Motivated by the need for accelerating text entry in augmentative and alternative communication (AAC) for people with severe motor impairments, we propose a paradigm in which phrases are abbreviated aggressively as primarily word-initial letters. Our approach is to expand the abbreviations into full-phrase options by leveraging conversation context with the power of pretrained large language models (LLMs). Through zero-shot, few-shot, and fine-tuning experiments on four public conversation datasets, we show that for replies to the initial turn of a dialog, an LLM with 64B parameters is able to exactly expand over 70% of phrases with abbreviation length up to 10, leading to an effective keystroke saving rate of up to about 77% on these exact expansions. Including a small amount of context in the form of a single conversation turn more than doubles abbreviation expansion accuracies compared to having no context, an effect that is more pronounced for longer phrases. Additionally, the robustness of models against typo noise can be enhanced through fine-tuning on noisy data.
In this paper, we introduce Kathaka, a model trained with a novel two-stage training process for neural speech synthesis with contextually appropriate prosody. In Stage I, we learn a prosodic distribution at the sentence level from mel-spectrograms available during training. In Stage II, we propose a novel method to sample from this learnt prosodic distribution using the contextual information available in text. To do this, we use BERT on text, and graph-attention networks on parse trees extracted from text. We show a statistically significant relative improvement of $13.2\%$ in naturalness over a strong baseline when compared to recordings. We also conduct an ablation study on variations of our sampling technique, and show a statistically significant improvement over the baseline in each case.
The Korean wave, which denotes the global popularity of South Korea's cultural economy, contributes to the increasing demand for the Korean language. However, as there does not exist any application for foreigners to learn Korean, this paper suggested a design of a novel Korean learning application. Speech recognition, speech-to-text, and speech-to-waveform are the three key systems in the proposed system. The Google API and the librosa library will transform the user's voice into a sentence and MFCC. The software will then display the user's phrase and answer, with mispronounced elements highlighted in red, allowing users to more easily recognize the incorrect parts of their pronunciation. Furthermore, the Siamese network might utilize those translated spectrograms to provide a similarity score, which could subsequently be used to offer feedback to the user. Despite the fact that we were unable to collect sufficient foreigner data for this research, it is notable that we presented a novel Korean pronunciation correction method for foreigners.
In this paper, we demonstrate that information retrieval can be accomplished with a single Transformer, in which all information about the corpus is encoded in the parameters of the model. To this end, we introduce the Differentiable Search Index (DSI), a new paradigm that learns a text-to-text model that maps string queries directly to relevant docids; in other words, a DSI model answers queries directly using only its parameters, dramatically simplifying the whole retrieval process. We study variations in how documents and their identifiers are represented, variations in training procedures, and the interplay between models and corpus sizes. Experiments demonstrate that given appropriate design choices, DSI significantly outperforms strong baselines such as dual encoder models. Moreover, DSI demonstrates strong generalization capabilities, outperforming a BM25 baseline in a zero-shot setup.
Cross-lingual word embeddings can be applied to several natural language processing applications across multiple languages. Unlike prior works that use word embeddings based on the Euclidean space, this short paper presents a simple and effective cross-lingual Word2Vec model that adapts to the Poincar\'e ball model of hyperbolic space to learn unsupervised cross-lingual word representations from a German-English parallel corpus. It has been shown that hyperbolic embeddings can capture and preserve hierarchical relationships. We evaluate the model on both hypernymy and analogy tasks. The proposed model achieves comparable performance with the vanilla Word2Vec model on the cross-lingual analogy task, the hypernymy task shows that the cross-lingual Poincar\'e Word2Vec model can capture latent hierarchical structure from free text across languages, which are absent from the Euclidean-based Word2Vec representations. Our results show that by preserving the latent hierarchical information, hyperbolic spaces can offer better representations for cross-lingual embeddings.
Research in Artificial Intelligence (AI)-assisted decision-making is experiencing tremendous growth with a constantly rising number of studies evaluating the effect of AI with and without techniques from the field of explainable AI (XAI) on human decision-making performance. However, as tasks and experimental setups vary due to different objectives, some studies report improved user decision-making performance through XAI, while others report only negligible effects. Therefore, in this article, we present an initial synthesis of existing research on XAI studies using a statistical meta-analysis to derive implications across existing research. We observe a statistically positive impact of XAI on users' performance. Additionally, first results might indicate that human-AI decision-making yields better task performance on text data. However, we find no effect of explanations on users' performance compared to sole AI predictions. Our initial synthesis gives rise to future research to investigate the underlying causes as well as contribute to further development of algorithms that effectively benefit human decision-makers in the form of explanations.
