In this work, we are dedicated to text-guided image generation and propose a novel framework, i.e., CLIP2GAN, by leveraging CLIP model and StyleGAN. The key idea of our CLIP2GAN is to bridge the output feature embedding space of CLIP and the input latent space of StyleGAN, which is realized by introducing a mapping network. In the training stage, we encode an image with CLIP and map the output feature to a latent code, which is further used to reconstruct the image. In this way, the mapping network is optimized in a self-supervised learning way. In the inference stage, since CLIP can embed both image and text into a shared feature embedding space, we replace CLIP image encoder in the training architecture with CLIP text encoder, while keeping the following mapping network as well as StyleGAN model. As a result, we can flexibly input a text description to generate an image. Moreover, by simply adding mapped text features of an attribute to a mapped CLIP image feature, we can effectively edit the attribute to the image. Extensive experiments demonstrate the superior performance of our proposed CLIP2GAN compared to previous methods.
Prompting large language models has enabled significant recent progress in multi-step reasoning over text. However, when applied to text generation from semi-structured data (e.g., graphs or tables), these methods typically suffer from low semantic coverage, hallucination, and logical inconsistency. We propose MURMUR, a neuro-symbolic modular approach to text generation from semi-structured data with multi-step reasoning. MURMUR is a best-first search method that generates reasoning paths using: (1) neural and symbolic modules with specific linguistic and logical skills, (2) a grammar whose production rules define valid compositions of modules, and (3) value functions that assess the quality of each reasoning step. We conduct experiments on two diverse data-to-text generation tasks like WebNLG and LogicNLG. These tasks differ in their data representations (graphs and tables) and span multiple linguistic and logical skills. MURMUR obtains significant improvements over recent few-shot baselines like direct prompting and chain-of-thought prompting, while also achieving comparable performance to fine-tuned GPT-2 on out-of-domain data. Moreover, human evaluation shows that MURMUR generates highly faithful and correct reasoning paths that lead to 26% more logically consistent summaries on LogicNLG, compared to direct prompting.
Computational models of syntax are predominantly text-based. Here we propose that basic syntax can be modeled directly from raw speech in a fully unsupervised way. We focus on one of the most ubiquitous and basic properties of syntax -- concatenation. We introduce spontaneous concatenation: a phenomenon where convolutional neural networks (CNNs) trained on acoustic recordings of individual words start generating outputs with two or even three words concatenated without ever accessing data with multiple words in the input. Additionally, networks trained on two words learn to embed words into novel unobserved word combinations. To our knowledge, this is a previously unreported property of CNNs trained on raw speech in the Generative Adversarial Network setting and has implications both for our understanding of how these architectures learn as well as for modeling syntax and its evolution from raw acoustic inputs.
Background: Large language models such as ChatGPT are capable of generating grammatically perfect and human-like text content, and a large number of ChatGPT-generated texts have appeared on the Internet. However, medical texts such as clinical notes and diagnoses require rigorous validation, and erroneous medical content generated by ChatGPT could potentially lead to disinformation that poses significant harm to healthcare and the general public. Objective: This research is among the first studies on responsible and ethical AIGC (Artificial Intelligence Generated Content) in medicine. We focus on analyzing the differences between medical texts written by human experts and generated by ChatGPT, and designing machine learning workflows to effectively detect and differentiate medical texts generated by ChatGPT. Methods: We first construct a suite of datasets containing medical texts written by human experts and generated by ChatGPT. In the next step, we analyze the linguistic features of these two types of content and uncover differences in vocabulary, part-of-speech, dependency, sentiment, perplexity, etc. Finally, we design and implement machine learning methods to detect medical text generated by ChatGPT. Results: Medical texts written by humans are more concrete, more diverse, and typically contain more useful information, while medical texts generated by ChatGPT pay more attention to fluency and logic, and usually express general terminologies rather than effective information specific to the context of the problem. A BERT-based model can effectively detect medical texts generated by ChatGPT, and the F1 exceeds 95%.
Despite the fact that text-to-video (TTV) model has recently achieved remarkable success, there have been few approaches on TTV for its extension to video editing. Motivated by approaches on TTV models adapting from diffusion-based text-to-image (TTI) models, we suggest the video editing framework given only a pretrained TTI model and a single <text, video> pair, which we term Edit-A-Video. The framework consists of two stages: (1) inflating the 2D model into the 3D model by appending temporal modules and tuning on the source video (2) inverting the source video into the noise and editing with target text prompt and attention map injection. Each stage enables the temporal modeling and preservation of semantic attributes of the source video. One of the key challenges for video editing include a background inconsistency problem, where the regions not included for the edit suffer from undesirable and inconsistent temporal alterations. To mitigate this issue, we also introduce a novel mask blending method, termed as sparse-causal blending (SC Blending). We improve previous mask blending methods to reflect the temporal consistency so that the area where the editing is applied exhibits smooth transition while also achieving spatio-temporal consistency of the unedited regions. We present extensive experimental results over various types of text and videos, and demonstrate the superiority of the proposed method compared to baselines in terms of background consistency, text alignment, and video editing quality.
