Related papers: Formality Style Transfer with Hybrid Textual Annot…
Tuning-free diffusion-based models have demonstrated significant potential in the realm of image personalization and customization. However, despite this notable progress, current models continue to grapple with several complex challenges…
Prompting approaches have been recently explored in text style transfer, where a textual prompt is used to query a pretrained language model to generate style-transferred texts word by word in an autoregressive manner. However, such a…
Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e.g. their gender or ethnicity. Style transfer is an effective way of transforming texts in order to remove any…
Existing neural style transfer methods require reference style images to transfer texture information of style images to content images. However, in many practical situations, users may not have reference style images but still be…
Back-translation based approaches have recently lead to significant progress in unsupervised sequence-to-sequence tasks such as machine translation or style transfer. In this work, we extend the paradigm to the problem of learning a…
Large language models (LLMs) make it easy to rewrite a text in any style -- e.g. to make it more polite, persuasive, or more positive -- but evaluation thereof is not straightforward. A challenge lies in measuring content preservation: that…
Unsupervised Text Style Transfer (UTST) aims to build a system to transfer the stylistic properties of a given text without parallel text pairs. Compared with text transfer between style polarities, UTST for controllable intensity is more…
The stylistic properties of text have intrigued computational linguistics researchers in recent years. Specifically, researchers have investigated the Text Style Transfer (TST) task, which aims to change the stylistic properties of the text…
There is a huge performance gap between formal and informal language understanding tasks. The recent pre-trained models that improved the performance of formal language understanding tasks did not achieve a comparable result on informal…
Style is ubiquitous in our daily language uses, while what is language style to learning machines? In this paper, by exploiting the second-order statistics of semantic vectors of different corpora, we present a novel perspective on this…
As the application space of language models continues to evolve, a natural question to ask is how we can quickly adapt models to new tasks. We approach this classic question from a continual learning perspective, in which we aim to continue…
This work aims to produce translations that convey source language content at a formality level that is appropriate for a particular audience. Framing this problem as a neural sequence-to-sequence task ideally requires training triplets…
Generating responses in a targeted style is a useful yet challenging task, especially in the absence of parallel data. With limited data, existing methods tend to generate responses that are either less stylized or less context-relevant. We…
This thesis advances the computational understanding and manipulation of text styles through three interconnected pillars: (1) Text Style Transfer (TST), which alters stylistic properties (e.g., sentiment, formality) while preserving…
Transformer-based models achieve favorable performance in artistic style transfer recently thanks to its global receptive field and powerful multi-head/layer attention operations. Nevertheless, the over-paramerized multi-layer structure…
The interest in demographic information retrieval based on text data has increased in the research community because applications have shown success in different sectors such as security, marketing, heath-care, and others. Recognition and…
Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…
Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve…
Models pre-trained on large-scale regular text corpora often do not work well for user-generated data where the language styles differ significantly from the mainstream text. Here we present Context-Aware Rule Injection (CARI), an…
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has…