Document-level event factuality identification (DEFI) assesses the veracity degree to which an event mentioned in a document has happened, which is crucial for many natural language processing tasks. Previous work assesses event factuality by solely relying on the semantic information within a single document, which fails to identify hard cases where the document itself is hallucinative or counterfactual. There is also a pressing need for more suitable data of this kind. To tackle these issues, we construct Factualusion, a novel corpus with hallucination features that can be used not only for DEFI but can also be applied for hallucination evaluation for large language models. We further propose Trucidator, a graph-based framework that constructs intra-document and cross-document graphs and employs a multi-task learning paradigm to acquire more robust node embeddings, leveraging cross-document inference for more accurate identification. Experiments show that our proposed framework outperformed several baselines, demonstrating the effectiveness of our method.

In previous research on zero-shot cross-lingual event argument extraction (EAE), almost no one has considered constructing models that utilize language-independent information to promote cross-lingual transfer and improve model performance. In the paper, building on previous studies, we take them a step further. Our approach encodes structures of the event and gets the relevance among argument roles by regarding EAE as a language generation problem and introducing language-independent information of event argument roles to the model’s input. In order to facilitate cross-lingual transfer, we also introduce language-independent templates to express structures of the event argument that are consistent with all languages. Our suggested approach fine-tunes multilingual pre-trained generative language models to extract event arguments from the input passages (the process of extracting these arguments combines the role relevance learned from the input language-independent role information), which fills language-independent templates and ultimately generates the required string sentences. After training on source languages, the model is applied immediately to target languages in EAE. Extensive experiments on two datasets which contain English, Arabic and Spanish show that our proposed approach results in a substantial improvement compared with previous studies on zero-shot cross-lingual EAE. Additional analysis illustrates the interpretability of our method.

Cross-Document Fact Verification (CDFV) aims to retrieve related evidence from multiple documents to verify the factuality of a given claim, relying on the quality of the retrieved evidence. However, existing CDFV approaches heavily depend on specific heuristics or rule-based strategies, leveraging similarity measures of semantic or surface forms between claims and documents for evidence retrieval. To address the problem above, we propose an Evidential Graph Attention neTwork (EGAT) for CDFV. EGAT utilizes graph attention network to capture relationships between sentences, updating their representations and obtaining more expressive sentence embeddings. To acquire credible evidence, EGAT leverages golden evidence which is manually annotated and capable of verifying the factuality of the claim. Sentences in the graph that are most relevant to the gold evidence are selected as evidence sentences. To enhance the reliability of claim verification, EGAT utilizes a homogeneous network to fuse the information of the claim and evidence, which makes full use of the information provided by evidence and reduces the duplication of work in the process of claim verification. Experimental results confirm the effectiveness of EGAT in retrieving credible evidence and demonstrate improvements in achieving accurate claim verification.

In the age of social media, the spread of information on the Internet transcends the geographical restrictions, and any netizen on the Internet can express views, which is the main reason that rumors on the Internet can spread rapidly. To regulate and stop the malicious spread of rumors, rumor detection automatically has become a hot field. Few previous studies consider both the temporal text information and the structural information in rumor detection, ignoring the correlation between the events. To address the above issues, this paper proposes a novel hierarchical structure based on event and topic, i.e., TEH-GCN (Topic-Event Hierarchical Graph Convolutional Networks), for rumor detection. TEH-GCN first fully learns the feature representation of rumor events at the event-level by combining the temporal and the structural information characteristics, then it uses graph network to interact the features of the rumor events in topic-level. The experimental results on the three datasets indicate that the proposed TEH-GCN can achieve better performance compared with various benchmarks.

The rhetorical question is a commonly used rhetorical technique in modern Chinese. It can be divided into explicit rhetorical questions and implicit rhetorical questions according to whether it contains rhetorical cues. The implicit rhetorical questions express more emotion and are more complex in form, which has caught the attention of researchers. Most previous works relied too much on manually designed features or massive labeled data, failing to address the integration of multi-level information in sentences. In this paper, we propose a novel implicit rhetorical questions recognition framework named Hierarchical Information Fusion Graph Neural Networks (HIFGN). In particular, in order to improve the robustness of the encoder, we design a contrastive adversarial representation learning approach to map samples into the representation space. Moreover, different subgraphs of the heterogeneous graph are constructed to help the model extract profound sentence information from diverse perspectives. The experimental results on the Chinese rhetorical questions corpus show that the proposed HIFGN model achieves state-of-the-art performance on the task of implicit rhetorical questions recognition.

Due to the huge number of users and its easy access, rumors often spread widely and rapidly on social media. In order to monitor and discriminate rumor message dynamicly during propagation, automatic Rumor Detection (RD) has become an important task in NLP. This paper studies automatic event-level rumor detection on the web, which is a collection of posts in chronological order. Previous studies did not consider the connection between texts and propagation structure, which will miss useful information of temporal order or propagation structure. To address this issue, we propose a novel method Temporal Incorporating Structure Networks (TISN) to learn information from both plain text and propagation structure. Especially, we utilize transformer encoders to extract text information, and employ GCN (Graph Convolutional Network) to learn the patterns of rumor propagation. In addition, we enhance the influence of objective information by source tweet. Our method effectively achieves good performance by combining both structured and plain textual information. Experimental results on three datasets show the proposed method TISN achieves better performance than several baselines.

Grapheme-to-phoneme (G2P) conversion is an indispensable part of the Chinese Mandarin text-to-speech (TTS) system, and the core of G2P conversion is to solve the problem of polyphone disambiguation, which is to pick up the correct pronunciation for several candidates for a Chinese polyphonic character.In this paper, we propose a Chinese polyphone BERT model to predict the pronunciations of Chinese polyphonic characters.Firstly, we create 741 new Chinese monophonic characters from 354 source Chinese polyphonic characters by pronunciation.Then we get a Chinese polyphone BERT by extending a pre-trained Chinese BERT with 741 new Chinese monophonic characters and adding a corresponding embedding layer for new tokens, which is initialized by the embeddings of source Chinese polyphonic characters.In this way, we can turn the polyphone disambiguation task into a pre-training task of the Chinese polyphone BERT.Experimental results demonstrate the effectiveness of the proposed model, and the polyphone BERT model obtain 2% (from 92.1% to 94.1%) improvement of average accuracy compared with the BERT-based classifier model, which is the prior state-of-the-art in polyphone disambiguation.

A complete event description is usually scattered over several sentences and documents, so that how to mine a complete event from several documents or event mentions is an issue currently. This paper proposes an event fusion approach to merge a set of event mentions which distributed over several HTML files into a complete event. Firstly it introduced plain features and structured features into the similarity calculation and applied the hierarchical clustering algorithm to cluster event mentions. Then it proposed an event fusion approach based on a ranking model to merge those argument instances with highest ranking rate in each cluster to form a complete event. The experimental result showed that our approach was effective and could achieve higher accuracy than the baseline.