Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network. In addition to the text recognition, the model is trained to label text parts using begin and end tags in an XML-like fashion. This model is made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process. It takes whole text documents as input and sequentially outputs characters, as well as logical layout tokens. Contrary to the existing segmentation-based approaches, the model is trained without using any segmentation label. We achieve competitive results on the READ 2016 dataset at page level, as well as double-page level with a CER of 3.53% and 3.69%, respectively. We also provide results for the RIMES 2009 dataset at page level, reaching 4.54% of CER. We provide all source code and pre-trained model weights at https://github.com/FactoDeepLearning/DAN.
Current methods for text-to-video retrieval (T2VR) are trained and tested on video-captioning oriented datasets such as MSVD, MSR-VTT and VATEX. A key property of these datasets is that videos are assumed to be temporally pre-trimmed with short duration, whilst the provided captions well describe the gist of the video content. Consequently, for a given paired video and caption, the video is supposed to be fully relevant to the caption. In reality, however, as queries are not known a priori, pre-trimmed video clips may not contain sufficient content to fully meet the query. This suggests a gap between the literature and the real world. To fill the gap, we propose in this paper a novel T2VR subtask termed Partially Relevant Video Retrieval (PRVR). An untrimmed video is considered to be partially relevant w.r.t. a given textual query if it contains a moment relevant to the query. PRVR aims to retrieve such partially relevant videos from a large collection of untrimmed videos. PRVR differs from single video moment retrieval and video corpus moment retrieval, as the latter two are to retrieve moments rather than untrimmed videos. We formulate PRVR as a multiple instance learning (MIL) problem, where a video is simultaneously viewed as a bag of video clips and a bag of video frames. Clips and frames represent video content at different time scales. We propose a Multi-Scale Similarity Learning (MS-SL) network that jointly learns clip-scale and frame-scale similarities for PRVR. Extensive experiments on three datasets (TVR, ActivityNet Captions, and Charades-STA) demonstrate the viability of the proposed method. We also show that our method can be used for improving video corpus moment retrieval.
The increasingly sophisticated and growing number of threat actors along with the sheer speed at which cyber attacks unfold, make timely identification of attacks imperative to an organisations' security. Consequently, persons responsible for security employ a large variety of information sources concerning emerging attacks, attackers' course of actions or indicators of compromise. However, a vast amount of the needed security information is available in unstructured textual form, which complicates the automated and timely extraction of attackers' Tactics, Techniques and Procedures (TTPs). In order to address this problem we systematically evaluate and compare different Natural Language Processing (NLP) and machine learning techniques used for security information extraction in research. Based on our investigations we propose a data processing pipeline that automatically classifies unstructured text according to attackers' tactics and techniques derived from a knowledge base of adversary tactics, techniques and procedures.
Prosody plays an important role in characterizing the style of a speaker or an emotion, but most non-parallel voice or emotion style transfer algorithms do not convert any prosody information. Two major components of prosody are pitch and rhythm. Disentangling the prosody information, particularly the rhythm component, from the speech is challenging because it involves breaking the synchrony between the input speech and the disentangled speech representation. As a result, most existing prosody style transfer algorithms would need to rely on some form of text transcriptions to identify the content information, which confines their application to high-resource languages only. Recently, SpeechSplit has made sizeable progress towards unsupervised prosody style transfer, but it is unable to extract high-level global prosody style in an unsupervised manner. In this paper, we propose AutoPST, which can disentangle global prosody style from speech without relying on any text transcriptions. AutoPST is an Autoencoder-based Prosody Style Transfer framework with a thorough rhythm removal module guided by the self-expressive representation learning. Experiments on different style transfer tasks show that AutoPST can effectively convert prosody that correctly reflects the styles of the target domains.
Vector quantized diffusion (VQ-Diffusion) is a powerful generative model for text-to-image synthesis, but sometimes can still generate low-quality samples or weakly correlated images with text input. We find these issues are mainly due to the flawed sampling strategy. In this paper, we propose two important techniques to further improve the sample quality of VQ-Diffusion. 1) We explore classifier-free guidance sampling for discrete denoising diffusion model and propose a more general and effective implementation of classifier-free guidance. 2) We present a high-quality inference strategy to alleviate the joint distribution issue in VQ-Diffusion. Finally, we conduct experiments on various datasets to validate their effectiveness and show that the improved VQ-Diffusion suppresses the vanilla version by large margins. We achieve an 8.44 FID score on MSCOCO, surpassing VQ-Diffusion by 5.42 FID score. When trained on ImageNet, we dramatically improve the FID score from 11.89 to 4.83, demonstrating the superiority of our proposed techniques.
