相关论文: Converge to the Truth: Factual Error Correction vi…

Despite the success achieved in neural abstractive summarization based on pre-trained language models, one unresolved issue is that the generated summaries are not always faithful to the input document. There are two possible causes of the…

Neural machine translation systems have become state-of-the-art approaches for Grammatical Error Correction (GEC) task. In this paper, we propose a copy-augmented architecture for the GEC task by copying the unchanged words from the source…

Abstractive summarization models often generate inconsistent summaries containing factual errors or hallucinated content. Recent works focus on correcting factual errors in generated summaries via post-editing. Such correction models are…

The proliferation of fake news has emerged as a significant threat to the integrity of information dissemination, particularly on social media platforms. Misinformation can spread quickly due to the ease of creating and disseminating…

Optimizing the phrasing of argumentative text is crucial in higher education and professional development. However, assessing whether and how the different claims in a text should be revised is a hard task, especially for novice writers. In…

We propose a novel system to help fact-checkers formulate search queries for known misinformation claims and effectively search across multiple social media platforms. We introduce an adaptable rewriting strategy, where editing actions for…

Counterfactual explanations (CEs) offer a human-understandable way to explain decisions by identifying specific changes to the input parameters of a base or present model that would lead to a desired change in the outcome. For optimization…

The most commonly used metrics for evaluating automatic speech transcriptions, namely Word Error Rate (WER) and Character Error Rate (CER), have been heavily criticized for their poor correlation to human perception and their inability to…

This work proposes a hybrid modeling framework based on recurrent neural networks (RNNs) and the finite element (FE) method to approximate model discrepancies in time dependent, multi-fidelity problems, and use the trained hybrid models to…

Text-driven image editing enables users to flexibly modify visual content through natural language instructions, and is widely applied to tasks such as semantic object replacement, insertion, and removal. While recent inversion-based…

Fact verification systems typically assess whether a claim is supported by retrieved evidence, assuming that truthfulness depends solely on what is stated. However, many real-world claims are half-truths, factually correct yet misleading…

Recently, several works tackled the video editing task fostered by the success of large-scale text-to-image generative models. However, most of these methods holistically edit the frame using the text, exploiting the prior given by…

Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of…

Modern large language models demonstrate impressive capabilities in text generation and generalization. However, they often struggle with solving text editing tasks, particularly when it comes to correcting spelling errors and mistypings.…

Reinforcement learning for open-ended text generation is constrained by the lack of verifiable rewards, necessitating reliance on judge models that require either annotated data or powerful closed-source models. Inspired by recent work on…

Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre-trained with self-supervised methods. However, ensuring the factual consistency of the generated…

In this paper, we explore the artificial generation of typographical errors based on real-world statistics. We first draw on a small set of annotated data to compute spelling error statistics. These are then invoked to introduce errors into…

A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

Fact verification (FV) aims to assess the veracity of a claim based on relevant evidence. The traditional approach for automated FV includes a three-part pipeline relying on short evidence snippets and encoder-only inference models. More…