This work offers a novel view on the use of human input as labels, acknowledging that humans may err. We build a behavioral profile for human annotators which is used as a feature representation of the provided input. We show that by utilizing black-box machine learning, we can take into account human behavior and calibrate their input to improve the labeling quality. To support our claims and provide a proof-of-concept, we experiment with three different matching tasks, namely, schema matching, entity matching and text matching. Our empirical evaluation suggests that the method can improve the quality of gathered labels in multiple settings including cross-domain (across different matching tasks).
Generative language models (LMs) such as GPT-2/3 can be prompted to generate text with remarkable quality. While they are designed for text-prompted generation, it remains an open question how the generation process could be guided by modalities beyond text such as images. In this work, we propose a training-free framework, called MAGIC (iMAge-Guided text generatIon with CLIP), for plugging in visual controls in the generation process and enabling LMs to perform multimodal tasks (e.g., image captioning) in a zero-shot manner. MAGIC is a simple yet efficient plug-and-play framework, which directly combines an off-the-shelf LM (i.e., GPT-2) and an image-text matching model (i.e., CLIP) for image-grounded text generation. During decoding, MAGIC influences the generation of the LM by introducing a CLIP-induced score, called magic score, which regularizes the generated result to be semantically related to a given image while being coherent to the previously generated context. Notably, the proposed decoding scheme does not involve any gradient update operation, therefore being computationally efficient. On the challenging task of zero-shot image captioning, MAGIC outperforms the state-of-the-art method by notable margins with a nearly 27 times decoding speedup. MAGIC is a flexible framework and is theoretically compatible with any text generation tasks that incorporate image grounding. In the experiments, we showcase that it is also capable of performing visually grounded story generation given both an image and a text prompt.
In recent years, the pre-training-then-fine-tuning paradigm has yielded immense success on a wide spectrum of cross-modal tasks, such as visual question answering (VQA), in which a visual-language (VL) model is first optimized via self-supervised task objectives, e.g., masked language modeling (MLM) and image-text matching (ITM), and then fine-tuned to adapt to downstream task (e.g., VQA) via a brand-new objective function, e.g., answer prediction. The inconsistency of the objective forms not only severely limits the generalization of pre-trained VL models to downstream tasks, but also requires a large amount of labeled data for fine-tuning. To alleviate the problem, we propose an innovative VL fine-tuning paradigm (named Declaration-based Prompt Tuning, abbreviated as DPT), which jointly optimizes the objectives of pre-training and fine-tuning of VQA model, boosting the effective adaptation of pre-trained VL models to the downstream task. Specifically, DPT reformulates the objective form of VQA task via (1) textual adaptation, which converts the given questions into declarative sentence-form for prompt-tuning, and (2) task adaptation, which optimizes the objective function of VQA problem in the manner of pre-training phase. Experimental results on GQA dataset show that DPT outperforms the fine-tuned counterpart by a large margin regarding accuracy in both fully-supervised (2.68%) and zero-shot/few-shot (over 31%) settings. All the data and codes will be available to facilitate future research.
Neural text matching models have been used in a range of applications such as question answering and natural language inference, and have yielded a good performance. However, these neural models are of a limited adaptability, resulting in a decline in performance when encountering test examples from a different dataset or even a different task. The adaptability is particularly important in the few-shot setting: in many cases, there is only a limited amount of labeled data available for a target dataset or task, while we may have access to a richly labeled source dataset or task. However, adapting a model trained on the abundant source data to a few-shot target dataset or task is challenging. To tackle this challenge, we propose a Meta-Weight Regulator (MWR), which is a meta-learning approach that learns to assign weights to the source examples based on their relevance to the target loss. Specifically, MWR first trains the model on the uniformly weighted source examples, and measures the efficacy of the model on the target examples via a loss function. By iteratively performing a (meta) gradient descent, high-order gradients are propagated to the source examples. These gradients are then used to update the weights of source examples, in a way that is relevant to the target performance. As MWR is model-agnostic, it can be applied to any backbone neural model. Extensive experiments are conducted with various backbone text matching models, on four widely used datasets and two tasks. The results demonstrate that our proposed approach significantly outperforms a number of existing adaptation methods and effectively improves the cross-dataset and cross-task adaptability of the neural text matching models in the few-shot setting.
