Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence

May 08, 2019
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon

Blind video decaptioning is a problem of automatically removing text overlays and inpainting the occluded parts in videos without any input masks. While recent deep learning based inpainting methods deal with a single image and mostly assume that the positions of the corrupted pixels are known, we aim at automatic text removal in video sequences without mask information. In this paper, we propose a simple yet effective framework for fast blind video decaptioning. We construct an encoder-decoder model, where the encoder takes multiple source frames that can provide visible pixels revealed from the scene dynamics. These hints are aggregated and fed into the decoder. We apply a residual connection from the input frame to the decoder output to enforce our network to focus on the corrupted regions only. Our proposed model was ranked in the first place in the ECCV Chalearn 2018 LAP Inpainting Competition Track2: Video decaptioning. In addition, we further improve this strong model by applying a recurrent feedback. The recurrent feedback not only enforces temporal coherence but also provides strong clues on where the corrupted pixels are. Both qualitative and quantitative experiments demonstrate that our full model produces accurate and temporally consistent video results in real time (50+ fps).

* Accepted at CVPR 2019 

  Access Paper or Ask Questions

Unsupervised Abbreviation Disambiguation Contextual disambiguation using word embeddings

Apr 01, 2019
Ciosici, Manuel, Sommer, Tobias, Assent, Ira

As abbreviations often have several distinct meanings, disambiguating their intended meaning in context is important for Machine Reading tasks such as document search, recommendation and question answering. Existing approaches mostly rely on labelled examples of abbreviations and their correct long forms, which is costly to generate and limits their applicability and flexibility. Importantly, they need to be subjected to a full empirical evaluation, which is cumbersome in practice. In this paper, we present an entirely unsupervised abbreviation disambiguation method (called UAD) that picks up abbreviation definitions from text. Creating distinct tokens per meaning, we learn context representations as word embeddings. We demonstrate how to further boost abbreviation disambiguation performance by obtaining better context representations from additional unstructured text. Our method is the first abbreviation disambiguation approach which features a transparent model that allows performance analysis without requiring full-scale evaluation, making it highly relevant for real-world deployments. In our thorough empirical evaluation, UAD achieves high performance on large real world document data sets from different domains and outperforms both baseline and state-of-the-art methods. UAD scales well and supports thousands of abbreviations with many different meanings with a single model.

  Access Paper or Ask Questions

Sparsemax and Relaxed Wasserstein for Topic Sparsity

Oct 22, 2018
Tianyi Lin, Zhiyue Hu, Xin Guo

Topic sparsity refers to the observation that individual documents usually focus on several salient topics instead of covering a wide variety of topics, and a real topic adopts a narrow range of terms instead of a wide coverage of the vocabulary. Understanding this topic sparsity is especially important for analyzing user-generated web content and social media, which are featured in the form of extremely short posts and discussions. As topic sparsity of individual documents in online social media increases, so does the difficulty of analyzing the online text sources using traditional methods. In this paper, we propose two novel neural models by providing sparse posterior distributions over topics based on the Gaussian sparsemax construction, enabling efficient training by stochastic backpropagation. We construct an inference network conditioned on the input data and infer the variational distribution with the relaxed Wasserstein (RW) divergence. Unlike existing works based on Gaussian softmax construction and Kullback-Leibler (KL) divergence, our approaches can identify latent topic sparsity with training stability, predictive performance, and topic coherence. Experiments on different genres of large text corpora have demonstrated the effectiveness of our models as they outperform both probabilistic and neural methods.

* 9 Pages. To appear in WSDM 2019 

  Access Paper or Ask Questions

Representation learning through cross-modal conditional teacher-student training for speech emotion recognition

