Efficient Dual-Process Cognitive Recommender Balancing Accuracy and Diversity

We present an online multilingual system for event detection and comprehension from media feeds. The system retrieves information from news sites, aggregates them into events (event detection), and summarizes them by extracting semantic labels of its most relevant entities (event representation) in order to answer the journalism Ws: who, what, when and where. The generated events populate VLX-Stories -an event ontology- transforming unstructured text data to a structured knowledge base representation. Our system exploits an external entity Knowledge Graph (VKG) to help populate VLX-Stories. At the same time, this external knowledge graph can also be extended with a Dynamic Entity Linking (DEL) module, which detects emerging entities (EE) on unstructured data. The system is currently deployed in production and used by media producers in the editorial process, providing real-time access to breaking news. Each month, VLX-Stories detects over 9000 events from over 4000 news feeds from seven different countries and in three different languages. At the same time, it detects over 1300 EE per month, which populate VKG.

Zhekun Luo, Shalini Ghosh, Devin Guillory, Keizo Kato, Trevor Darrell, Huijuan Xu. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Recently, neural language representation models pre-trained on large corpus can capture rich co-occurrence information and be fine-tuned in downstream tasks to improve the performance. As a result, they have achieved state-of-the-art results in a large range of language tasks. However, there exists other valuable semantic information such as similar, opposite, or other possible meanings in external knowledge graphs (KGs). We argue that entities in KGs could be used to enhance the correct semantic meaning of language sentences. In this paper, we propose a new method CKG: Dynamic Representation Based on Context and Knowledge Graph. On the one side, CKG can extract rich semantic information from a large corpus. On the other side, it can make full use of inside information such as co-occurrence in large corpus and outside information such as similar entities in KGs. We conduct extensive experiments on a wide range of tasks, including QQP, MRPC, SST-5, SQuAD, CoNLL 2003, and SNLI. The experiment results show that CKG achieves SOTA 89.2 on SQuAD compared with SAN (84.4), ELMo (85.8), and BERT_Base (88.5).

LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension

Aiming at the problems of lack of background knowledge and the inconsistent response of robots in the current human-computer interaction system, we proposed a human-computer interaction model based on a knowledge graph ripple network. The model simulated the natural human communication process to realize a more natural and intelligent human-computer interaction system. This study had three contributions: first, the affective friendliness of human-computer interaction was obtained by calculating the affective evaluation value and the emotional measurement of human-computer interaction. Then, the external knowledge graph was introduced as the background knowledge of the robot, and the conversation entity was embedded into the ripple network of the knowledge graph to obtain the potential entity content of interest of the participant. Finally, the robot replies based on emotional friendliness and content friendliness. The experimental results showed that, compared with the comparison models, the emotional friendliness and coherence of robots with background knowledge and emotional measurement effectively improve the response accuracy by 5.5% at least during human-computer interaction.

The increasing reliance on Large Language Models (LLMs) for health information seeking can pose severe risks due to the potential for misinformation and the complexity of these topics. This paper introduces KnowNet a visualization system that integrates LLMs with Knowledge Graphs (KG) to provide enhanced accuracy and structured exploration. Specifically, for enhanced accuracy, KnowNet extracts triples (e.g., entities and their relations) from LLM outputs and maps them into the validated information and supported evidence in external KGs. For structured exploration, KnowNet provides next-step recommendations based on the neighborhood of the currently explored entities in KGs, aiming to guide a comprehensive understanding without overlooking critical aspects. To enable reasoning with both the structured data in KGs and the unstructured outputs from LLMs, KnowNet conceptualizes the understanding of a subject as the gradual construction of graph visualization. A progressive graph visualization is introduced to monitor past inquiries, and bridge the current query with the exploration history and next-step recommendations. We demonstrate the effectiveness of our system via use cases and expert interviews.

Knowledge-aware multi-center clinical dataset adaptation: Problem, method, and application

Traditional Chinese Medicine (TCM), with its extensive knowledge base documented in ancient texts, offers a unique resource for contemporary drug discovery, particularly in combatting microbial infections. The success of antimalarial drugs like artemisinin and artesunate, derived from the TCM herb Artemisia annua L., exemplifies the potential of TCM-derived small molecules. This rich repository of natural products and intricate molecular structures could reveal novel compounds with unexplored mechanisms of action. Our study employs a multifaceted approach that combines text mining, detailed textual analysis, and modern antibacterial molecular prediction methodologies to unlock the potential of ancient TCM remedies. We use external knowledge maps, which include databases of known bioactive compounds and their targets, to identify promising TCM candidates. This approach leverages both historical texts and contemporary scientific data to explore the therapeutic potential of TCM. We discovered that herb patterns DiYu→ZeXie and Kushen→ShengJiang potentially combat both Grams-positive and Grams-negative bacteria. We utilized the AntiBac-Pred online tool to identify and analyze the chemical components of herbs, integrating data from ancient texts and TCMDB@Taiwan external knowledge graph. The DiYu→ZeXie groups showed antimicrobial potential against resistant Staphylococcus simulans, while the Kushen→ShengJiang groups exhibited dual antimicrobial effects against Bacillus subtilis. Exploring TCM's extensive repository offers numerous opportunities for discovering therapeutically active compounds. Our synergistic approach, which combines ancient wisdom with modern science, holds significant promise for enhancing our ability to combat infectious diseases. This method could pave the way for a new era of personalized medicine, addressing the urgent need for innovative treatments against multidrug-resistant bacteria and viruses.

