Employing large-scale pre-trained model CLIP to conduct video-text retrieval task (VTR) has become a new trend, which exceeds previous VTR methods. Though, due to the heterogeneity of structures and contents between video and text, previous CLIP-based models are prone to overfitting in the training phase, resulting in relatively poor retrieval performance. In this paper, we propose a multi-stream Corpus Alignment network with single gate Mixture-of-Experts (CAMoE) and a novel Dual Softmax Loss (DSL) to solve the two heterogeneity. The CAMoE employs Mixture-of-Experts (MoE) to extract multi-perspective video representations, including action, entity, scene, etc., then align them with the corresponding part of the text. In this stage, we conduct massive explorations towards the feature extraction module and feature alignment module. DSL is proposed to avoid the one-way optimum-match which occurs in previous contrastive methods. Introducing the intrinsic prior of each pair in a batch, DSL serves as a reviser to correct the similarity matrix and achieves the dual optimal match. DSL is easy to implement with only one-line code but improves significantly. The results show that the proposed CAMoE and DSL are of strong efficiency, and each of them is capable of achieving State-of-The-Art (SOTA) individually on various benchmarks such as MSR-VTT, MSVD, and LSMDC. Further, with both of them, the performance is advanced to a big extend, surpassing the previous SOTA methods for around 4.6\% R@1 in MSR-VTT.
The real-time prediction of business processes using historical event data is an important capability of modern business process monitoring systems. Existing process prediction methods are able to also exploit the data perspective of recorded events, in addition to the control-flow perspective. However, while well-structured numerical or categorical attributes are considered in many prediction techniques, almost no technique is able to utilize text documents written in natural language, which can hold information critical to the prediction task. In this paper, we illustrate the design, implementation, and evaluation of a novel text-aware process prediction model based on Long Short-Term Memory (LSTM) neural networks and natural language models. The proposed model can take categorical, numerical and textual attributes in event data into account to predict the activity and timestamp of the next event, the outcome, and the cycle time of a running process instance. Experiments show that the text-aware model is able to outperform state-of-the-art process prediction methods on simulated and real-world event logs containing textual data.
Information Extraction (IE) tasks are commonly studied topics in various domains of research. Hence, the community continuously produces multiple techniques, solutions, and tools to perform such tasks. However, running those tools and integrating them within existing infrastructure requires time, expertise, and resources. One pertinent task here is triples extraction and linking, where structured triples are extracted from a text and aligned to an existing Knowledge Graph (KG). In this paper, we present PLUMBER, the first framework that allows users to manually and automatically create suitable IE pipelines from a community-created pool of tools to perform triple extraction and alignment on unstructured text. Our approach provides an interactive medium to alter the pipelines and perform IE tasks. A short video to show the working of the framework for different use-cases is available online under: https://www.youtube.com/watch?v=XC9rJNIUv8g
Scholars have recently drawn attention to a range of controversial issues posed by the use of computer vision for automatically generating descriptions of people in images. Despite these concerns, automated image description has become an important tool to ensure equitable access to information for blind and low vision people. In this paper, we investigate the ethical dilemmas faced by companies that have adopted the use of computer vision for producing alt text: textual descriptions of images for blind and low vision people, We use Facebook's automatic alt text tool as our primary case study. First, we analyze the policies that Facebook has adopted with respect to identity categories, such as race, gender, age, etc., and the company's decisions about whether to present these terms in alt text. We then describe an alternative -- and manual -- approach practiced in the museum community, focusing on how museums determine what to include in alt text descriptions of cultural artifacts. We compare these policies, using notable points of contrast to develop an analytic framework that characterizes the particular apprehensions behind these policy choices. We conclude by considering two strategies that seem to sidestep some of these concerns, finding that there are no easy ways to avoid the normative dilemmas posed by the use of computer vision to automate alt text.
