One major problem in Natural Language Processing is the automatic analysis and representation of human language. Human language is ambiguous and deeper understanding of semantics and creating human-to-machine interaction have required an effort in creating the schemes for act of communication and building common-sense knowledge bases for the 'meaning' in texts. This paper introduces computational methods for semantic analysis and the quantifying the meaning of short scientific texts. Computational methods extracting semantic feature are used to analyse the relations between texts of messages and 'representations of situations' for a newly created large collection of scientific texts, Leicester Scientific Corpus. The representation of scientific-specific meaning is standardised by replacing the situation representations, rather than psychological properties, with the vectors of some attributes: a list of scientific subject categories that the text belongs to. First, this paper introduces 'Meaning Space' in which the informational representation of the meaning is extracted from the occurrence of the word in texts across the scientific categories, i.e., the meaning of a word is represented by a vector of Relative Information Gain about the subject categories. Then, the meaning space is statistically analysed for Leicester Scientific Dictionary-Core and we investigate 'Principal Components of the Meaning' to describe the adequate dimensions of the meaning. The research in this paper conducts the base for the geometric representation of the meaning of texts.
Achieving realistic, vivid, and human-like synthesized conversational gestures conditioned on multi-modal data is still an unsolved problem, due to the lack of available datasets, models and standard evaluation metrics. To address this, we build Body-Expression-Audio-Text dataset, BEAT, which has i) 76 hours, high-quality, multi-modal data captured from 30 speakers talking with eight different emotions and in four different languages, ii) 32 millions frame-level emotion and semantic relevance annotations.Our statistical analysis on BEAT demonstrates the correlation of conversational gestures with facial expressions, emotions, and semantics, in addition to the known correlation with audio, text, and speaker identity. Qualitative and quantitative experiments demonstrate metrics' validness, ground truth data quality, and baseline's state-of-the-art performance. To the best of our knowledge, BEAT is the largest motion capture dataset for investigating the human gestures, which may contribute to a number of different research fields including controllable gesture synthesis, cross-modality analysis, emotional gesture recognition. The data, code and model will be released for research.
Although a polygon is a more accurate representation than an upright bounding box for text detection, the annotations of polygons are extremely expensive and challenging. Unlike existing works that employ fully-supervised training with polygon annotations, we propose a novel text detection system termed SelfText Beyond Polygon (SBP) with Bounding Box Supervision (BBS) and Dynamic Self Training (DST), where training a polygon-based text detector with only a limited set of upright bounding box annotations. For BBS, we firstly utilize the synthetic data with character-level annotations to train a Skeleton Attention Segmentation Network (SASN). Then the box-level annotations are adopted to guide the generation of high-quality polygon-liked pseudo labels, which can be used to train any detectors. In this way, our method achieves the same performance as text detectors trained with polygon annotations (i.e., both are 85.0% F-score for PSENet on ICDAR2015 ). For DST, through dynamically removing the false alarms, it is able to leverage limited labeled data as well as massive unlabeled data to further outperform the expensive baseline. We hope SBP can provide a new perspective for text detection to save huge labeling costs.
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent natural language generation, naturally leading to development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation. However, it is also investigated that such generation includes hallucinated texts, which makes the performances of text generation fail to meet users' expectations in many real-world scenarios. In order to address this issue, studies in evaluation and mitigation methods of hallucinations have been presented in various tasks, but have not been reviewed in a combined manner. In this survey, we provide a broad overview of the research progress and challenges in the hallucination problem of NLG. The survey is organized into two big divisions: (i) a general overview of metrics, mitigation methods, and future directions; (ii) task-specific research progress for hallucinations in a large set of downstream tasks: abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey could facilitate collaborative efforts among researchers in these tasks.
Language models that utilize extensive self-supervised pre-training from unlabeled text, have recently shown to significantly advance the state-of-the-art performance in a variety of language understanding tasks. However, it is yet unclear if and how these recent models can be harnessed for conducting text-based recommendations. In this work, we introduce RecoBERT, a BERT-based approach for learning catalog-specialized language models for text-based item recommendations. We suggest novel training and inference procedures for scoring similarities between pairs of items, that don't require item similarity labels. Both the training and the inference techniques were designed to utilize the unlabeled structure of textual catalogs, and minimize the discrepancy between them. By incorporating four scores during inference, RecoBERT can infer text-based item-to-item similarities more accurately than other techniques. In addition, we introduce a new language understanding task for wine recommendations using similarities based on professional wine reviews. As an additional contribution, we publish annotated recommendations dataset crafted by human wine experts. Finally, we evaluate RecoBERT and compare it to various state-of-the-art NLP models on wine and fashion recommendations tasks.