Probabilistic embeddings have proven useful for capturing polysemous word meanings, as well as ambiguity in image matching. In this paper, we study the advantages of probabilistic embeddings in a cross-modal setting (i.e., text and images), and propose a simple approach that replaces the standard vector point embeddings in extant image-text matching models with probabilistic distributions that are parametrically learned. Our guiding hypothesis is that the uncertainty encoded in the probabilistic embeddings captures the cross-modal ambiguity in the input instances, and that it is through capturing this uncertainty that the probabilistic models can perform better at downstream tasks, such as image-to-text or text-to-image retrieval. Through extensive experiments on standard and new benchmarks, we show a consistent advantage for probabilistic representations in cross-modal retrieval, and validate the ability of our embeddings to capture uncertainty.
Video search has become the main routine for users to discover videos relevant to a text query on large short-video sharing platforms. During training a query-video bi-encoder model using online search logs, we identify a modality bias phenomenon that the video encoder almost entirely relies on text matching, neglecting other modalities of the videos such as vision, audio. This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most training samples can be solved solely by text matching. Here we share our practices to improve the first retrieval stage including our solution for the modality imbalance issue. We propose MBVR (short for Modality Balanced Video Retrieval) with two key components: manually generated modality-shuffled (MS) samples and a dynamic margin (DM) based on visual relevance. They can encourage the video encoder to pay balanced attentions to each modality. Through extensive experiments on a real world dataset, we show empirically that our method is both effective and efficient in solving modality bias problem. We have also deployed our MBVR in a large video platform and observed statistically significant boost over a highly optimized baseline in an A/B test and manual GSB evaluations.
The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models with a text prompt. However, the zero-shot use of CLIP is unstable with respect to the phrasing of the input text, making it necessary to carefully engineer the prompts used. We find that this instability stems from a selective similarity score, which is based only on a subset of the semantically meaningful input tokens. To mitigate it, we present a novel explainability-based approach, which adds a loss term to ensure that CLIP focuses on all relevant semantic parts of the input, in addition to employing the CLIP similarity loss used in previous works. When applied to one-shot classification through prompt engineering, our method yields an improvement in the recognition rate, without additional training or fine-tuning. Additionally, we show that CLIP guidance of generative models using our method significantly improves the generated images. Finally, we demonstrate a novel use of CLIP guidance for text-based image generation with spatial conditioning on object location, by requiring the image explainability heatmap for each object to be confined to a pre-determined bounding box.
Image-Text matching (ITM) is a common task for evaluating the quality of Vision and Language (VL) models. However, existing ITM benchmarks have a significant limitation. They have many missing correspondences, originating from the data construction process itself. For example, a caption is only matched with one image although the caption can be matched with other similar images and vice versa. To correct the massive false negatives, we construct the Extended COCO Validation (ECCV) Caption dataset by supplying the missing associations with machine and human annotators. We employ five state-of-the-art ITM models with diverse properties for our annotation process. Our dataset provides x3.6 positive image-to-caption associations and x8.5 caption-to-image associations compared to the original MS-COCO. We also propose to use an informative ranking-based metric mAP@R, rather than the popular Recall@K (R@K). We re-evaluate the existing 25 VL models on existing and proposed benchmarks. Our findings are that the existing benchmarks, such as COCO 1K R@K, COCO 5K R@K, CxC R@1 are highly correlated with each other, while the rankings change when we shift to the ECCV mAP@R. Lastly, we delve into the effect of the bias introduced by the choice of machine annotator. Source code and dataset are available at https://github.com/naver-ai/eccv-caption
Text matching is a fundamental technique in both information retrieval and natural language processing. Text matching tasks share the same paradigm that determines the relationship between two given texts. The relationships vary from task to task, e.g.~relevance in document retrieval, semantic alignment in paraphrase identification and answerable judgment in question answering. However, the essential signals for text matching remain in a finite scope, i.e.~exact matching, semantic matching, and inference matching. Ideally, a good text matching model can learn to capture and aggregate these signals for different matching tasks to achieve competitive performance, while recent state-of-the-art text matching models, e.g.~Pre-trained Language Models (PLMs), are hard to generalize. It is because the end-to-end supervised learning on task-specific dataset makes model overemphasize the data sample bias and task-specific signals instead of the essential matching signals. To overcome this problem, we adopt a specialization-generalization training strategy and refer to it as Match-Prompt. In specialization stage, descriptions of different matching tasks are mapped to a few prompt tokens. In generalization stage, matching model explores the essential matching signals by being trained on diverse matching tasks. High diverse matching tasks avoid model fitting the data bias on a specific task, so that model can focus on learning the essential matching signals. Meanwhile, the prompt tokens obtained in the first step help the model distinguish different task-specific matching signals. Experimental results on public datasets show that Match-Prompt can improve multi-task generalization capability of PLMs in text matching and yield better in-domain multi-task, out-of-domain multi-task and new task adaptation performance than multi-task and task-specific models trained by previous fine-tuning paradigm.
