Self-training for Named Entity Recognition (NER) aims at identifying named entities and their types in the text using self-training to fully make use of the limited labeled data and a large amount of unlabeled data. The major challenge in self-training is confirmation bias where incorrect pseudo-labels increase errors. Many efforts have been made to address this challenge, but few labeled data limit their performance. In this paper, we introduce Large Language Model (LLM) into self-training to select high-quality pseudo-labels leveraging its rich knowledge and few-shot learning capability. Specifically, we design a comprehensive prompt to improve the judgment performance of LLM, where the prompt incorporates task rules mined by LLM itself to fully leverage labeled data. In addition, to reduce the impact of LLM's hallucinations, we adopt a collaborative pseudo-label selection based on combined confidence and calibration-guided probability smoothing. Our empirical study conducted on several NER datasets shows that our method outperforms state-of-the-art approaches. The code is available at https://github.com/cheniison/llm-judged-ST.

In recent years, graph anomaly detection has gained considerable attention and has found extensive applications in various domains such as social, financial, and communication networks. However, anomalies in graph-structured data present unique challenges, including label scarcity, ill-defined anomalies, and varying anomaly types, making supervised or semi-supervised methods unreliable. Researchers often adopt unsupervised approaches to address these challenges, assuming that anomalies deviate significantly from the normal data distribution. Yet, when the available data is insufficient, capturing the normal distribution accurately and comprehensively becomes difficult. To overcome this limitation, we propose to utilize external graph data (i.e., graph data in the wild) to help anomaly detection tasks. This naturally raises the question: How can we use external data to help graph anomaly detection task? To answer this question, we propose a novel framework Wild-GAD. Our framework is built upon a unified database, UniWildGraph, which comprises a large and diverse collection of graph data with broad domain coverage, ample data volume, and a unified feature space. We further develop selection criteria based on representativity and diversity to identify the most suitable external data for each anomaly detection task. Extensive experiments on six real-world test datasets demonstrate the effectiveness of Wild-GAD. Compared to the baseline methods, our framework has an average 18% AUCROC and 32% AUCPR improvement over the best-competing methods.

Multimodal knowledge bases (MMKBs) provide cross-modal aligned knowledge crucial for multimodal tasks. However, the images in existing MMKBs are generally collected for entities in encyclopedia knowledge graphs. Therefore, detailed groundings of visual semantics with linguistic concepts are lacking, which are essential for the visual concept cognition ability of multimodal models. Addressing this gap, we introduce M2 ConceptBase, the first concept-centric MMKB. M2 ConceptBase models concepts as nodes with associated images and detailed textual descriptions. We propose a context-aware multimodal symbol grounding approach to align concept-image and concept-description pairs using context information from image-text datasets. Comprising 951K images and 152K concepts, M2 ConceptBase links each concept to an average of 6.27 images and a single description, ensuring comprehensive visual and textual semantics. Human studies confirm more than 95% alignment accuracy, underscoring its quality. Additionally, our experiments demonstrate that M2 ConceptBase significantly enhances VQA model performance on the OK-VQA task. M2 ConceptBase also substantially improves the fine-grained concept understanding capabilities of multimodal large language models through retrieval augmentation in two concept-related tasks, highlighting its value.

Extracting entities and relations from text is a significant task of information extraction. Existing extraction models often straightforwardly produce their confident prediction results without any reconsideration or double-checking, resulting in avoidable mistakes and sub-optimal performance. In this paper, we propose a novel coarse-to-fine extraction framework, which first extracts high-potential relations as well as entities via knowledge distillation, and then rechecks the predictions via handcrafted natural language inference (NLI) task in a fine-grained manner. Specifically, based on the knowledge distillation mechanism, we train multiple teacher models iteratively through an adaptive loss function for making one teacher concentrate more on the data that others are incompetent for. Then, these complementary teacher models are utilized to provide valuable soft-label information for training a considerate student model, enabling it to generate reliable preliminary predictions. Further, these generated potential relations and entities are formulated as hypotheses, together with the original sentences as premises, serving as the input for an NLI model. Considering the linguistic diversity of relational expression, we automatically generate various semantic templates for hypotheses through an$\mathcal{N}$-gram mining strategy. Moreover, due to the existence of multi-fact sentences, a relation-guided Gaussian attention is designed to reduce the gap between the single-relation hypothesis and the multi-relation premise. To implement efficient training, we also develop several ways to generate high-quality negative samples, which help the NLI model learn to identify errors. Experimental results show that the proposed method is effective and outperforms other strong baselines on public benchmarks.

