For document-level event argument extraction, existing role-based span selection strategies suffer from several limitations: (1) ignoring interrelations among arguments within an event instance; (2) relying on pre-trained language models to capture role semantics at either the event pattern or document, without leveraging pattern-instance associations. To address these limitations, this paper proposes a multi-round role representation learning strategy. First, we construct an event pattern-instance graph (EPIG) to comprehensively capture the role semantics embedded in various direct and indirect associations, including those among roles within event patterns, arguments within event instances, and the alignments between patterns and instances. Second, to enhance the learning of role node representation in the graph, we optimize the update mechanisms for both node and edge representations in the EPIG graph. By leveraging the graph attention network, we iteratively update the representations of role nodes and role edges. The role representations learned from the EPIG are then integrated into the original role representations, further enriching their semantic information. Finally, a role representation memory module and a multi-round learning strategy is proposed to retain and refine role representations learned from previously analyzed documents. This memory mechanism enhances the prediction performance in subsequent rounds of span selection. Extensive experiments on three datasets verify the effectiveness of the model.

The rapid development of Chinese large language models (LLMs) poses big challenges for efficient LLM evaluation. While current initiatives have introduced new benchmarks or evaluation platforms for assessing Chinese LLMs, many of these focus primarily on capabilities, usually overlooking potential alignment and safety issues. To address this gap, we introduce OpenEval, an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety. For capability assessment, we include 12 benchmark datasets to evaluate Chinese LLMs from 4 sub-dimensions: NLP tasks, disciplinary knowledge, commonsense reasoning and mathematical reasoning. For alignment assessment, OpenEval contains 7 datasets that examines the bias, offensiveness and illegalness in the outputs yielded by Chinese LLMs. To evaluate safety, especially anticipated risks (e.g., power-seeking, self-awareness) of advanced LLMs, we include 6 datasets. In addition to these benchmarks, we have implemented a phased public evaluation and benchmark update strategy to ensure that OpenEval is in line with the development of Chinese LLMs or even able to provide cutting-edge benchmark datasets to guide the development of Chinese LLMs. In our first public evaluation, we have tested a range of Chinese LLMs, spanning from 7B to 72B parameters, including both open-source and proprietary models. Evaluation results indicate that while Chinese LLMs have shown impressive performance in certain tasks, more attention should be directed towards broader aspects such as commonsense reasoning, alignment, and safety.

“尽管现有语言模型在自然语言处理任务上表现出色,但在深层次语义理解和常识推理方面仍有提升空间。本研究通过测试模型在儿童故事常识推理与寓意理解数据集(CRMUS)上的性能,探究如何增强模型在复杂任务中的能力。在本次任务的赛道二中,本研究使用多个7B以内的开源大模型(如Qwen、InternLM等)进行零样本推理,并选择表现最优的模型基于LoRA进行指令微调来提高其表现。除此之外,本研究还对数据集进行了分析与增强。研究结果显示,通过设计有效的指令格式和调整LoRA微调参数,模型在常识推理和寓意理解上的准确率显著提高。最终在本次任务的赛道二中取得第一名的成绩,该任务的评价指标Acc值为74.38,达到了较为先进的水准。”

Event Extraction is a crucial yet arduous task in natural language processing (NLP), as its performance is significantly hindered by laborious data annotation. Given this challenge, recent research has predominantly focused on two approaches: pretraining task-oriented models for event extraction and employing data augmentation techniques. These methods involve integrating external knowledge, semantic structures, or artificially generated samples using large language models (LLMs). However, their performances can be compromised due to two fundamental issues. Firstly, the alignment between the introduced knowledge and event extraction knowledge is crucial. Secondly, the introduction of data noise during the augmentation is unavoidable and can mislead the model’s convergence. To address these issues, we propose a Contrastive Event Aggregation Network with LLM-based Augmentation to promote low-resource learning and reduce data noise for event extraction. Different from the existing methods introducing linguistic knowledge into data augmentation, an event aggregation network is established to introduce event knowledge into supervised learning by constructing adaptively-updated semantic representation for trigger and argument. For LLM-based augmentation, we design a new scheme including a multi-pattern rephrasing paradigm and a data-free composing paradigm. Instead of directly using augmentation samples in the supervised task, we introduce span-level contrastive learning to reduce data noise. Experiments on the ACE2005 and ERE-EN demonstrate that our proposed approach achieves new state-of-the-art results on both of the two datasets.

What a large language model (LLM) would respond in ethically relevant context? In this paper, we curate a large benchmark CMoralEval for morality evaluation of Chinese LLMs. The data sources of CMoralEval are two-fold: 1) a Chinese TV program discussing Chinese moral norms with stories from the society and 2) a collection of Chinese moral anomies from various newspapers and academic papers on morality. With these sources, we aim to create a moral evaluation dataset characterized by diversity and authenticity. We develop a morality taxonomy and a set of fundamental moral principles that are not only rooted in traditional Chinese culture but also consistent with contemporary societal norms. To facilitate efficient construction and annotation of instances in CMoralEval, we establish a platform with AI-assisted instance generation to streamline the annotation process. These help us curate CMoralEval that encompasses both explicit moral scenarios (14,964 instances) and moral dilemma scenarios (15,424 instances), each with instances from different data sources. We conduct extensive experiments with CMoralEval to examine a variety of Chinese LLMs. Experiment results demonstrate that CMoralEval is a challenging benchmark for Chinese LLMs.

