Pseudo-Relevance Feedback (PRF) is a key technique in information retrieval (IR). Traditional implementations rely on statistical information, such as term frequency, for precise matching and relevance assessment. However, these methods struggle to fully capture the deep semantic integrity of query terms, especially in handling polysemy, high semantic relevance, and long-document comprehension. To address these challenges, this paper innovatively proposes a large language model-assisted PRF probabilistic model. The model first employs a precise matching algorithm to evaluate and determine the term-level weights, and then uses a large language model to encode the contextual relationships within the query and feedback documents, thereby accurately acquiring the global semantic weights of terms relevant to the query at the document level. By adjusting a balancing factor to allocate weights between these two components, the model comprehensively selects expanded terms for constructing a new query representation and executing query expansion (QE). This model not only facilitates approximate matching through the integration of global semantic features of documents but also effectively combines with the precise matching information of traditional PRF models, enabling a comprehensive and accurate optimization of queries from a broader perspective. To validate effectiveness, extensive empirical analyses on five TREC datasets assess performance across key metrics such as MAP, P@10, NDCG, and MRR. Experimental results show significant improvements over baseline models. Comparative analyses and case studies confirm that the expanded terms maintain high semantic relevance and consistency with the original query while preserving diversity and effectively capturing global document semantics, establishing an efficient QE mechanism.

In the field of information Retrieval (IR), Pseudo-relevance feedback (PRF) and Query Expansion (QE) techniques have garnered significant attention for their efficacy in enhancing retrieval effectiveness. However, traditional PRF approaches predominantly concentrate solely on pseudo-relevant documents identified during the initial retrieval stage, neglecting the rich semantic information embedded within non-pseudo-relevant documents. This paper introduces an innovative PRF model that integrates soft negative samples and contrastive learning to address this limitation, aiming for a more comprehensive capture and representation of semantics. First, we employ the BM25 algorithm as the baseline retrieval mechanism to accurately pinpoint pseudo-relevant documents from the first stage retrieval and assign weights to their terms. Second, a contrastive learning strategy is introduced to distill semantic features from all documents globally, further refining the semantic weights of terms. To mitigate the risk of information loss associated with soft negative samples, we ingeniously leverage the statistical properties of kernel function to precisely gauge the co-occurrence frequencies between terms, ensuring the preservation of core information and thus obtaining kernel function term co-occurrence weights. Third, we select semantically related terms highly relevant to the query for creating an optimized query by balancing these three weight distributions. Extensive empirical analyses conducted on several TREC datasets demonstrate the practical feasibility of our proposed model. It outperforms baseline models and state-of-the-art technologies on core evaluation metrics such as MAP, P@10, NDCG, and MRR. Deeper comparative experiments and case studies reveal that the expansion terms generated by our model exhibits a deeper level of semantic coherence with the original query, underscoring the dual advantages of the model in both theory and practice. In summary, the model presented herein not only opens a new path at the technical level, but also provides a more accurate and efficient solution for real-world applications in IR.

Abstract Continual relation extraction aims to learn new relations from a continuous stream of data while avoiding forgetting old relations. Existing methods typically use the BERT encoder to obtain semantic embeddings, ignoring the fact that the vector representations suffer from anisotropy and uneven distribution. Furthermore, the relation prototypes are usually computed by memory samples directly, resulting in the model being overly sensitive to memory samples. To solve these problems, we propose a new continual relation extraction method. Firstly, we modified the basic structure of the sample encoder to generate uniformly distributed semantic embeddings using the supervised SimCSE-BERT to obtain richer sample information. Secondly, we introduced static relation prototypes and dynamically adjust their proportion with dynamic relation prototypes to adapt to the feature space. Lastly, through experimental analysis on the widely used FewRel and TACRED datasets, the results demonstrate that the proposed method effectively enhances semantic embeddings and relation prototypes, resulting in a further alleviation of catastrophic forgetting in the model. The code will be soon released at https://github.com/SuyueW/SS-CRE .

Abstract In the field of recommendation algorithms, the representation learning for users and items has evolved from using single IDs or historical interactions to utilizing higher-order neighbors. This can be achieved by modeling the user–item interaction graph to capture user preferences for items. Despite the promising results achieved by these algorithms, they still suffer from the issue of data sparsity. In order to mitigate the impact of data sparsity, contrastive learning has been adopted in graph collaborative filtering to enhance performance. However, current recommendation algorithms using contrastive learning yield uneven representations after data augmentation and do not consider the potential relationships among users (or items). To address these challenges, we propose a graph neural network-based recommendation model that integrates contrastive learning (GNNCL). This model combines data augmentation with added noise and the exploration of semantic neighbors for nodes. For the structural neighbors on the interaction graph, we introduce a novel and straightforward contrastive learning approach, abandoning previous graph augmentation methods, and introducing uniform noise into the embedding space to create contrastive views. To unearth potential semantic neighbor relationships in the semantic space, we assume that users with similar representations possess semantic neighbor relationships and merge these semantic neighbors into the prototype contrastive learning. We utilize a clustering algorithm to obtain prototypes for users and items and employ the EM algorithm for prototype contrastive learning. Experimental results validate the effectiveness of our approach. Particularly, on the Yelp2018 and Amazon-book datasets, our method exhibits significant performance improvements compared to basic graph collaborative filtering models.