Recently, various neural encoder-decoder models pioneered by Seq2Seq framework have been proposed to achieve the goal of generating more abstractive summaries by learning to map input text to output text. At a high level, such neural models can freely generate summaries without any constraint on the words or phrases used. Moreover, their format is closer to human-edited summaries and output is more readable and fluent. However, the neural model's abstraction ability is a double-edged sword. A commonly observed problem with the generated summaries is the distortion or fabrication of factual information in the article. This inconsistency between the original text and the summary has caused various concerns over its applicability, and the previous evaluation methods of text summarization are not suitable for this issue. In response to the above problems, the current research direction is predominantly divided into two categories, one is to design fact-aware evaluation metrics to select outputs without factual inconsistency errors, and the other is to develop new summarization systems towards factual consistency. In this survey, we focus on presenting a comprehensive review of these fact-specific evaluation methods and text summarization models.
Web-crawled datasets have enabled remarkable generalization capabilities in recent image-text models such as CLIP (Contrastive Language-Image pre-training) or Flamingo, but little is known about the dataset creation processes. In this work, we introduce a testbed of six publicly available data sources - YFCC, LAION, Conceptual Captions, WIT, RedCaps, Shutterstock - to investigate how pre-training distributions induce robustness in CLIP. We find that the performance of the pre-training data varies substantially across distribution shifts, with no single data source dominating. Moreover, we systematically study the interactions between these data sources and find that combining multiple sources does not necessarily yield better models, but rather dilutes the robustness of the best individual data source. We complement our empirical findings with theoretical insights from a simple setting, where combining the training data also results in diluted robustness. In addition, our theoretical model provides a candidate explanation for the success of the CLIP-based data filtering technique recently employed in the LAION dataset. Overall our results demonstrate that simply gathering a large amount of data from the web is not the most effective way to build a pre-training dataset for robust generalization, necessitating further study into dataset design.
The recent literature in text classification is biased towards short text sequences (e.g., sentences or paragraphs). In real-world applications, multi-page multi-paragraph documents are common and they cannot be efficiently encoded by vanilla Transformer-based models. We compare different Transformer-based Long Document Classification (TrLDC) approaches that aim to mitigate the computational overhead of vanilla transformers to encode much longer text, namely sparse attention and hierarchical encoding methods. We examine several aspects of sparse attention (e.g., size of local attention window, use of global attention) and hierarchical (e.g., document splitting strategy) transformers on four document classification datasets covering different domains. We observe a clear benefit from being able to process longer text, and, based on our results, we derive practical advice of applying Transformer-based models on long document classification tasks.
Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality, annotated datasets with only a few manual annotations, thus strongly reducing annotation cost and effort. For this purpose, we combine an active learning (AL) approach with a pre-trained language model to semi-automatically identify annotation categories in the given text documents. To highlight our research direction's potential, we evaluate the approach on the task of identifying frames in news articles. Our preliminary results show that employing AL strongly reduces the number of annotations for correct classification of even these complex and subtle frames. On the framing dataset, the AL approach needs only 16.3\% of the annotations to reach the same performance as a model trained on the full dataset.
Text Classification finds interesting applications in the pickup and delivery services industry where customers require one or more items to be picked up from a location and delivered to a certain destination. Classifying these customer transactions into multiple categories helps understand the market needs for different customer segments. Each transaction is accompanied by a text description provided by the customer to describe the products being picked up and delivered which can be used to classify the transaction. BERT-based models have proven to perform well in Natural Language Understanding. However, the product descriptions provided by the customers tend to be short, incoherent and code-mixed (Hindi-English) text which demands fine-tuning of such models with manually labelled data to achieve high accuracy. Collecting this labelled data can prove to be expensive. In this paper, we explore Active Learning strategies to label transaction descriptions cost effectively while using BERT to train a transaction classification model. On TREC-6, AG's News Corpus and an internal dataset, we benchmark the performance of BERT across different Active Learning strategies in Multi-Class Text Classification.