Text-VQA aims at answering questions that require understanding the textual cues in an image. Despite the great progress of existing Text-VQA methods, their performance suffers from insufficient human-labeled question-answer (QA) pairs. However, we observe that, in general, the scene text is not fully exploited in the existing datasets -- only a small portion of the text in each image participates in the annotated QA activities. This results in a huge waste of useful information. To address this deficiency, we develop a new method to generate high-quality and diverse QA pairs by explicitly utilizing the existing rich text available in the scene context of each image. Specifically, we propose, TAG, a text-aware visual question-answer generation architecture that learns to produce meaningful, and accurate QA samples using a multimodal transformer. The architecture exploits underexplored scene text information and enhances scene understanding of Text-VQA models by combining the generated QA pairs with the initial training data. Extensive experimental results on two well-known Text-VQA benchmarks (TextVQA and ST-VQA) demonstrate that our proposed TAG effectively enlarges the training data that helps improve the Text-VQA performance without extra labeling effort. Moreover, our model outperforms state-of-the-art approaches that are pre-trained with extra large-scale data. Code is available at https://github.com/HenryJunW/TAG.
Recently, there has been an increasing interest in building question answering (QA) models that reason across multiple modalities, such as text and images. However, QA using images is often limited to just picking the answer from a pre-defined set of options. In addition, images in the real world, especially in news, have objects that are co-referential to the text, with complementary information from both modalities. In this paper, we present a new QA evaluation benchmark with 1,384 questions over news articles that require cross-media grounding of objects in images onto text. Specifically, the task involves multi-hop questions that require reasoning over image-caption pairs to identify the grounded visual object being referred to and then predicting a span from the news body text to answer the question. In addition, we introduce a novel multimedia data augmentation framework, based on cross-media knowledge extraction and synthetic question-answer generation, to automatically augment data that can provide weak supervision for this task. We evaluate both pipeline-based and end-to-end pretraining-based multimedia QA models on our benchmark, and show that they achieve promising performance, while considerably lagging behind human performance hence leaving large room for future work on this challenging new task.
The Earth's surface is continually changing, and identifying changes plays an important role in urban planning and sustainability. Although change detection techniques have been successfully developed for many years, these techniques are still limited to experts and facilitators in related fields. In order to provide every user with flexible access to change information and help them better understand land-cover changes, we introduce a novel task: change detection-based visual question answering (CDVQA) on multi-temporal aerial images. In particular, multi-temporal images can be queried to obtain high level change-based information according to content changes between two input images. We first build a CDVQA dataset including multi-temporal image-question-answer triplets using an automatic question-answer generation method. Then, a baseline CDVQA framework is devised in this work, and it contains four parts: multi-temporal feature encoding, multi-temporal fusion, multi-modal fusion, and answer prediction. In addition, we also introduce a change enhancing module to multi-temporal feature encoding, aiming at incorporating more change-related information. Finally, effects of different backbones and multi-temporal fusion strategies are studied on the performance of CDVQA task. The experimental results provide useful insights for developing better CDVQA models, which are important for future research on this task.
We focus on Multimodal Machine Reading Comprehension (M3C) where a model is expected to answer questions based on given passage (or context), and the context and the questions can be in different modalities. Previous works such as RecipeQA have proposed datasets and cloze-style tasks for evaluation. However, we identify three critical biases stemming from the question-answer generation process and memorization capabilities of large deep models. These biases makes it easier for a model to overfit by relying on spurious correlations or naive data patterns. We propose a systematic framework to address these biases through three Control-Knobs that enable us to generate a test bed of datasets of progressive difficulty levels. We believe that our benchmark (referred to as Meta-RecipeQA) will provide, for the first time, a fine grained estimate of a model's generalization capabilities. We also propose a general M3C model that is used to realize several prior SOTA models and motivate a novel hierarchical transformer based reasoning network (HTRN). We perform a detailed evaluation of these models with different language and visual features on our benchmark. We observe a consistent improvement with HTRN over SOTA (~18% in Visual Cloze task and ~13% in average over all the tasks). We also observe a drop in performance across all the models when testing on RecipeQA and proposed Meta-RecipeQA (e.g. 83.6% versus 67.1% for HTRN), which shows that the proposed dataset is relatively less biased. We conclude by highlighting the impact of the control knobs with some quantitative results.