Nov 30, 2021
Sundararajan Srinivasan, Zhaocheng Huang, Katrin Kirchhoff

Generic pre-trained speech and text representations promise to reduce the need for large labeled datasets on specific speech and language tasks. However, it is not clear how to effectively adapt these representations for speech emotion recognition. Recent public benchmarks show the efficacy of several popular self-supervised speech representations for emotion classification. In this study, we show that the primary difference between the top-performing representations is in predicting valence while the differences in predicting activation and dominance dimensions are less pronounced. However, we show that even the best-performing HuBERT representation underperforms on valence prediction compared to a multimodal model that also incorporates text representation. We address this shortcoming by injecting lexical information into the speech representation using the multimodal model as a teacher. To improve the efficacy of our approach, we propose a novel estimate of the quality of the emotion predictions, to condition teacher-student training. We report new audio-only state-of-the-art concordance correlation coefficient (CCC) values of 0.757, 0.627, 0.671 for activation, valence and dominance predictions, respectively, on the MSP-Podcast corpus, and also state-of-the-art values of 0.667, 0.582, 0.545 on the IEMOCAP corpus.

  Access Paper or Ask Questions

Deep Keyphrase Completion

Oct 29, 2021
Yu Zhao, Jia Song, Huali Feng, Fuzhen Zhuang, Qing Li, Xiaojie Wang, Ji Liu

Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval. Though previous studies have made substantial efforts for automated keyphrase extraction and generation, surprisingly, few studies have been made for \textit{keyphrase completion} (KPC). KPC aims to generate more keyphrases for document (e.g. scientific publication) taking advantage of document content along with a very limited number of known keyphrases, which can be applied to improve text indexing system, etc. In this paper, we propose a novel KPC method with an encoder-decoder framework. We name it \textit{deep keyphrase completion} (DKPC) since it attempts to capture the deep semantic meaning of the document content together with known keyphrases via a deep learning framework. Specifically, the encoder and the decoder in DKPC play different roles to make full use of the known keyphrases. The former considers the keyphrase-guiding factors, which aggregates information of known keyphrases into context. On the contrary, the latter considers the keyphrase-inhibited factor to inhibit semantically repeated keyphrase generation. Extensive experiments on benchmark datasets demonstrate the efficacy of our proposed model.

  Access Paper or Ask Questions

Local Correlation Clustering with Asymmetric Classification Errors

Aug 11, 2021
Jafar Jafarov, Sanchit Kalhan, Konstantin Makarychev, Yury Makarychev

In the Correlation Clustering problem, we are given a complete weighted graph $G$ with its edges labeled as "similar" and "dissimilar" by a noisy binary classifier. For a clustering $\mathcal{C}$ of graph $G$, a similar edge is in disagreement with $\mathcal{C}$, if its endpoints belong to distinct clusters; and a dissimilar edge is in disagreement with $\mathcal{C}$ if its endpoints belong to the same cluster. The disagreements vector, $\text{dis}$, is a vector indexed by the vertices of $G$ such that the $v$-th coordinate $\text{dis}_v$ equals the weight of all disagreeing edges incident on $v$. The goal is to produce a clustering that minimizes the $\ell_p$ norm of the disagreements vector for $p\geq 1$. We study the $\ell_p$ objective in Correlation Clustering under the following assumption: Every similar edge has weight in the range of $[\alpha\mathbf{w},\mathbf{w}]$ and every dissimilar edge has weight at least $\alpha\mathbf{w}$ (where $\alpha \leq 1$ and $\mathbf{w}>0$ is a scaling parameter). We give an $O\left((\frac{1}{\alpha})^{\frac{1}{2}-\frac{1}{2p}}\cdot \log\frac{1}{\alpha}\right)$ approximation algorithm for this problem. Furthermore, we show an almost matching convex programming integrality gap.

* 24 pages, 2 figures. The conference version of this paper appeared in the proceedings of ICML 2021 

  Access Paper or Ask Questions

On the Design of Strategic Task Recommendations for Sustainable Crowdsourcing-Based Content Moderation

Jun 04, 2021
Sainath Sanga, Venkata Sriram Siddhardh Nadendla

Crowdsourcing-based content moderation is a platform that hosts content moderation tasks for crowd workers to review user submissions (e.g. text, images and videos) and make decisions regarding the admissibility of the posted content, along with a gamut of other tasks such as image labeling and speech-to-text conversion. In an attempt to reduce cognitive overload at the workers and improve system efficiency, these platforms offer personalized task recommendations according to the worker's preferences. However, the current state-of-the-art recommendation systems disregard the effects on worker's mental health, especially when they are repeatedly exposed to content moderation tasks with extreme content (e.g. violent images, hate-speech). In this paper, we propose a novel, strategic recommendation system for the crowdsourcing platform that recommends jobs based on worker's mental status. Specifically, this paper models interaction between the crowdsourcing platform's recommendation system (leader) and the worker (follower) as a Bayesian Stackelberg game where the type of the follower corresponds to the worker's cognitive atrophy rate and task preferences. We discuss how rewards and costs should be designed to steer the game towards desired outcomes in terms of maximizing the platform's productivity, while simultaneously improving the working conditions of crowd workers.