Despite astonishing progress, generating realistic images of complex scenes remains a challenging problem. Recently, layout-to-image synthesis approaches have attracted much interest by conditioning the generator on a list of bounding boxes and corresponding class labels. However, previous approaches are very restrictive because the set of labels is fixed a priori. Meanwhile, text-to-image synthesis methods have substantially improved and provide a flexible way for conditional image generation. In this work, we introduce dense text-to-image (DT2I) synthesis as a new task to pave the way toward more intuitive image generation. Furthermore, we propose DTC-GAN, a novel method to generate images from semantically rich region descriptions, and a multi-modal region feature matching loss to encourage semantic image-text matching. Our results demonstrate the capability of our approach to generate plausible images of complex scenes using region captions.
As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates. However, existing studies mainly focus on the recommendation scenario, while neglecting another important channel for linking positions with job seekers, i.e. search. Intuitively, search history contains rich user behavior in job seeking, reflecting important evidence for job intention of users. In this paper, we present a novel Search History enhanced Person-Job Fit model, named as SHPJF. To utilize both text content from jobs/resumes and search histories from users, we propose two components with different purposes. For text matching component, we design a BERT-based text encoder for capturing the semantic interaction between resumes and job descriptions. For intention modeling component, we design two kinds of intention modeling approaches based on the Transformer architecture, either based on the click sequence or query text sequence. To capture underlying job intentions, we further propose an intention clustering technique to identify and summarize the major intentions from search logs. Extensive experiments on a large real-world recruitment dataset have demonstrated the effectiveness of our approach.
Reasoning-based approaches have demonstrated their powerful ability for the task of image-text matching. In this work, two issues are addressed for image-text matching. First, for reasoning processing, conventional approaches have no ability to find and use multi-level hierarchical similarity information. To solve this problem, a hierarchical similarity reasoning module is proposed to automatically extract context information, which is then co-exploited with local interaction information for efficient reasoning. Second, previous approaches only consider learning single-stream similarity alignment (i.e., image-to-text level or text-to-image level), which is inadequate to fully use similarity information for image-text matching. To address this issue, a two-stream architecture is developed to decompose image-text matching into image-to-text level and text-to-image level similarity computation. These two issues are investigated by a unifying framework that is trained in an end-to-end manner, namely two-stream hierarchical similarity reasoning network. The extensive experiments performed on the two benchmark datasets of MSCOCO and Flickr30K show the superiority of the proposed approach as compared to existing state-of-the-art methods.
In recent years, Internet memes have been widely used in online chatting. Compared with text-based communication, conversations become more expressive and attractive when Internet memes are incorporated. This paper presents our solutions for the Meme incorporated Open-domain Dialogue (MOD) Challenge of DSTC10, where three tasks are involved: text response modeling, meme retrieval, and meme emotion classification. Firstly, we leverage a large-scale pre-trained dialogue model for coherent and informative response generation. Secondly, based on interaction-based text-matching, our approach can retrieve appropriate memes with good generalization ability. Thirdly, we propose to model the emotion flow (EF) in conversations and introduce an auxiliary task of emotion description prediction (EDP) to boost the performance of meme emotion classification. Experimental results on the MOD dataset demonstrate that our methods can incorporate Internet memes into dialogue systems effectively.
The short text matching task employs a model to determine whether two short texts have the same semantic meaning or intent. Existing short text matching models usually rely on the content of short texts which are lack information or missing some key clues. Therefore, the short texts need external knowledge to complete their semantic meaning. To address this issue, we propose a new short text matching framework for introducing external knowledge to enhance the short text contextual representation. In detail, we apply a self-attention mechanism to enrich short text representation with external contexts. Experiments on two Chinese datasets and one English dataset demonstrate that our framework outperforms the state-of-the-art short text matching models.
Motivated by recent findings from cognitive neural science, we advocate the use of a dual-level model for concept representations: the embodied level consists of concept-oriented feature representations, and the symbolic level consists of concept graphs. Embodied concept representations are modality specific and exist in the form of feature vectors in a feature space. Symbolic concept representations, on the other hand, are amodal and language specific, and exist in the form of word / knowledge-graph embeddings in a concept / knowledge space. The human conceptual system comprises both embodied representations and symbolic representations, which typically interact to drive conceptual processing. As such, we further advocate the use of dual embodied-symbolic concept representations for deep learning. To demonstrate their usage and value, we discuss two important use cases: embodied-symbolic knowledge distillation for few-shot class incremental learning, and embodied-symbolic fused representation for image-text matching. Dual embodied-symbolic concept representations are the foundation for deep learning and symbolic AI integration. We discuss two important examples of such integration: scene graph generation with knowledge graph bridging, and multimodal knowledge graphs.