Integrating commonsense knowledge with GPT embeddings for emotion classification☆

Open-set action recognition (OSAR) aims to learn a recognition framework capable of both classifying known classes and identifying unknown actions in open-set scenarios. Existing OSAR methods typically reside in a data-driven paradigm, which ignore the rich semantics in both known and unknown categories. In fact, we humans have the capability of leveraging the captured semantic information, i.e., knowledge and experience, to incisively distinguish samples from known and unknown classes. Motivated by this observation, in this paper, we propose a Unified Semantic Exploration (USE) framework for recognizing actions in open-set scenarios. Specifically, we explore the explicit knowledge semantics by simulating the unknown classes with knowledge-guided virtual classes based on an external knowledge graph, which enables the model to simulate open-set perception during model training. Besides, we propose to learn the implicit data semantics by transferring the knowledge structure of action categories to the visual prototype space for semantic structure preservation. Extensive experiments on several action recognition benchmarks validate the effectiveness of our proposed method.

Modeling user preferences from users' historical sequences is one of the core problems of sequential recommendation. Previous studies only considered transition patterns between user-items, ignoring transition patterns between item features and item-item interactions. Recently, there has been interest in integrating knowledge graphs as auxiliary information into sequential recommendation. Most of the existing methods deal with the heterogeneous information in the knowledge graph in a coarse-grained manner. We believe that fine-grained processing of information in knowledge graphs can help recommendation systems understand changes in user preferences, i.e. dividing hetero-geneous information into item-to-item relationships and item-to-attribute relationships. In this paper, we propose a dual-level self-attention network for sequential recommendation. Specifically, we divide the knowledge graph heterogeneous information about items into relation level and attribute level, representing item-item relationship and item-attribute relationship, respectively. Afterwards, the self-attention network is used to learn user preferences at dual-level, respectively. Then, the outputs of the above dual levels are integrated for next item recommendation. Based on extensive experiments on three real-world data sets, our model achieves significant improvements compared to state-of-the-art baseline methods.

CommonsenseQA is a task in which a correct answer is predicted through commonsense reasoning with pre-defined knowledge. To shed light upon the semantic interpretation of the question, we propose an AMR-ConceptNet-Pruned (ACP) graph. The ACP graph is pruned from a full integrated graph encompassing Abstract Meaning Representation (AMR) graph generated from input questions and an external commonsense knowledge graph, ConceptNet (CN). Then the ACP graph is exploited to interpret the reasoning path as well as to predict the correct answer on the CommonsenseQA task.

The proliferation of electronic health records (EHRs) and advances in deep learning have enabled personalized drug combination recommendations. However, traditional deep learning models often lack the contextual understanding and medical knowledge integration necessary for accurate predictions. While large language model (LLM)-based approaches address some of these challenges, they still fall short in incorporating critical medical knowledge, addressing comprehensive safety constraints such as multi-disease drug contraindications (MDCs), and providing sufficient interpretability of the causal mechanisms behind their outputs. To overcome these limitations, we propose KELLM, a knowledge-enhanced LLM framework for drug recommendations. By linking medical entities in EHRs to an external medical knowledge graph, inputs are enriched with causal chains, enhancing both prediction accuracy and interpretability. Additionally, we introduce a fine-tuned label-wise LLaMA model designed for multi-label classification, which incorporates safety considerations such as drug-drug interactions (DDIs) and MDCs to ensure clinically accurate and safe recommendations. Experimental results show that KELLM achieves state-of-the-art performance in effectiveness and safety metrics, while also providing evidence-based insights through causal chains that clarify its reasoning process. This establishes a new benchmark for trustworthy, interpretable drug combination recommendations.

CommonsenseQA is a task in which a correct answer is predicted through commonsense reasoning with pre-defined knowledge. Most previous works have aimed to improve the performance with distributed representation without considering the process of predicting the answer from the semantic representation of the question. To shed light upon the semantic interpretation of the question, we propose an AMR-ConceptNet-Pruned (ACP) graph. The ACP graph is pruned from a full integrated graph encompassing Abstract Meaning Representation (AMR) graph generated from input questions and an external commonsense knowledge graph, ConceptNet (CN). Then the ACP graph is exploited to interpret the reasoning path as well as to predict the correct answer on the CommonsenseQA task. This paper presents the manner in which the commonsense reasoning process can be interpreted with the relations and concepts provided by the ACP graph. Moreover, ACP-based models are shown to outperform the baselines.

Recently, Large Language Model (LLM)-empowered recommender systems have revolutionized personalized recommendation frameworks and attracted extensive attention. Despite the remarkable success, existing LLM-empowered RecSys have been demonstrated to be highly vulnerable to minor perturbations. To mitigate the negative impact of such vulnerabilities, one potential solution is to employ collaborative signals based on item-item co-occurrence to purify the malicious collaborative knowledge from the user’s irrelevant historical interactions. On the other hand, due to the capabilities to expand insufficient internal knowledge of LLMs, Retrieval-Augmented Generation (RAG) techniques provide unprecedented opportunities to enhance the robustness of LLM-empowered recommender systems by introducing external collaborative knowledge. Therefore, in this paper, we propose a novel framework ( RETURN ) by retrieving external collaborative signals to purify the poisoned user profiles and enhance the robustness of LLM-empowered RecSys in a plug-and-play manner. Specifically, retrieval-augmented perturbation positioning is proposed to identify potential perturbations within the users’ historical sequences by retrieving external knowledge from collaborative item graphs. After that, we further retrieve the collaborative knowledge to cleanse the perturbations by using either deletion or replacement strategies and introduce a robust ensemble recommendation strategy to generate final robust predictions. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed RETURN.