* Presented at International Workshop on Autonomous Agents for Social Good (AASG), May 2021 

  Access Paper or Ask Questions

Recognition and Processing of NATOM

Apr 29, 2021
YiPeng Deng, YinHui Luo

In this paper we show how to process the NOTAM (Notice to Airmen) data of the field in civil aviation. The main research contents are as follows: 1.Data preprocessing: For the original data of the NOTAM, there is a mixture of Chinese and English, and the structure is poor. The original data is cleaned, the Chinese data and the English data are processed separately, word segmentation is completed, and stopping-words are removed. Using Glove word vector methods to represent the data for using a custom mapping vocabulary. 2.Decoupling features and classifiers: In order to improve the ability of the text classification model to recognize minority samples, the overall model training process is decoupled from the perspective of the algorithm as a whole, divided into two stages of feature learning and classifier learning. The weights of the feature learning stage and the classifier learning stage adopt different strategies to overcome the influence of the head data and tail data of the imbalanced data set on the classification model. Experiments have proved that the use of decoupling features and classifier methods based on the neural network classification model can complete text multi-classification tasks in the field of civil aviation, and at the same time can improve the recognition accuracy of the minority samples in the data set.

  Access Paper or Ask Questions

UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training

Apr 01, 2021
Mingyang Zhou, Luowei Zhou, Shuohang Wang, Yu Cheng, Linjie Li, Zhou Yu, Jingjing Liu

Vision-and-language pre-training has achieved impressive success in learning multimodal representations between vision and language. To generalize this success to non-English languages, we introduce UC2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning. To tackle the scarcity problem of multilingual captions for image datasets, we first augment existing English-only datasets with other languages via machine translation (MT). Then we extend the standard Masked Language Modeling and Image-Text Matching training objectives to multilingual setting, where alignment between different languages is captured through shared visual context (i.e, using image as pivot). To facilitate the learning of a joint embedding space of images and all languages of interest, we further propose two novel pre-training tasks, namely Masked Region-to-Token Modeling (MRTM) and Visual Translation Language Modeling (VTLM), leveraging MT-enhanced translated data. Evaluation on multilingual image-text retrieval and multilingual visual question answering benchmarks demonstrates that our proposed framework achieves new state-of-the-art on diverse non-English benchmarks while maintaining comparable performance to monolingual pre-trained models on English tasks.

  Access Paper or Ask Questions

Cooperative Learning of Zero-Shot Machine Reading Comprehension

Mar 22, 2021
Hongyin Luo, Shang-Wen Li, Seunghak Yu, James Glass

Pretrained language models have significantly improved the performance of down-stream language understanding tasks, including extractive question answering, by providing high-quality contextualized word embeddings. However, learning question answering models still need large-scaled data annotation in specific domains. In this work, we propose a cooperative, self-play learning framework, REGEX, for question generation and answering. REGEX is built upon a masked answer extraction task with an interactive learning environment containing an answer entity REcognizer, a question Generator, and an answer EXtractor. Given a passage with a masked entity, the generator generates a question around the entity, and the extractor is trained to extract the masked entity with the generated question and raw texts. The framework allows the training of question generation and answering models on any text corpora without annotation. We further leverage a reinforcement learning technique to reward generating high-quality questions and to improve the answer extraction model's performance. Experiment results show that REGEX outperforms the state-of-the-art (SOTA) pretrained language models and zero-shot approaches on standard question-answering benchmarks, and yields the new SOTA performance under the zero-shot setting.

  Access Paper or Ask Questions