the system must add wording rather than swap it [arxiv:2004.14257 §1] 2004.14257 §4.2.
The invariant the method keeps is the content of the source. It edits by inserting target-style phrases into the source sentence, so the original words stay in place 2004.14257 §4.2. Older methods instead retrieve a similar sentence from the other style and delete and replace words 2004.14257 §2.
Variants
Only one paper with a card covers this concept so far. Its tagger comes in two forms, and the paper compares them on two datasets.
Add-tagger for neutral sources
The tagger is trained only on target-style sentences. Each training source is the target sentence with its style phrases deleted, and the tagger learns to put position tags where those phrases were 2004.14257 §4.2 [arxiv:2004.14257 eq. 4]. Because the source needs no phrases, this suits a neutral input. It is the variant the authors use for politeness 2004.14257 §4.2. The generator, trained on tagged sentences paired with the original target, then fills each tag with a phrase 2004.14257 §4.3 2004.14257 eq. 5. Card: Politeness Transfer: A Tag and Generate Approach.
Replace-tagger for styled sources
The tagger is trained on source-style sentences, with the source phrases replaced by tags 2004.14257 §4.2 2004.14257 eq. 3. This needs the input to carry phrases that can be removed. Table 5 reports it on Yelp and Captions only 2004.14257 tab. 5.
Combined tagger
The authors also report a combined tagger that uses both training sets 2004.14257 tab. 5. On Yelp it gives the highest BLEU-r of the three taggers (22.46) with accuracy 72.5, between the two single variants. On Captions it gives the highest BLEU-r (18.51) but the lowest accuracy of the three (82.17) 2004.14257 tab. 5.
When to use which
| Situation | Use | Why |
|---|---|---|
| Input is neutral, with no style phrases to delete (for example, plain requests to become polite) | Add-tagger | The paper's own setting; the add-tagger is trained for this case 2004.14257 §4.2 |
| Input already carries phrases of the source style that can be cut out | Replace-tagger | Trained for that case 2004.14257 §4.2; it reaches 86.6 accuracy on Yelp against 53.2 for the add-tagger 2004.14257 tab. 5 |
| Accuracy matters and the data looks like Captions, not Yelp | Add-tagger, checked on your data | On Captions the add-tagger reaches 93.17 accuracy and 15.63 BLEU-r, against 84.5 and 15.04 for the replace-tagger. On Yelp the add-tagger reached only 53.2 2004.14257 tab. 5 |
| Content overlap (BLEU-r) matters more than accuracy | Combined tagger | Highest BLEU-r on Yelp and Captions, but accuracy falls to 72.5 and 82.17 2004.14257 tab. 5 |
The paper gives these results on its own datasets and under its own metrics only. They do not show which tagger is better for a new domain 2004.14257 §5.
Constraints the paper states for its method:
- Data. Two labelled corpora are needed: target-style sentences for the add-tagger, plus, for the replace-tagger, source-style sentences 2004.14257 §4.2. The politeness data is built from Enron emails and scored with an external classifier; the 800-sentence test set is hand-annotated 2004.14257 §3.1.
- Models. Two sequence-to-sequence transformers, a tagger and a generator, with four layers and hidden size 512 in the paper's setting [arxiv:2004.14257 §5]. Inference runs both models with beam size 5 2004.14257 §5.
- Effort. The phrase scoring in 2004.14257 eq. 1 and [arxiv:2004.14257 eq. 2] is simple counting, but the method runs two trained models at inference time, each with beam search 2004.14257 §4.
- Evaluation. Politeness accuracy comes from a classifier trained on other data, so accuracy inherits that classifier's biases 2004.14257 §5.
Implementation sketch
Two-stage pipeline for the add-tagger. Phrase scores come from tf-idf ratios between the target and source corpora 2004.14257 eq. 1. Phrases are then normalised with smoothing exponent 0.75 2004.14257 eq. 2 2004.14257 §5.
# Score candidate phrases by target-to-source tf-idf ratio
# [arxiv:2004.14257 eq. 1]
# Smooth with exponent gamma = 0.75, then normalise
# [arxiv:2004.14257 eq. 2]
def phrase_scores(target_sents, source_sents, gamma):
...
# Training pairs for the add-tagger: phrases deleted in, tags out
# [arxiv:2004.14257 §4.2]
def tagger_pairs(target_sents, phrases):
...
# Train the tagger on those pairs, then the generator on tagged-to-target
# pairs [arxiv:2004.14257 §4.3]
# Inference: tagger proposes tags (reranked to prefer more tags), generator
# fills them [arxiv:2004.14257 §5]
def transfer(source, tagger, generator):
tagged = beam_search(tagger, source, beam=5, prefer_tags=True)
return beam_search(generator, tagged, beam=5)Where variants differ: the replace-tagger changes only the tagger's training pairs, which are built from source-style sentences 2004.14257 §4.2. The rest of the pipeline is the same 2004.14257 §4.2.
Implementers should check the paper's phrase-selection threshold 2004.14257 §4.1 against the released code before copying it. The code applies it differently from the paper's literal wording; see the card's Paper vs code section.
Contradictions
Within the paper, the BLEU-r gain on Captions is given two ways. The text says 3.64 2004.14257 §5, while the table difference between 15.63 and 11.78 is 3.85 2004.14257 tab. 2. The paper gives no reason for the gap.
No disagreements with other papers are known, because only one card covers this concept so far.
Papers
- Politeness Transfer: A Tag and Generate Approach: tags positions for phrase insertion on neutral sentences, then generates the phrases. Politeness BLEU-self 70.44 against 11.83 for DRG, at accuracy 89.50 against 90.25 (author-reported).
Source and license
Compiled from the papers listed on this page, all published under CC BY, CC BY-SA or CC0, with citations. See each paper's page for its authors and license.