Existing question answering (QA) techniques are created mainly to answer questions asked by humans. But in educational applications, teachers often need to decide what questions they should ask, in order to help students to improve their narrative understanding capabilities. We design an automated question-answer generation (QAG) system for this education scenario: given a story book at the kindergarten to eighth-grade level as input, our system can automatically generate QA pairs that are capable of testing a variety of dimensions of a student's comprehension skills. Our proposed QAG model architecture is demonstrated using a new expert-annotated FairytaleQA dataset, which has 278 child-friendly storybooks with 10,580 QA pairs. Automatic and human evaluations show that our model outperforms state-of-the-art QAG baseline systems. On top of our QAG system, we also start to build an interactive story-telling application for the future real-world deployment in this educational scenario.
This paper targets the problem of procedural multimodal machine comprehension (M3C). This task requires an AI to comprehend given steps of multimodal instructions and then answer questions. Compared to vanilla machine comprehension tasks where an AI is required only to understand a textual input, procedural M3C is more challenging as the AI needs to comprehend both the temporal and causal factors along with multimodal inputs. Recently Yagcioglu et al. [35] introduced RecipeQA dataset to evaluate M3C. Our first contribution is the introduction of two new M3C datasets- WoodworkQA and DecorationQA with 16K and 10K instructional procedures, respectively. We then evaluate M3C using a textual cloze style question-answering task and highlight an inherent bias in the question answer generation method from [35] that enables a naive baseline to cheat by learning from only answer choices. This naive baseline performs similar to a popular method used in question answering- Impatient Reader [6] that uses attention over both the context and the query. We hypothesized that this naturally occurring bias present in the dataset affects even the best performing model. We verify our proposed hypothesis and propose an algorithm capable of modifying the given dataset to remove the bias elements. Finally, we report our performance on the debiased dataset with several strong baselines. We observe that the performance of all methods falls by a margin of 8% - 16% after correcting for the bias. We hope these datasets and the analysis will provide valuable benchmarks and encourage further research in this area.
A large majority of American adults get at least some of their news from the Internet. Even though many online news products have the goal of informing their users about the news, they lack scalable and reliable tools for measuring how well they are achieving this goal, and therefore have to resort to noisy proxy metrics (e.g., click-through rates or reading time) to track their performance. As a first step towards measuring news informedness at a scale, we study the problem of quiz-style multiple-choice question generation, which may be used to survey users about their knowledge of recent news. In particular, we formulate the problem as two sequence-to-sequence tasks: question-answer generation (QAG) and distractor, or incorrect answer, generation (DG). We introduce NewsQuizQA, the first dataset intended for quiz-style question-answer generation, containing 20K human written question-answer pairs from 5K news article summaries. Using this dataset, we propose a series of novel techniques for applying large pre-trained Transformer encoder-decoder models, namely PEGASUS and T5, to the tasks of question-answer generation and distractor generation. We show that our models outperform strong baselines using both automated metrics and human raters. We provide a case study of running weekly quizzes on real-world users via the Google Surveys platform over the course of two months. We found that users generally found the automatically generated questions to be educational and enjoyable. Finally, to serve the research community, we are releasing the NewsQuizQA dataset.
We study a novel task, Video Question-Answer Generation (VQAG), for challenging Video Question Answering (Video QA) task in multimedia. Due to expensive data annotation costs, many widely used, large-scale Video QA datasets such as Video-QA, MSVD-QA and MSRVTT-QA are automatically annotated using Caption Question Generation (CapQG) which inputs captions instead of the video itself. As captions neither fully represent a video, nor are they always practically available, it is crucial to generate question-answer pairs based on a video via Video Question-Answer Generation (VQAG). Existing video-to-text (V2T) approaches, despite taking a video as the input, only generate a question alone. In this work, we propose a novel model Generator-Pretester Network that focuses on two components: (1) The Joint Question-Answer Generator (JQAG) which generates a question with its corresponding answer to allow Video Question "Answering" training. (2) The Pretester (PT) verifies a generated question by trying to answer it and checks the pretested answer with both the model's proposed answer and the ground truth answer. We evaluate our system with the only two available large-scale human-annotated Video QA datasets and achieves state-of-the-art question generation performances. Furthermore, using our generated QA pairs only on the Video QA task, we can surpass some supervised baselines. We apply our generated questions to Video QA applications and surpasses some supervised baselines using generated questions only. As a pre-training strategy, we outperform both CapQG and transfer learning approaches when employing semi-supervised (20%) or fully supervised learning with annotated data. These experimental results suggest the novel perspectives for Video QA training.