Summarization models often generate text that is poorly calibrated to quality metrics because they are trained to maximize the likelihood of a single reference (MLE). To address this, recent work has added a calibration step, which exposes a model to its own ranked outputs to improve relevance or, in a separate line of work, contrasts positive and negative sets to improve faithfulness. While effective, much of this work has focused on how to generate and optimize these sets. Less is known about why one setup is more effective than another. In this work, we uncover the underlying characteristics of effective sets. For each training instance, we form a large, diverse pool of candidates and systematically vary the subsets used for calibration fine-tuning. Each selection strategy targets distinct aspects of the sets, such as lexical diversity or the size of the gap between positive and negatives. On three diverse scientific long-form summarization datasets (spanning biomedical, clinical, and chemical domains), we find, among others, that faithfulness calibration is optimal when the negative sets are extractive and more likely to be generated, whereas for relevance calibration, the metric margin between candidates should be maximized and surprise--the disagreement between model and metric defined candidate rankings--minimized. Code to create, select, and optimize calibration sets is available at https://github.com/griff4692/calibrating-summaries
Content-based fashion image retrieval (CBFIR) has been widely used in our daily life for searching fashion images or items from online platforms. In e-commerce purchasing, the CBFIR system can retrieve fashion items or products with the same or comparable features when a consumer uploads a reference image, image with text, sketch or visual stream from their daily life. This lowers the CBFIR system reliance on text and allows for a more accurate and direct searching of the desired fashion product. Considering recent developments, CBFIR still has limits when it comes to visual searching in the real world due to the simultaneous availability of multiple fashion items, occlusion of fashion products, and shape deformation. This paper focuses on CBFIR methods with the guidance of images, images with text, sketches, and videos. Accordingly, we categorized CBFIR methods into four main categories, i.e., image-guided CBFIR (with the addition of attributes and styles), image and text-guided, sketch-guided, and video-guided CBFIR methods. The baseline methodologies have been thoroughly analyzed, and the most recent developments in CBFIR over the past six years (2017 to 2022) have been thoroughly examined. Finally, key issues are highlighted for CBFIR with promising directions for future research.
Subjectivity and difference of opinion are key social phenomena, and it is crucial to take these into account in the annotation and detection process of derogatory textual content. In this paper, we use four datasets provided by SemEval-2023 Task 11 and fine-tune a BERT model to capture the disagreement in the annotation. We find individual annotator modeling and aggregation lowers the Cross-Entropy score by an average of 0.21, compared to the direct training on the soft labels. Our findings further demonstrate that annotator metadata contributes to the average 0.029 reduction in the Cross-Entropy score.
Designing complex 3D scenes has been a tedious, manual process requiring domain expertise. Emerging text-to-3D generative models show great promise for making this task more intuitive, but existing approaches are limited to object-level generation. We introduce \textbf{locally conditioned diffusion} as an approach to compositional scene diffusion, providing control over semantic parts using text prompts and bounding boxes while ensuring seamless transitions between these parts. We demonstrate a score distillation sampling--based text-to-3D synthesis pipeline that enables compositional 3D scene generation at a higher fidelity than relevant baselines.
Multi-turn compositional image generation (M-CIG) is a challenging task that aims to iteratively manipulate a reference image given a modification text. While most of the existing methods for M-CIG are based on generative adversarial networks (GANs), recent advances in image generation have demonstrated the superiority of diffusion models over GANs. In this paper, we propose a diffusion-based method for M-CIG named conditional denoising diffusion with image compositional matching (CDD-ICM). We leverage CLIP as the backbone of image and text encoders, and incorporate a gated fusion mechanism, originally proposed for question answering, to compositionally fuse the reference image and the modification text at each turn of M-CIG. We introduce a conditioning scheme to generate the target image based on the fusion results. To prioritize the semantic quality of the generated target image, we learn an auxiliary image compositional match (ICM) objective, along with the conditional denoising diffusion (CDD) objective in a multi-task learning framework. Additionally, we also perform ICM guidance and classifier-free guidance to improve performance. Experimental results show that CDD-ICM achieves state-of-the-art results on two benchmark datasets for M-CIG, i.e., CoDraw and i-CLEVR.