Related papers: A Sequence-to-Sequence&Set Model for Text-to-Table…
Most deep learning approaches for text-to-SQL generation are limited to the WikiSQL dataset, which only supports very simple queries. Recently, template-based and sequence-to-sequence approaches were proposed to support complex queries,…
Deep learning-based code generation has completely transformed the way developers write programs today. Existing approaches to code generation have focused either on the Sequence-to-Sequence paradigm, which generates target code as a…
Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training…
Traditional table-to-text natural language generation (NLG) tasks focus on generating text from schemas that are already seen in the training set. This limitation curbs their generalizabilities towards real-world scenarios, where the…
The encoder-decoder model is widely used in natural language generation tasks. However, the model sometimes suffers from repeated redundant generation, misses important phrases, and includes irrelevant entities. Toward solving these…
Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models, a popular choice for set…
For the advancements of time series classification, scrutinizing previous studies, most existing methods adopt a common learning-to-classify paradigm - a time series classifier model tries to learn the relation between sequence inputs and…
End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases. In this paper, we propose a novel yet simple end-to-end differentiable model called memory-to-sequence (Mem2Seq) to address this…
Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to-end. These models rely on representation learning…
Table-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, which requires large-scale training samples. However, the lack…
Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural…
This work proposes a novel adaptation of a pretrained sequence-to-sequence model to the task of document ranking. Our approach is fundamentally different from a commonly-adopted classification-based formulation of ranking, based on…
Sequence-to-Sequence (Seq2Seq) models have witnessed a notable success in generating natural conversational exchanges. Notwithstanding the syntactically well-formed responses generated by these neural network models, they are prone to be…
We present TableSeq, an image-only, end-to-end framework for joint table structure recognition, content recognition, and cell localization. The model formulates these tasks as a single sequence-generation problem: one decoder produces an…
Since we can leverage a large amount of unlabeled data without any human supervision to train a model and transfer the knowledge to target tasks, self-supervised learning is a de-facto component for the recent success of deep learning in…
Despite the unprecedented success of text-to-image diffusion models, controlling the number of depicted objects using text is surprisingly hard. This is important for various applications from technical documents, to children's books to…
Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…
Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In…
This paper proposes a fundamentally new paradigm for image generation through set-based tokenization and distribution modeling. Unlike conventional methods that serialize images into fixed-position latent codes with a uniform compression…
Simultaneous sequence generation is a pivotal task for real-time scenarios, such as streaming speech recognition, simultaneous machine translation and simultaneous speech translation, where the target sequence is generated while receiving…