In this paper, we pay attention to the issue which is usually overlooked, i.e., \textit{similarity should be determined from different perspectives}. To explore this issue, we release a Multi-Perspective Text Similarity (MPTS) dataset, in which sentence similarities are labeled from twelve perspectives. Furthermore, we conduct a series of experimental analysis on this task by retrofitting some famous text matching models. Finally, we obtain several conclusions and baseline models, laying the foundation for the following investigation of this issue. The dataset and code are publicly available at Github\footnote{\url{https://github.com/autoliuweijie/MPTS}
Previous vision-language pre-training models mainly construct multi-modal inputs with tokens and objects (pixels) followed by performing cross-modality interaction between them. We argue that the input of only tokens and object features limits high-level semantic alignment like phrase-to-region grounding. Meanwhile, multi-level alignments are inherently consistent and able to facilitate the representation learning synergistically. Therefore, in this paper, we propose to learn Multi-level semantic alignment for Vision-language Pre-TRaining (MVPTR). In MVPTR, we follow the nested structure of both modalities to introduce concepts as high-level semantics. To ease the learning from multi-modal multi-level inputs, our framework is split into two stages, the first stage focuses on intra-modality multi-level representation learning, the second enforces interactions across modalities via both coarse-grained and fine-grained semantic alignment tasks. In addition to the commonly used image-text matching and masked language model tasks, we introduce a masked concept recovering task in the first stage to enhance the concept representation learning, and two more tasks in the second stage to explicitly encourage multi-level alignments across modalities. Our code is available at https://github.com/Junction4Nako/mvp_pytorch.
Referring expression grounding is an important and challenging task in computer vision. To avoid the laborious annotation in conventional referring grounding, unpaired referring grounding is introduced, where the training data only contains a number of images and queries without correspondences. The few existing solutions to unpaired referring grounding are still preliminary, due to the challenges of learning image-text matching and lack of the top-down guidance with unpaired data. In this paper, we propose a novel bidirectional cross-modal matching (BiCM) framework to address these challenges. Particularly, we design a query-aware attention map (QAM) module that introduces top-down perspective via generating query-specific visual attention maps. A cross-modal object matching (COM) module is further introduced, which exploits the recently emerged image-text matching pretrained model, CLIP, to predict the target objects from a bottom-up perspective. The top-down and bottom-up predictions are then integrated via a similarity funsion (SF) module. We also propose a knowledge adaptation matching (KAM) module that leverages unpaired training data to adapt pretrained knowledge to the target dataset and task. Experiments show that our framework outperforms previous works by 6.55% and 9.94% on two popular grounding datasets.
Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream tasks, e.g., visual question answering, image-text retrieval and visual entailment, they do not possess the ability to generate. To tackle this problem, we propose Unified multimodal pre-training for both Vision-Language understanding and generation (UniVL). The proposed UniVL is capable of handling both understanding tasks and generative tasks. We augment existing pretraining paradigms that only use random masks with causal masks, i.e., triangular masks that mask out future tokens, such that the pre-trained models can have autoregressive generation abilities by design. We formulate several previous understanding tasks as a text generation task and propose to use prompt-based method for fine-tuning on different downstream tasks. Our experiments show that there is a trade-off between understanding tasks and generation tasks while using the same model, and a feasible way to improve both tasks is to use more data. Our UniVL framework attains comparable performance to recent vision-language pre-training methods on both understanding tasks and generation tasks. Moreover, we demostrate that prompt-based finetuning is more data-efficient - it outperforms discriminative methods in few-shot scenarios.
With the booming of pre-trained transformers, representation-based models based on Siamese transformer encoders have become mainstream techniques for efficient text matching. However, these models suffer from severe performance degradation due to the lack of interaction between the text pair, compared with interaction-based models. Prior arts attempt to address this through performing extra interaction for Siamese encoded representations, while the interaction during encoding is still ignored. To remedy this, we propose a \textit{Virtual} InteRacTion mechanism (VIRT) to transfer interactive knowledge from interaction-based models into Siamese encoders through attention map distillation. As a train-time-only component, VIRT could completely maintain the high efficiency of the Siamese structure and brings no extra computation cost during inference. To fully utilize the learned interactive knowledge, we further design a VIRT-adapted interaction strategy. Experimental results on multiple text matching datasets demonstrate that our method outperforms state-of-the-art representation-based models. What's more, VIRT can be easily integrated into existing representation-based methods to achieve further improvements.