The image-based multimodal automatic speech recognition (ASR) model enhances speech recognition performance by incorporating audio-related image. However, some works suggest that introducing image information to model does not help improving ASR performance. In this paper, we propose a novel approach effectively utilizing audio-related image information and set up VHASR, a multimodal speech recognition system that uses vision as hotwords to strengthen the model’s speech recognition capability. Our system utilizes a dual-stream architecture, which firstly transcribes the text on the two streams separately, and then combines the outputs. We evaluate the proposed model on four datasets: Flickr8k, ADE20k, COCO, and OpenImages. The experimental results show that VHASR can effectively utilize key information in images to enhance the model’s speech recognition ability. Its performance not only surpasses unimodal ASR, but also achieves SOTA among existing image-based multimodal ASR.

The prevalent approach for optimizing pre-trained language models in downstream tasks is fine-tuning. However, it is both time-consuming and memory-inefficient. In response, a more efficient method called Prefix Tuning, which insert learnable vectors into each Transformer layers, has been proposed and proven effective. Recent investigations reveal that prefix tokens carry context-specific information, prompting the hypothesis that enhancing their specialization can improve model performance. To address this, we propose Selective Prefix Tuning (SPT), integrating a selective mechanism inspired by selective self-attention. Additionally, we introduce Selective Loss (SL) to encourage diversity in prefix tokens. Extensive experiments validate the effectiveness of SPT in sentence and token classification tasks. We contribute insight into understanding the role of prefix in model adaptation.

Benchmark plays a pivotal role in assessing the advancements of large language models (LLMs). While numerous benchmarks have been proposed to evaluate LLMs’ capabilities, there is a notable absence of a dedicated benchmark for assessing their musical abilities. To address this gap, we present ZIQI-Eval, a comprehensive and large-scale music benchmark specifically designed to evaluate the music-related capabilities of LLMs.ZIQI-Eval encompasses a wide range of questions, covering 10 major categories and 56 subcategories, resulting in over 14,000 meticulously curated data entries. By leveraging ZIQI-Eval, we conduct a comprehensive evaluation over 16 LLMs to evaluate and analyze LLMs’ performance in the domain of music.Results indicate that all LLMs perform poorly on the ZIQI-Eval benchmark, suggesting significant room for improvement in their musical capabilities.With ZIQI-Eval, we aim to provide a standardized and robust evaluation framework that facilitates a comprehensive assessment of LLMs’ music-related abilities. The dataset is available at GitHub and HuggingFace.

Semantic entity recognition is an important task in the field of visually-rich document understanding. It distinguishes the semantic types of text by analyzing the position relationship between text nodes and the relation between text content. The existing document understanding models mainly focus on entity categories while ignoring the extraction of entity boundaries. We build a novel hypergraph attention document semantic entity recognition framework, HGA, which uses hypergraph attention to focus on entity boundaries and entity categories at the same time. It can conduct a more detailed analysis of the document text representation analyzed by the upstream model and achieves a better performance of semantic information. We apply this method on the basis of GraphLayoutLM to construct a new semantic entity recognition model HGALayoutLM. Our experiment results on FUNSD, CORD, XFUND and SROIE show that our method can effectively improve the performance of semantic entity recognition tasks based on the original model. The results of HGALayoutLM on FUNSD and XFUND reach the new state-of-the-art results.

Despite the rapid development of neural-based models, syntax still plays a crucial role in modern natural language processing. However, few studies have incorporated syntactic information into ancient Chinese understanding tasks due to the lack of syntactic annotation. This paper explores the role of syntax in ancient Chinese understanding based on the noisy syntax trees from unsupervised derivation and modern Chinese syntax parsers. On top of that, we propose a novel syntax encoding component – confidence-based syntax encoding network (cSEN) to alleviate the side effects from the existing noise caused by unsupervised syntax derivation and the incompatibility between ancient and modern Chinese. Experiments on two typical ancient Chinese understanding tasks, ancient poetry theme classification and ancient-modern Chinese translation, demonstrate that syntactic information can effectively enhance the understanding of ancient Chinese over strong baselines, and that the proposed cSEN plays an important role in noisy scenarios.

Entity alignment (EA) aims to identify equivalent entities from different Knowledge Graphs (KGs), which is a fundamental task for integrating KGs. Throughout its development, Graph Convolutional Network (GCN) has become one of the mainstream methods for EA. These GCN-based methods learn the representations of entities from two KGs by message passing mechanism and then make alignments via measuring the similarity between entity embeddings. The key idea that GCN works in EA is that entities with similar neighbor structures are highly likely to be aligned. However, the noisy neighbors of entities transfer invalid information, drown out equivalent information, lead to inaccurate entity embeddings, and finally reduce the performance of EA. Based on the Sinkhorn algorithm, we design a reliability measure for potential equivalent entities and propose Adaptive Graph Convolutional Network to deal with neighbor noises in GCN. During the training, the network dynamically updates the adaptive weights of relation triples to weaken the propagation of noises. While calculating entity similarity, it comprehensively considers the self-similarity and neighborhood similarity of the entity pair to alleviate the influence of noises. Furthermore, we design a straightforward but efficient strategy to construct pseudo alignments for unsupervised EA. Extensive experiments on benchmark datasets demonstrate that our framework outperforms the state-of-the-art methods in both supervised and unsupervised settings.

In this paper, we propose a new few-shot text classification method. Compared with supervised learning methods which require a large corpus of labeled documents, our method aims to make it possible to classify unlabeled text with few labeled data. To achieve this goal, we take advantage of advanced pre-trained language model to extract the semantic features of each document. Furthermore, we utilize an edge-labeling graph neural network to implicitly models the intra-cluster similarity and the inter-cluster dissimilarity of the documents. Finally, we take the results of the graph neural network as the input of a prototypical network to classify the unlabeled texts. We verify the effectiveness of our method on a sentiment analysis dataset and a relation classification dataset and achieve the state-of-the-art performance on both tasks.

Neural abstractive text summarization (NATS) has received a lot of attention in the past few years from both industry and academia. In this paper, we introduce an open-source toolkit, namely LeafNATS, for training and evaluation of different sequence-to-sequence based models for the NATS task, and for deploying the pre-trained models to real-world applications. The toolkit is modularized and extensible in addition to maintaining competitive performance in the NATS task. A live news blogging system has also been implemented to demonstrate how these models can aid blog/news editors by providing them suggestions of headlines and summaries of their articles.