相关论文: T-STAR: Truthful Style Transfer using AMR Graph as…

Text style transfer (TST) is the task of transforming a text to reflect a particular style while preserving its original content. Evaluating TST outputs is a multidimensional challenge, requiring the assessment of style transfer accuracy,…

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) systems in diverse target domains, such as noise and accents.…

Abstract Meaning Representation (AMR) parsing aims to predict an AMR graph from textual input. Recently, there has been notable growth in AMR parsing performance. However, most existing work focuses on improving the performance in the…

Given an arbitrary content and style image, arbitrary style transfer aims to render a new stylized image which preserves the content image's structure and possesses the style image's style. Existing arbitrary style transfer methods are…

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

This paper introduces ASTRA, a novel method for improving Automatic Speech Recognition (ASR) through text injection.Unlike prevailing techniques, ASTRA eliminates the need for sampling to match sequence lengths between speech and text…

Style transfer aims to render the content of a given image in the graphical/artistic style of another image. The fundamental concept underlying NeuralStyle Transfer (NST) is to interpret style as a distribution in the feature space of a…

Automatic evaluation of ST systems is typically performed by comparing translation hypotheses with one or more reference translations. While effective to some extent, this approach inherits the limitation of reference-based evaluation that…

Most existing style transfer methods follow the assumption that styles can be represented with global statistics (e.g., Gram matrices or covariance matrices), and thus address the problem by forcing the output and style images to have…

We introduce replacing language model (RLM), a sequence-to-sequence language modeling framework for text style transfer (TST). Our method autoregressively replaces each token of the source sentence with a text span that has a similar…

The performance of existing text style transfer models is severely limited by the non-parallel datasets on which the models are trained. In non-parallel datasets, no direct mapping exists between sentences of the source and target style;…

Abstract meaning representations (AMRs) are broad-coverage sentence-level semantic representations. AMRs represent sentences as rooted labeled directed acyclic graphs. AMR parsing is challenging partly due to the lack of annotated…

With an ever increasing size of text present on the Internet, automatic summary generation remains an important problem for natural language understanding. In this work we explore a novel full-fledged pipeline for text summarization with an…

In cross-lingual Abstract Meaning Representation (AMR) parsing, researchers develop models that project sentences from various languages onto their AMRs to capture their essential semantic structures: given a sentence in any language, 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…

Abstract Meaning Representations (AMR) are a broad-coverage semantic formalism which represents sentence meaning as a directed acyclic graph. To train most AMR parsers, one needs to segment the graph into subgraphs and align each such…

A neural artistic style transformation (NST) model can modify the appearance of a simple image by adding the style of a famous image. Even though the transformed images do not look precisely like artworks by the same artist of the…

Traditional Smooth Transition Autoregressive (STAR) models offer an effective way to model these dynamics through smooth regime changes based on specific transition variables. In this paper, we propose a novel approach by drawing an analogy…

Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities. To this end, we exploit Abstract Meaning Representation (AMR)…

As comprehensive large model evaluation becomes prohibitively expensive, predicting model performance from limited observations has become essential. However, existing statistical methods struggle with pattern shifts, data sparsity, and…