相关论文: Spivavtor: An Instruction Tuned Ukrainian Text Edi…

In this paper, we introduce OmniGEC, a collection of multilingual silver-standard datasets for the task of Grammatical Error Correction (GEC), covering eleven languages: Czech, English, Estonian, German, Greek, Icelandic, Italian, Latvian,…

As text-based speech editing becomes increasingly prevalent, the demand for unrestricted free-text editing continues to grow. However, existing speech editing techniques encounter significant challenges, particularly in maintaining…

This paper investigates the finetuning of end-to-end models for bidirectional Estonian-English and Estonian-Russian conversational speech-to-text translation. Due to the limited availability of speech translation data for Estonian, we…

We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify…

We propose EdiText, a controllable text editing method that modifies the reference text to desired attributes at various scales. We integrate an SDEdit-based editing technique that allows for broad adjustments in the degree of text editing.…

While the evaluation of multimodal English-centric models is an active area of research with numerous benchmarks, there is a profound lack of benchmarks or evaluation suites for low- and mid-resource languages. We introduce ZNO-Vision, a…

Domain models are central to software engineering, as they enable a shared understanding, guide implementation, and support automated analyses and model-driven development. Yet, despite these benefits, practitioners often skip modeling…

Text embeddings are essential for many tasks, such as document retrieval, clustering, and semantic similarity assessment. In this paper, we study how to contrastively train text embedding models in a compute-optimal fashion, given a suite…

Instruction-based video editing requires transforming a source video according to a natural-language instruction while preserving irrelevant content and remaining temporally coherent. We argue that existing Diffusion Transformer (DiT)…

We propose a framework for training non-autoregressive sequence-to-sequence models for editing tasks, where the original input sequence is iteratively edited to produce the output. We show that the imitation learning algorithms designed to…

The text editing tasks, including sentence fusion, sentence splitting and rephrasing, text simplification, and Grammatical Error Correction (GEC), share a common trait of dealing with highly similar input and output sequences. This area of…

Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the generated images. We propose a novel learning method for…

Multimodal dataset distillation aims to synthesize a small set of image-text pairs that enables efficient training of large-scale vision-language models. While dataset distillation has shown promise in unimodal tasks, extending it to…

Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world. Yet, the key factors driving the model's capability to understand and follow…

Text simplification (TS) systems rewrite text to make it more readable while preserving its content. However, what makes a text easy to read depends on the intended readers. Recent work has shown that pre-trained language models can…

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…

We present an unsupervised explainable word embedding technique, called EVE, which is built upon the structure of Wikipedia. The proposed model defines the dimensions of a semantic vector representing a word using human-readable labels,…

This technical report presents the training methodology and evaluation results of the open-source multilingual E5 text embedding models, released in mid-2023. Three embedding models of different sizes (small / base / large) are provided,…

This paper describes the conversion of a Hidden Markov Model into a sequential transducer that closely approximates the behavior of the stochastic model. This transformation is especially advantageous for part-of-speech tagging because the…

In recent years, pretrained models have been widely used in various fields, including natural language understanding, computer vision, and natural language generation. However, the performance of these language generation models is highly…