Synthesizing high-resolution realistic images from text descriptions is a challenging task. Almost all existing text-to-image methods employ stacked generative adversarial networks as the backbone, utilize cross-modal attention mechanisms to fuse text and image features, and use extra networks to ensure text-image semantic consistency. The existing text-to-image models have three problems: 1) For the backbone, there are multiple generators and discriminators stacked for generating different scales of images making the training process slow and inefficient. 2) For semantic consistency, the existing models employ extra networks to ensure the semantic consistency increasing the training complexity and bringing an additional computational cost. 3) For the text-image feature fusion method, cross-modal attention is only applied a few times during the generation process due to its computational cost impeding fusing the text and image features deeply. To solve these limitations, we propose 1) a novel simplified text-to-image backbone which is able to synthesize high-quality images directly by one pair of generator and discriminator, 2) a novel regularization method called Matching-Aware zero-centered Gradient Penalty which promotes the generator to synthesize more realistic and text-image semantic consistent images without introducing extra networks, 3) a novel fusion module called Deep Text-Image Fusion Block which can exploit the semantics of text descriptions effectively and fuse text and image features deeply during the generation process. Compared with the previous text-to-image models, our DF-GAN is simpler and more efficient and achieves better performance. Extensive experiments and ablation studies on both Caltech-UCSD Birds 200 and COCO datasets demonstrate the superiority of the proposed model in comparison to state-of-the-art models.
Applying generative adversarial networks (GANs) to text-related tasks is challenging due to the discrete nature of language. One line of research resolves this issue by employing reinforcement learning (RL) and optimizing the next-word sampling policy directly in a discrete action space. Such methods compute the rewards from complete sentences and avoid error accumulation due to exposure bias. Other approaches employ approximation techniques that map the text to continuous representation in order to circumvent the non-differentiable discrete process. Particularly, autoencoder-based methods effectively produce robust representations that can model complex discrete structures. In this paper, we propose a novel text GAN architecture that promotes the collaborative training of the continuous-space and discrete-space methods. Our method employs an autoencoder to learn an implicit data manifold, providing a learning objective for adversarial training in a continuous space. Furthermore, the complete textual output is directly evaluated and updated via RL in a discrete space. The collaborative interplay between the two adversarial trainings effectively regularize the text representations in different spaces. The experimental results on three standard benchmark datasets show that our model substantially outperforms state-of-the-art text GANs with respect to quality, diversity, and global consistency.
Detecting keywords in texts is important for many text mining applications. Graph-based methods have been commonly used to automatically find the key concepts in texts, however, relevant information provided by embeddings has not been widely used to enrich the graph structure. Here we modeled texts co-occurrence networks, where nodes are words and edges are established either by contextual or semantical similarity. We compared two embedding approaches -- Word2vec and BERT -- to check whether edges created via word embeddings can improve the quality of the keyword extraction method. We found that, in fact, the use of virtual edges can improve the discriminability of co-occurrence networks. The best performance was obtained when we considered low percentages of addition of virtual (embedding) edges. A comparative analysis of structural and dynamical network metrics revealed the degree, PageRank, and accessibility are the metrics displaying the best performance in the model enriched with virtual edges.
Multimodal sentiment analysis has attracted increasing attention and lots of models have been proposed. However, the performance of the state-of-the-art models decreases sharply when they are deployed in the real world. We find that the main reason is that real-world applications can only access the text outputs by the automatic speech recognition (ASR) models, which may be with errors because of the limitation of model capacity. Through further analysis of the ASR outputs, we find that in some cases the sentiment words, the key sentiment elements in the textual modality, are recognized as other words, which makes the sentiment of the text change and hurts the performance of multimodal sentiment models directly. To address this problem, we propose the sentiment word aware multimodal refinement model (SWRM), which can dynamically refine the erroneous sentiment words by leveraging multimodal sentiment clues. Specifically, we first use the sentiment word position detection module to obtain the most possible position of the sentiment word in the text and then utilize the multimodal sentiment word refinement module to dynamically refine the sentiment word embeddings. The refined embeddings are taken as the textual inputs of the multimodal feature fusion module to predict the sentiment labels. We conduct extensive experiments on the real-world datasets including MOSI-Speechbrain, MOSI-IBM, and MOSI-iFlytek and the results demonstrate the effectiveness of our model, which surpasses the current state-of-the-art models on three datasets. Furthermore, our approach can be adapted for other multimodal feature fusion models easily. Data and code are available at https://github.com/albertwy/SWRM.
We present COCO-LM, a new self-supervised learning framework that pretrains Language Models by COrrecting challenging errors and COntrasting text sequences. COCO-LM employs an auxiliary language model to mask-and-predict tokens in original text sequences. It creates more challenging pretraining inputs, where noises are sampled based on their likelihood in the auxiliary language model. COCO-LM then pretrains with two tasks: The first task, corrective language modeling, learns to correct the auxiliary model's corruptions by recovering the original tokens. The second task, sequence contrastive learning, ensures that the language model generates sequence representations that are invariant to noises and transformations. In our experiments on the GLUE and SQuAD benchmarks, COCO-LM outperforms recent pretraining approaches in various pretraining settings and few-shot evaluations, with higher pretraining efficiency. Our analyses reveal that COCO-LM's advantages come from its challenging training signals, more contextualized token representations, and regularized sequence representations.