Training an image captioner without annotated image-sentence pairs has gained traction in recent years. Previous approaches can be categorized into two strategies: crawling sentences from mismatching corpora and aligning them with the given images as pseudo annotations, or pre-training the captioner using external image-text pairs. However, the aligning setting seems to reach its performance limit due to the quality problem of pairs, and pre-training requires significant computational resources. To address these challenges, we propose a new strategy ``LPM + retrieval-augmented learning" where the prior knowledge from large pre-trained models (LPMs) is leveraged as supervision, and a retrieval process is integrated to further reinforce its effectiveness. Specifically, we introduce Retrieval-augmented Pseudo Sentence Generation (RaPSG), which adopts an efficient approach to retrieve highly relevant short region descriptions from the mismatching corpora and use them to generate a variety of pseudo sentences with distinct representations as well as high quality via LPMs. In addition, a fluency filter and a CLIP-guided training objective are further introduced to facilitate model optimization. Experimental results demonstrate that our method surpasses the SOTA pre-training model (Flamingo3B) by achieving a CIDEr score of 78.1 (+5.1) while utilizing only 0.3% of its trainable parameters (1.3B VS 33M). Importantly, our approach eliminates the need of computationally expensive pre-training processes on external datasets (e.g., the requirement of 312M image-text pairs for Flamingo3B). We further show that with a simple extension, the generated pseudo sentences can be deployed as weak supervision to boost the 1% semi-supervised image caption benchmark up to 93.4 CIDEr score (+8.9) which showcases the versatility and effectiveness of our approach.
In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion. We propose to first encode speech signals into a phoneme-rate latent representation with a variational autoencoder enhanced by adversarial training, and then jointly model the duration and the latent representation with a diffusion model. Subjective evaluations on LJSpeech and LibriTTS datasets demonstrate that our method beats the best publicly available systems in naturalness. By adopting recent generative inverse problem solving algorithms for diffusion models, DiffVoice achieves the state-of-the-art performance in text-based speech editing, and zero-shot adaptation.
Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is still suboptimal as they sample multiple tokens simultaneously without considering the dependence among them. We empirically investigate this problem and propose a learnable sampling model, Text-Conditioned Token Selection (TCTS), to select optimal tokens via localized supervision with text information. TCTS improves not only the image quality but also the semantic alignment of the generated images with the given texts. To further improve the image quality, we introduce a cohesive sampling strategy, Frequency Adaptive Sampling (FAS), to each group of tokens divided according to the self-attention maps. We validate the efficacy of TCTS combined with FAS with various generative tasks, demonstrating that it significantly outperforms the baselines in image-text alignment and image quality. Our text-conditioned sampling framework further reduces the original inference time by more than 50% without modifying the original generative model.
We propose a novel cascaded cross-modal transformer (CCMT) that combines speech and text transcripts to detect customer requests and complaints in phone conversations. Our approach leverages a multimodal paradigm by transcribing the speech using automatic speech recognition (ASR) models and translating the transcripts into different languages. Subsequently, we combine language-specific BERT-based models with Wav2Vec2.0 audio features in a novel cascaded cross-attention transformer model. We apply our system to the Requests Sub-Challenge of the ACM Multimedia 2023 Computational Paralinguistics Challenge, reaching unweighted average recalls (UAR) of 65.41% and 85.87% for the complaint and request classes, respectively.
Given a controversial target such as ``nuclear energy'', argument mining aims to identify the argumentative text from heterogeneous sources. Current approaches focus on exploring better ways of integrating the target-associated semantic information with the argumentative text. Despite their empirical successes, two issues remain unsolved: (i) a target is represented by a word or a phrase, which is insufficient to cover a diverse set of target-related subtopics; (ii) the sentence-level topic information within an argument, which we believe is crucial for argument mining, is ignored. To tackle the above issues, we propose a novel explainable topic-enhanced argument mining approach. Specifically, with the use of the neural topic model and the language model, the target information is augmented by explainable topic representations. Moreover, the sentence-level topic information within the argument is captured by minimizing the distance between its latent topic distribution and its semantic representation through mutual learning. Experiments have been conducted on the benchmark dataset in both the in-target setting and the cross-target setting. Results demonstrate the superiority of the proposed model against the state-of-the-art baselines.
One major challenge in reinforcement learning (RL) is the large amount of steps for the RL agent needs to converge in the training process and learn the optimal policy, especially in text-based game environments where the action space is extensive. However, non-player characters (NPCs) sometimes hold some key information about the game, which can potentially help to train RL agents faster. Thus, this paper explores how to interact and converse with NPC agents to get the key information using large language models (LLMs), as well as incorporate this information to speed up RL agent's training using knowledge graphs (KGs) and Story Shaping.
In this article we describe an efficient approach to guiding language model text generation with regular expressions and context-free grammars. Our approach adds little to no overhead to the token sequence generation process, and makes guided generation feasible in practice. An implementation is provided in the open source Python library Outlines.
With social media usage growing exponentially in the past few years, fake news has also become extremely prevalent. The detrimental impact of fake news emphasizes the need for research focused on automating the detection of false information and verifying its accuracy. In this work, we present the outcome of the Factify 2 shared task, which provides a multi-modal fact verification and satire news dataset, as part of the DeFactify 2 workshop at AAAI'23. The data calls for a comparison based approach to the task by pairing social media claims with supporting documents, with both text and image, divided into 5 classes based on multi-modal relations. In the second iteration of this task we had over 60 participants and 9 final test-set submissions. The best performances came from the use of DeBERTa for text and Swinv2 and CLIP for image. The highest F1 score averaged for all five classes was 81.82%.
In the paradigm of AI-generated content (AIGC), there has been increasing attention in extending pre-trained text-to-image (T2I) models to text-to-video (T2V) generation. Despite their effectiveness, these frameworks face challenges in maintaining consistent narratives and handling rapid shifts in scene composition or object placement from a single user prompt. This paper introduces a new framework, dubbed DirecT2V, which leverages instruction-tuned large language models (LLMs) to generate frame-by-frame descriptions from a single abstract user prompt. DirecT2V utilizes LLM directors to divide user inputs into separate prompts for each frame, enabling the inclusion of time-varying content and facilitating consistent video generation. To maintain temporal consistency and prevent object collapse, we propose a novel value mapping method and dual-softmax filtering. Extensive experimental results validate the effectiveness of the DirecT2V framework in producing visually coherent and consistent videos from abstract user prompts, addressing the challenges of zero-shot video generation.
In text classification tasks, fine tuning pretrained language models like BERT and GPT-3 yields competitive accuracy; however, both methods require pretraining on large text datasets. In contrast, general topic modeling methods possess the advantage of analyzing documents to extract meaningful patterns of words without the need of pretraining. To leverage topic modeling's unsupervised insights extraction on text classification tasks, we develop the Knowledge Distillation Semi-supervised Topic Modeling (KDSTM). KDSTM requires no pretrained embeddings, few labeled documents and is efficient to train, making it ideal under resource constrained settings. Across a variety of datasets, our method outperforms existing supervised topic modeling methods in classification accuracy, robustness and efficiency and achieves similar performance compare to state of the art weakly supervised text classification methods.