The classification of news headlines is an important direction in the field of NLP, and its data has the characteristics of compactness, uniqueness and various forms. Aiming at the problem that the traditional neural network model cannot adequately capture the underlying feature information of the data and cannot jointly extract key global features and deep local features, a dual-channel network model DC-EBAD based on the ERNIE pre-training model is proposed. Use ERNIE to extract the lexical, semantic and contextual feature information at the bottom of the text, generate dynamic word vector representations fused with context, and then use the BiLSTM-AT network channel to secondary extract the global features of the data and use the attention mechanism to give key parts higher The weight of the DPCNN channel is used to overcome the long-distance text dependence problem and obtain deep local features. The local and global feature vectors are spliced, and finally passed to the fully connected layer, and the final classification result is output through Softmax. The experimental results show that the proposed model improves the accuracy, precision and F1-score of news headline classification compared with the traditional neural network model and the single-channel model under the same conditions. It can be seen that it can perform well in the multi-classification application of news headline text under large data volume.
Recent years have seen remarkable progress of text generation in different contexts, such as the most common setting of generating text from scratch, and the emerging paradigm of retrieval-and-rewriting. Text infilling, which fills missing text portions of a sentence or paragraph, is also of numerous use in real life, yet is under-explored. Previous work has focused on restricted settings by either assuming single word per missing portion or limiting to a single missing portion to the end of the text. This paper studies the general task of text infilling, where the input text can have an arbitrary number of portions to be filled, each of which may require an arbitrary unknown number of tokens. We study various approaches for the task, including a self-attention model with segment-aware position encoding and bidirectional context modeling. We create extensive supervised data by masking out text with varying strategies. Experiments show the self-attention model greatly outperforms others, creating a strong baseline for future research.
Recent end-to-end trainable methods for scene text spotting, integrating detection and recognition, showed much progress. However, most of the current arbitrary-shape scene text spotters use region proposal networks (RPN) to produce proposals. RPN relies heavily on manually designed anchors and its proposals are represented with axis-aligned rectangles. The former presents difficulties in handling text instances of extreme aspect ratios or irregular shapes, and the latter often includes multiple neighboring instances into a single proposal, in cases of densely oriented text. To tackle these problems, we propose Mask TextSpotter v3, an end-to-end trainable scene text spotter that adopts a Segmentation Proposal Network (SPN) instead of an RPN. Our SPN is anchor-free and gives accurate representations of arbitrary-shape proposals. It is therefore superior to RPN in detecting text instances of extreme aspect ratios or irregular shapes. Furthermore, the accurate proposals produced by SPN allow masked RoI features to be used for decoupling neighboring text instances. As a result, our Mask TextSpotter v3 can handle text instances of extreme aspect ratios or irregular shapes, and its recognition accuracy won't be affected by nearby text or background noise. Specifically, we outperform state-of-the-art methods by 21.9 percent on the Rotated ICDAR 2013 dataset (rotation robustness), 5.9 percent on the Total-Text dataset (shape robustness), and achieve state-of-the-art performance on the MSRA-TD500 dataset (aspect ratio robustness). Code is available at: https://github.com/MhLiao/MaskTextSpotterV3
In this paper, we present a cross-modal recipe retrieval framework, Transformer-based Network for Large Batch Training (TNLBT), which is inspired by ACME~(Adversarial Cross-Modal Embedding) and H-T~(Hierarchical Transformer). TNLBT aims to accomplish retrieval tasks while generating images from recipe embeddings. We apply the Hierarchical Transformer-based recipe text encoder, the Vision Transformer~(ViT)-based recipe image encoder, and an adversarial network architecture to enable better cross-modal embedding learning for recipe texts and images. In addition, we use self-supervised learning to exploit the rich information in the recipe texts having no corresponding images. Since contrastive learning could benefit from a larger batch size according to the recent literature on self-supervised learning, we adopt a large batch size during training and have validated its effectiveness. In the experiments, the proposed framework significantly outperformed the current state-of-the-art frameworks in both cross-modal recipe retrieval and image generation tasks on the benchmark Recipe1M. This is the first work which confirmed the effectiveness of large batch training on cross-modal recipe embeddings.