Related papers: CUT: Controllable Unsupervised Text Simplification

Text generation rarely considers the control of lexical complexity, which limits its more comprehensive practical application. We introduce a novel task of lexical complexity controlled sentence generation, which aims at keywords to…

State-of-the-art text simplification (TS) systems adopt end-to-end neural network models to directly generate the simplified version of the input text, and usually function as a blackbox. Moreover, TS is usually treated as an all-purpose…

Previous work on controllable text generation has explored the idea of control from the latent space, such as optimizing a representation with attribute-related classifiers or sampling a representation from relevant discrete samples.…

Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data. Contrastive learning for Unpaired image-to-image Translation (CUT) yields state-of-the-art…

Topic-controllable summarization is an emerging research area with a wide range of potential applications. However, existing approaches suffer from significant limitations. For example, the majority of existing methods built upon recurrent…

Existing reference-free metrics have obvious limitations for evaluating controlled text generation models. Unsupervised metrics can only provide a task-agnostic evaluation result which correlates weakly with human judgments, whereas…

Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge. Neural MT systems can be trained in an unsupervised way without any…

Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. For example, researchers hoping…

Current summarization systems yield generic summaries that are disconnected from users' preferences and expectations. To address this limitation, we present CTRLsum, a novel framework for controllable summarization. Our approach enables…

Modern unsupervised machine translation (MT) systems reach reasonable translation quality under clean and controlled data conditions. As the performance gap between supervised and unsupervised MT narrows, it is interesting to ask whether…

Sentiment analysis is an important task in understanding social media content like customer reviews, Twitter and Facebook feeds etc. In multilingual communities around the world, a large amount of social media text is characterized by the…

Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification…

Speech LLM post-training increasingly relies on efficient cross-modal alignment and robust low-resource adaptation, yet collecting large-scale audio-text pairs remains costly. Text-only alignment methods such as TASU reduce this burden by…

We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation. We first…

Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology constraints remains an open problem. We describe our approach to…

We introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation. We verified our GEC system through…

Robotic systems that rely primarily on self-supervised learning have the potential to decrease the amount of human annotation and engineering effort required to learn control strategies. In the same way that prior robotic systems have…

Current deep learning methods for anomaly detection in text rely on supervisory signals in inliers that may be unobtainable or bespoke architectures that are difficult to tune. We study a simpler alternative: fine-tuning Transformers on the…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has…