In this paper, we explore how QuestEval, which is a Text-vs-Text metric, can be adapted for the evaluation of Data-to-Text Generation systems. QuestEval is a reference-less metric that compares the predictions directly to the structured input data by automatically asking and answering questions. Its adaptation to Data-to-Text is not straightforward as it requires multi-modal Question Generation and Answering (QG \& QA) systems. To this purpose, we propose to build synthetic multi-modal corpora that enables to train multi-modal QG/QA. The resulting metric is reference-less, multi-modal; it obtains state-of-the-art correlations with human judgement on the E2E and WebNLG benchmark.
In the field of car evaluation, more and more netizens choose to express their opinions on the Internet platform, and these comments will affect the decision-making of buyers and the trend of car word-of-mouth. As an important branch of natural language processing (NLP), sentiment analysis provides an effective research method for analyzing the sentiment types of massive car review texts. However, due to the lexical professionalism and large text noise of review texts in the automotive field, when a general sentiment analysis model is applied to car reviews, the accuracy of the model will be poor. To overcome these above challenges, we aim at the sentiment analysis task of car review texts. From the perspective of word vectors, pre-training is carried out by means of whole word mask of proprietary vocabulary in the automotive field, and then training data is carried out through the strategy of an adversarial training set. Based on this, we propose a car review text sentiment analysis model based on adversarial training and whole word mask BERT(ATWWM-BERT).
The temporal answering grounding in the video (TAGV) is a new task naturally derived from temporal sentence grounding in the video (TSGV). Given an untrimmed video and a text question, this task aims at locating the matching span from the video that can semantically answer the question. Existing methods tend to formulate the TAGV task with a visual span-based question answering (QA) approach by matching the visual frame span queried by the text question. However, due to the weak correlations and huge gaps of the semantic features between the textual question and visual answer, existing methods adopting visual span predictor perform poorly in the TAGV task. To bridge these gaps, we propose a visual-prompt text span localizing (VPTSL) method, which introduces the timestamped subtitles as a passage to perform the text span localization for the input text question, and prompts the visual highlight features into the pre-trained language model (PLM) for enhancing the joint semantic representations. Specifically, the context query attention is utilized to perform cross-modal interaction between the extracted textual and visual features. Then, the highlight features are obtained through the video-text highlighting for the visual prompt. To alleviate semantic differences between textual and visual features, we design the text span predictor by encoding the question, the subtitles, and the prompted visual highlight features with the PLM. As a result, the TAGV task is formulated to predict the span of subtitles matching the visual answer. Extensive experiments on the medical instructional dataset, namely MedVidQA, show that the proposed VPTSL outperforms the state-of-the-art (SOTA) method by 28.36% in terms of mIOU with a large margin, which demonstrates the effectiveness of the proposed visual prompt and the text span predictor.
Video question answering (VideoQA) is a complex task that requires diverse multi-modal data for training. Manual annotation of question and answers for videos, however, is tedious and prohibits scalability. To tackle this problem, recent methods consider zero-shot settings with no manual annotation of visual question-answer. In particular, a promising approach adapts frozen autoregressive language models pretrained on Web-scale text-only data to multi-modal inputs. In contrast, we here build on frozen bidirectional language models (BiLM) and show that such an approach provides a stronger and cheaper alternative for zero-shot VideoQA. In particular, (i) we combine visual inputs with the frozen BiLM using light trainable modules, (ii) we train such modules using Web-scraped multi-modal data, and finally (iii) we perform zero-shot VideoQA inference through masked language modeling, where the masked text is the answer to a given question. Our proposed approach, FrozenBiLM, outperforms the state of the art in zero-shot VideoQA by a significant margin on a variety of datasets, including LSMDC-FiB, iVQA, MSRVTT-QA, MSVD-QA, ActivityNet-QA, TGIF-FrameQA, How2QA and TVQA. It also demonstrates competitive performance in the few-shot and fully-supervised setting. Our code and models will be made publicly available at https://antoyang.github.io/frozenbilm.html.
The Differentiable Search Index (DSI) is a new, emerging paradigm for information retrieval. Unlike traditional retrieval architectures where index and retrieval are two different and separate components, DSI uses a single transformer model to perform both indexing and retrieval. In this paper, we identify and tackle an important issue of current DSI models: the data distribution mismatch that occurs between the DSI indexing and retrieval processes. Specifically, we argue that, at indexing, current DSI methods learn to build connections between long document texts and their identifies, but then at retrieval, short query texts are provided to DSI models to perform the retrieval of the document identifiers. This problem is further exacerbated when using DSI for cross-lingual retrieval, where document text and query text are in different languages. To address this fundamental problem of current DSI models we propose a simple yet effective indexing framework for DSI called DSI-QG. In DSI-QG, documents are represented by a number of relevant queries generated by a query generation model at indexing time. This allows DSI models to connect a document identifier to a set of query texts when indexing, hence mitigating data distribution mismatches present between the indexing and the retrieval phases. Empirical results on popular mono-lingual and cross-lingual passage retrieval benchmark datasets show that DSI-QG significantly outperforms the original DSI model.