Yifei Yu, Qian-Wen Zhang, Lingfeng Qiao, Di Yin, Fang Li, Jie Wang, Chen Zeng Xi, Suncong Zheng, Xiaolong Liang, Xing Sun. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Modeling hypernym-hyponym ("is-a") relations is important for many natural language processing (NLP) tasks, such as classification, natural language inference and relation extraction.Existing work on is-a relation extraction is mostly in the English language environment.Due to the flexibility of language expression and the lack of high-quality Chinese annotation datasets, it is still a challenge to accurately identify such relations from Chinese unstructured texts.To tackle this problem, we propose a Knowledge Enhanced Prompt Learning (KEPL) method for Chinese hypernymhyponym relation extraction.Our model uses the Hearst-like patterns as the prior knowledge.By exploiting a Dynamic Adaptor to select the matching pattern for the text into the prompt, our method simultaneously embedding patterns and text.Additionally, we construct a Chinese hypernym-hyponym relation extraction dataset, which contains three typical scenarios, as Baidu Encyclopedia, news and We-media.The experimental results on the dataset demonstrate the efficiency and effectiveness of our proposed model.

Xu Han, Yuqi Luo, Weize Chen, Zhiyuan Liu, Maosong Sun, Zhou Botong, Hao Fei, Suncong Zheng. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Forcing the answer of the Question Answering (QA) task to be a single text span might be restrictive since the answer can be multiple spans in the context. Moreover, we found that multi-span answers often appear with two characteristics when building the QA system for a real-world application. First, multi-span answers might be caused by users lacking domain knowledge and asking ambiguous questions, which makes the question need to be answered with conditions. Second, there might be hierarchical relations among multiple answer spans. Some recent span-extraction QA datasets include multi-span samples, but they only contain unconditional and parallel answers, which cannot be used to tackle this problem. To bridge the gap, we propose a new task: conditional question answering with hierarchical multi-span answers, where both the hierarchical relations and the conditions need to be extracted. Correspondingly, we introduce CMQA, a Conditional Multiple-span Chinese Question Answering dataset to study the new proposed task. The final release of CMQA consists of 7,861 QA pairs and 113,089 labels, where all samples contain multi-span answers, 50.4% of samples are conditional, and 56.6% of samples are hierarchical. CMQA can serve as a benchmark to study the new proposed task and help study building QA systems for real-world applications. The low performance of models drawn from related literature shows that the new proposed task is challenging for the community to solve.

Knowledge Graph Embedding (KGE) has been proposed and successfully utilized to knowledge Graph Completion (KGC). But classic KGE paradigm often fail in unseen relation representations. Previous studies mainly utilize the textual descriptions of relations and its neighbor relations to represent unseen relations. In fact, the semantics of a relation can be expressed by three kinds of graphs: factual graph, ontology graph, textual description graph, and they can complement each other. A more common scenario in the real world is that seen and unseen relations appear at the same time. In this setting, the training set (only seen relations) and testing set (both seen and unseen relations) own different distributions. And the train-test inconsistency problem will make KGE methods easiy overfit on seen relations and under-performance on unseen relations. In this paper, we propose decoupling mixture-of-graph experts (DMoG) for unseen relations learning, which could represent the unseen relations in the factual graph by fusing ontology and textual graphs, and decouple fusing space and reasoning space to alleviate overfitting for seen relations. The experiments on two unseen only public datasets and a mixture dataset verify the effectiveness of the proposed method, which improves the state-of-the-art methods by 6.84% in Hits@10 on average.

Joint extraction of entities and relations is an important task in information extraction.To tackle this problem, we firstly propose a novel tagging scheme that can convert the joint extraction task to a tagging problem.Then, based on our tagging scheme, we study different end-toend models to extract entities and their relations directly, without identifying entities and relations separately.We conduct experiments on a public dataset produced by distant supervision method and the experimental results show that the tagging based methods are better than most of the existing pipelined and joint learning methods.What's more, the end-to-end model proposed in this paper, achieves the best results on the public dataset.

Recently, end-to-end memory networks have shown promising results on Question Answering task, which encode the past facts into an explicit memory and perform reasoning ability by making multiple computational steps on the memory. However, memory networks conduct the reasoning on sentence-level memory to output coarse semantic vectors and do not further take any attention mechanism to focus on words, which may lead to the model lose some detail information, especially when the answers are rare or unknown words. In this paper, we propose a novel Hierarchical Memory Networks, dubbed HMN. First, we encode the past facts into sentence-level memory and word-level memory respectively. Then, k-max pooling is exploited following reasoning module on the sentence-level memory to sample the k most relevant sentences to a question and feed these sentences into attention mechanism on the word-level memory to focus the words in the selected sentences. Finally, the prediction is jointly learned over the outputs of the sentence-level reasoning module and the word-level attention mechanism. The experimental results demonstrate that our approach successfully conducts answer selection on unknown words and achieves a better performance than memory networks.

Recurrent Neural Network (RNN) is one of the most popular architectures used in Natural Language Processsing (NLP) tasks because its recurrent structure is very suitable to process variable-length text. RNN can utilize distributed representations of words by first converting the tokens comprising each text into vectors, which form a matrix. And this matrix includes two dimensions: the time-step dimension and the feature vector dimension. Then most existing models usually utilize one-dimensional (1D) max pooling operation or attention-based operation only on the time-step dimension to obtain a fixed-length vector. However, the features on the feature vector dimension are not mutually independent, and simply applying 1D pooling operation over the time-step dimension independently may destroy the structure of the feature representation. On the other hand, applying two-dimensional (2D) pooling operation over the two dimensions may sample more meaningful features for sequence modeling tasks. To integrate the features on both dimensions of the matrix, this paper explores applying 2D max pooling operation to obtain a fixed-length representation of the text. This paper also utilizes 2D convolution to sample more meaningful information of the matrix. Experiments are conducted on six text classification tasks, including sentiment analysis, question classification, subjectivity classification and newsgroup classification. Compared with the state-of-the-art models, the proposed models achieve excellent performance on 4 out of 6 tasks. Specifically, one of the proposed models achieves highest accuracy on Stanford Sentiment Treebank binary classification and fine-grained classification tasks.

Taking advantage of the large scale corpus on the web to effectively and efficiently mine the topics within texts is an essential problem in the era of big data. We focus on the problem of learning text topic embedding in an unsupervised manner, which enjoys the properties of efficiency and scalability. Text topic embedding represents words and documents in a semantic topic space, in which the words and documents with similar topic will be embedded close to each other. When compared with conventional topic models, which implicitly capture the document-level word co-occurrence patterns, text topic embedding alleviates the data sparsity problem and captures the semantic relevance between different words and documents. To model text topic embedding, we propose a Bidirectional Hierarchical Skip-Gram model (BHSG) based on skip-gram model. BHSG includes two components: semantic generation module to learn semantic relevance between texts and topic enhance module to produce the text topic embedding based on text embedding learned in the former module. We evaluated our method on two kinds of topic-related tasks: text classification and information retrieval. The experimental results on four public datasets and one dataset we provide all demonstrate that our proposed method can achieve a better performance.