Multi-modal knowledge graphs (MMKGs) combine different modal data (e.g., text and image) for a comprehensive understanding of entities. Despite the recent progress of large-scale MMKGs, existing MMKGs neglect the multi-aspect nature of entities, limiting the ability to comprehend entities from various perspectives.In this paper, we construct AspectMMKG, the first MMKG with aspect-related images by matching images to different entity aspects. Specifically, we collect aspect-related images from a knowledge base, and further extract aspect-related sentences from the knowledge base as queries to retrieve a large number of aspect-related images via an online image search engine. Finally, AspectMMKG contains 2,380 entities, 18,139 entity aspects, and 645,383 aspect-related images. We demonstrate the usability of AspectMMKG in entity aspect linking (EAL) downstream task and show that previous EAL models achieve a new state-of-the-art performance with the help of AspectMMKG.To facilitate the research on aspect-related MMKG, we further propose an aspect-related image retrieval (AIR) model, that aims to correct and expand aspect-related images in AspectMMKG.We train an AIR model to learn the relationship between entity image and entity aspect-related images by incorporating entity image, aspect, and aspect image information. Experimental results indicate that the AIR model could retrieve suitable images for a given entity w.r.t different aspects.

In recent years, graph pre-training has gained significant attention, focusing on acquiring transferable knowledge from unlabeled graph data to improve downstream performance. Despite these recent endeavors, the problem of negative transfer remains a major concern when utilizing graph pre-trained models to downstream tasks. Previous studies made great efforts on the issue of what to pre-train and how to pre-train by designing a variety of graph pre-training and fine-tuning strategies. However, there are cases where even the most advanced "pre-train and fine-tune" paradigms fail to yield distinct benefits. This paper introduces a generic framework W2PGNN to answer the crucial question of when to pre-train (.e., in what situations could we take advantage of graph pre-training) before performing effortful pre-training or fine-tuning. We start from a new perspective to explore the complex generative mechanisms from the pre-training data to downstream data. In particular, W2PGNN first fits the pre-training data into graphon bases, each element of graphon basis (i.e., a graphon) identifies a fundamental transferable pattern shared by a collection of pre-training graphs. All convex combinations of graphon bases give rise to a generator space, from which graphs generated form the solution space for those downstream data that can benefit from pre-training. In this manner, the feasibility of pre-training can be quantified as the generation probability of the downstream data from any generator in the generator space. W2PGNN offers three broad applications: providing the application scope of graph pre-trained models, quantifying the feasibility of pre-training, and assistance in selecting pre-training data to enhance downstream performance. We provide a theoretically sound solution for the first application and extensive empirical justifications for the latter two applications.

Cross-Lingual Summarization (CLS) aims at generating summaries in one language for the given documents in another language. CLS has attracted wide research attention due to its practical significance in the multi-lingual world. Though great contributions have been made, existing CLS works typically focus on short documents, such as news and guides. Different from these short texts, long documents such as academic articles usually discuss complicated subjects and consist of thousands of words, making them non-trivial to process and summarize. To promote CLS research on long documents, we construct Perseus, the first long-document CLS dataset which collects about 94K Chinese scientific documents paired with English summaries. The average length of documents in Perseus is more than 2000 tokens. As a preliminary study on long-document CLS, we build and evaluate various CLS baselines, including pipeline and end-to-end methods. Experimental results on Perseus show the superiority of the end-to-end baseline, which performs the best among all methods. Furthermore, to provide a deeper understanding, we manually analyze the model outputs and discuss specific challenges faced by current approaches. We hope that our work could benchmark long-document CLS and benefit future studies.

Sports game summarization aims at generating sports news from live commentaries. However, existing datasets are all constructed through automated collection and cleaning processes, resulting in a lot of noise. Besides, current works neglect the knowledge gap between live commentaries and sports news, which limits the performance of sports game summarization. In this paper, we introduce K-SportsSum, a new dataset with two characteristics: (1) K-SportsSum collects a large amount of data from massive games. It has 7,854 commentary-news pairs. To improve the quality, K-SportsSum employs a manual cleaning process; (2) Different from existing datasets, to narrow the knowledge gap, K-SportsSum further provides a large-scale knowledge corpus that contains the information of 523 sports teams and 14,724 sports players. Additionally, we also introduce a knowledge-enhanced summarizer that utilizes both live commentaries and the knowledge to generate sports news. Extensive experiments on K-SportsSum and SportsSum datasets show that our model achieves new state-of-the-art performances. Qualitative analysis and human study further verify that our model generates more informative sports news.

Sports game summarization aims to generate news articles from live text commentaries. A recent state-of-the-art work, SportsSum, not only constructs a large benchmark dataset, but also proposes a two-step framework. Despite its great contributions, the work has three main drawbacks: 1) the noise existed in SportsSum dataset degrades the summarization performance; 2) the neglect of lexical overlap between news and commentaries results in low-quality pseudo-labeling algorithm; 3) the usage of directly concatenating rewritten sentences to form news limits its practicability. In this paper, we publish a new benchmark dataset SportsSum2.0, together with a modified summarization framework. In particular, to obtain a clean dataset, we employ crowd workers to manually clean the original dataset. Moreover, the degree of lexical overlap is incorporated into the generation of pseudo labels. Further, we introduce a reranker-enhanced summarizer to take into account the fluency and expressiveness of the summarized news. Extensive experiments show that our model outperforms the state-of-the-art baseline.