Enforcing Paraphrase Generation via Controllable Latent Diffusion

Anonymous

Abstract:

Paraphrase generation aims to produce high-quality and diverse utterances of a given text.
Though state-of-the-art generation via the diffusion model reconciles generation quality and diversity, textual diffusion suffers from a truncation issue that hinders efficiency and quality control.
In this work, we propose \textit{L}atent \textit{D}iffusion \textit{P}araphraser~(LDP), a novel paraphrase generation by modeling a controllable diffusion process given a learned latent space.
LDP achieves superior generation efficiency compared to its diffusion counterparts.
It facilitates only input segments to enforce paraphrase semantics, which further improves the results without external features.
Experiments show that LDP achieves improved and diverse paraphrase generation compared to baselines.
Further analysis shows that our method is also helpful to other similar text generations and domain adaptations.
Our code and data are available at https://anonymous.4open.science/r/8F72 .

Paper Type: long

Research Area: Generation

Contribution Types: NLP engineering experiment

Languages Studied: English

Preprint Status: We are considering releasing a non-anonymous preprint in the next two months (i.e., during the reviewing process).

A1: yes

A1 Elaboration For Yes Or No: limitation section

A2: no

A2 Elaboration For Yes Or No: There is no potential risk regarding our improved paraphrase generation.

A3: yes

A3 Elaboration For Yes Or No: section 1

B: yes

B1: yes

B1 Elaboration For Yes Or No: section4, 5

B2: no

B2 Elaboration For Yes Or No: the work only involves the open-source baseline systems, which applies only for paraphrasing or text generation.

B3: no

B3 Elaboration For Yes Or No: The work only focus on improving paraphrase generation on open-source resources, which we follow the general open-source protocol

B4: no

B4 Elaboration For Yes Or No: The open-source paraphrase data does not involve privacy

B5: yes

B5 Elaboration For Yes Or No: section 4, datasets

B6: yes

B6 Elaboration For Yes Or No: section 4

C: yes

C1: yes

C1 Elaboration For Yes Or No: section 4

C2: yes

C2 Elaboration For Yes Or No: section 4

C3: yes

C3 Elaboration For Yes Or No: section 4

C4: yes

C4 Elaboration For Yes Or No: section 4

D: no

D1: n/a

D2: n/a

D3: n/a

D4: n/a

D5: n/a

E: no

E1: n/a