Related papers: Texar: A Modularized, Versatile, and Extensible To…
Recent approaches to text analysis from social media and other corpora rely on word lists to detect topics, measure meaning, or to select relevant documents. These lists are often generated by applying computational lexicon expansion…
This paper presents fairseq S^2, a fairseq extension for speech synthesis. We implement a number of autoregressive (AR) and non-AR text-to-speech models, and their multi-speaker variants. To enable training speech synthesis models with less…
Many language generation models are now available for a wide range of generation tasks, including machine translation and summarization. Combining such diverse models may lead to further progress, but ensembling generation models is…
Understanding complex scientific and mathematical concepts, particularly those presented in dense research papers, poses a significant challenge for learners. Dynamic visualizations can greatly enhance comprehension, but creating them…
As robotic systems become increasingly complex, the need for explainable decision-making becomes critical. Existing explainability approaches in robotics typically either focus on individual modules, which can be difficult to query from the…
In this work, we propose a complete framework that generates visual art. Unlike previous stylization methods that are not flexible with style parameters (i.e., they allow stylization with only one style image, a single stylization text or…
We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it.…
We present Speakerly, a new real-time voice-based writing assistance system that helps users with text composition across various use cases such as emails, instant messages, and notes. The user can interact with the system through…
Frontier language model quality increasingly hinges on our ability to organize web-scale text corpora for training. Today's dominant tools trade off speed and flexibility: lexical classifiers (e.g., FastText) are fast but limited to…
We introduce 3D-Speaker-Toolkit, an open-source toolkit for multimodal speaker verification and diarization, designed for meeting the needs of academic researchers and industrial practitioners. The 3D-Speaker-Toolkit adeptly leverages the…
We introduce an open-source toolkit for neural machine translation (NMT) to support research into model architectures, feature representations, and source modalities, while maintaining competitive performance, modularity and reasonable…
In the dynamic landscape of generative NLP, traditional text processing pipelines limit research flexibility and reproducibility, as they are tailored to specific dataset, task, and model combinations. The escalating complexity, involving…
Tabular question answering (TQA) presents a challenging setting for neural systems by requiring joint reasoning of natural language with large amounts of semi-structured data. Unlike humans who use programmatic tools like filters to…
In the vast majority of the academic and scientific domains, LaTeX has established itself as the de facto standard for typesetting complex mathematical equations and formulae. However, LaTeX's complex syntax and code-like appearance present…
Controllable text generation concerns two fundamental tasks of wide applications, namely generating text of given attributes (i.e., attribute-conditional generation), and minimally editing existing text to possess desired attributes (i.e.,…
This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. To this end, we tackle a variety of vision tasks into a…
Text-to-SQL is a key natural language processing task that maps natural language questions to SQL queries, enabling intuitive interaction with web-based databases. Although current methods perform well on benchmarks like BIRD and Spider,…
Teaching neural models to generate narrative coherent texts is a critical problem. Recent pre-trained language models have achieved promising results, but there is still a gap between human written texts and machine-generated outputs. In…
Generating natural and informative texts has been a long-standing problem in NLP. Much effort has been dedicated into incorporating pre-trained language models (PLMs) with various open-world knowledge, such as knowledge graphs or wiki…
Formal languages let us define the textual representation of data with precision. Formal grammars, typically in the form of BNF-like productions, describe the language syntax, which is then annotated for syntax-directed translation and…