Sentence matching aims to identify the special relationship between two sentences, and plays a key role in many natural language processing tasks. However, previous studies mainly focused on exploiting either syntactic or semantic information for sentence matching, and no studies consider integrating both of them. In this study, we propose integrating syntax and semantics into BERT with sentence matching. In particular, we use an implicit syntax and semantics integration method that is less sensitive to the output structure information. Thus the implicit integration can alleviate the error propagation problem. The experimental results show that our approach has achieved state-of-the-art or competitive performance on several sentence matching datasets, demonstrating the benefits of implicitly integrating syntactic and semantic features in sentence matching.

Existing works, including ELMO and BERT, have revealed the importance of pre-training for NLP tasks. While there does not exist a single pre-training model that works best in all cases, it is of necessity to develop a framework that is able to deploy various pre-training models efficiently. For this purpose, we propose an assemble-on-demand pre-training toolkit, namely Universal Encoder Representations (UER). UER is loosely coupled, and encapsulated with rich modules. By assembling modules on demand, users can either reproduce a state-of-the-art pre-training model or develop a pre-training model that remains unexplored. With UER, we have built a model zoo, which contains pre-trained models based on different corpora, encoders, and targets (objectives). With proper pre-trained models, we could achieve new state-of-the-art results on a range of downstream datasets.

Analogical reasoning is effective in capturing linguistic regularities. This paper proposes an analogical reasoning task on Chinese. After delving into Chinese lexical knowledge, we sketch 68 implicit morphological relations and 28 explicit semantic relations. A big and balanced dataset CA8 is then built for this task, including 17813 questions. Furthermore, we systematically explore the influences of vector representations, context features, and corpora on analogical reasoning. With the experiments, CA8 is proved to be a reliable benchmark for evaluating Chinese word embeddings.

Subword-level information is crucial for capturing the meaning and morphology of words, especially for out-of-vocabulary entries. We propose CNN- and RNN-based subword-level composition functions for learning word embeddings, and systematically compare them with popular word-level and subword-level models (Skip-Gram and FastText). Additionally, we propose a hybrid training scheme in which a pure subword-level model is trained jointly with a conventional word-level embedding model based on lookup-tables. This increases the fitness of all types of subword-level word embeddings; the word-level embeddings can be discarded after training, leaving only compact subword-level representation with much smaller data volume. We evaluate these embeddings on a set of intrinsic and extrinsic tasks, showing that subword-level models have advantage on tasks related to morphology and datasets with high OOV rate, and can be combined with other types of embeddings.

The existing word representation methods mostly limit their information source to word co-occurrence statistics. In this paper, we introduce ngrams into four representation methods: SGNS, GloVe, PPMI matrix, and its SVD factorization. Comprehensive experiments are conducted on word analogy and similarity tasks. The results show that improved word representations are learned from ngram co-occurrence statistics. We also demonstrate that the trained ngram representations are useful in many aspects such as finding antonyms and collocations. Besides, a novel approach of building co-occurrence matrix is proposed to alleviate the hardware burdens brought by ngrams.

Convolutional Neural Networks (CNNs) are widely used in NLP tasks. This paper presents a novel weight initialization method to improve the CNNs for text classification. Instead of randomly initializing the convolutional filters, we encode semantic features into them, which helps the model focus on learning useful features at the beginning of the training. Experiments demonstrate the effectiveness of the initialization technique on seven text classification tasks, including sentiment analysis and topic classification.

The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along with the published code, would be helpful for choosing the best context type and representation for a given task.

NBSVM is one of the most popular methods for text classification and has been widely used as baselines for various text representation approaches. It uses Naive Bayes (NB) feature to weight sparse bag-of-n-grams representation. N-gram captures word order in short context and NB feature assigns more weights to those important words. However, NBSVM suffers from sparsity problem and is reported to be exceeded by newly proposed distributed (dense) text representations learned by neural networks. In this paper, we transfer the n-grams and NB weighting to neural models. We train n-gram embeddings and use NB weighting to guide the neural models to focus on important words. In fact, our methods can be viewed as distributed (dense) counterparts of sparse bag-of-n-grams in NBSVM. We discover that n-grams and NB weighting are also effective in distributed representations. As a result, our models achieve new strong baselines on 9 text classification datasets, e.g. on IMDB dataset, we reach performance of 93.5% accuracy, which exceeds previous state-of-the-art results obtained by deep neural models. All source codes are publicly available at https://github.com/zhezhaoa/neural_BOW_toolkit.