One of the most crucial challenges in question answering (QA) is the scarcity of labeled data, since it is costly to obtain question-answer (QA) pairs for a target text domain with human annotation. An alternative approach to tackle the problem is to use automatically generated QA pairs from either the problem context or from large amount of unstructured texts (e.g. Wikipedia). In this work, we propose a hierarchical conditional variational autoencoder (HCVAE) for generating QA pairs given unstructured texts as contexts, while maximizing the mutual information between generated QA pairs to ensure their consistency. We validate our Information Maximizing Hierarchical Conditional Variational AutoEncoder (Info-HCVAE) on several benchmark datasets by evaluating the performance of the QA model (BERT-base) using only the generated QA pairs (QA-based evaluation) or by using both the generated and human-labeled pairs (semi-supervised learning) for training, against state-of-the-art baseline models. The results show that our model obtains impressive performance gains over all baselines on both tasks, using only a fraction of data for training.
The ability to ask questions is important in both human and machine intelligence. Learning to ask questions helps knowledge acquisition, improves question-answering and machine reading comprehension tasks, and helps a chatbot to keep the conversation flowing with a human. Existing question generation models are ineffective at generating a large amount of high-quality question-answer pairs from unstructured text, since given an answer and an input passage, question generation is inherently a one-to-many mapping. In this paper, we propose Answer-Clue-Style-aware Question Generation (ACS-QG), which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a human asks questions. Our system consists of: i) an information extractor, which samples from the text multiple types of assistive information to guide question generation; ii) neural question generators, which generate diverse and controllable questions, leveraging the extracted assistive information; and iii) a neural quality controller, which removes low-quality generated data based on text entailment. We compare our question generation models with existing approaches and resort to voluntary human evaluation to assess the quality of the generated question-answer pairs. The evaluation results suggest that our system dramatically outperforms state-of-the-art neural question generation models in terms of the generation quality, while being scalable in the meantime. With models trained on a relatively smaller amount of data, we can generate 2.8 million quality-assured question-answer pairs from a million sentences found in Wikipedia.
Typical active learning strategies are designed for tasks, such as classification, with the assumption that the output space is mutually exclusive. The assumption that these tasks always have exactly one correct answer has resulted in the creation of numerous uncertainty-based measurements, such as entropy and least confidence, which operate over a model's outputs. Unfortunately, many real-world vision tasks, like visual question answering and image captioning, have multiple correct answers, causing these measurements to overestimate uncertainty and sometimes perform worse than a random sampling baseline. In this paper, we propose a new paradigm that estimates uncertainty in the model's internal hidden space instead of the model's output space. We specifically study a manifestation of this problem for visual question answer generation (VQA), where the aim is not to classify the correct answer but to produce a natural language answer, given an image and a question. Our method overcomes the paraphrastic nature of language. It requires a semantic space that structures the model's output concepts and that enables the usage of techniques like dropout-based Bayesian uncertainty. We build a visual-semantic space that embeds paraphrases close together for any existing VQA model. We empirically show state-of-art active learning results on the task of VQA on two datasets, being 5 times more cost-efficient on Visual Genome and 3 times more cost-efficient on VQA 2.0.
IBM Watson is a cognitive computing system capable of question answering in natural languages. It is believed that IBM Watson can understand large corpora and answer relevant questions more effectively than any other question-answering system currently available. To unleash the full power of Watson, however, we need to train its instance with a large number of well-prepared question-answer pairs. Obviously, manually generating such pairs in a large quantity is prohibitively time consuming and significantly limits the efficiency of Watson's training. Recently, a large-scale dataset of over 30 million question-answer pairs was reported. Under the assumption that using such an automatically generated dataset could relieve the burden of manual question-answer generation, we tried to use this dataset to train an instance of Watson and checked the training efficiency and accuracy. According to our experiments, using this auto-generated dataset was effective for training Watson, complementing manually crafted question-answer pairs. To the best of the authors' knowledge, this work is the first attempt to use a large-scale dataset of automatically generated question-answer pairs for training IBM Watson. We anticipate that the insights and lessons obtained from our experiments will be useful for researchers who want to expedite Watson training leveraged by automatically generated question-answer pairs.