LollipopE: Bi-centered lollipop embedding for complex logic query on knowledge graph.

Answering complex First-Order Logic (FOL) query plays a vital role in multi-hop knowledge graph (KG) reasoning. Geometric methods have emerged as a promising category of approaches in this context. However, existing best-performing geometric query embedding (QE) model is still up against three-fold potential problems: (i) underutilization of embedding space, (ii) overreliance on angle information, (iii) uncaptured hierarchy structure. To bridge the gap, we propose a lollipop-like bi-centered query embedding method named LollipopE. To fully utilize embedding space, LollipopE employs learnable centroid positions to represent multiple entities distributed along the same axis. To address the potential overreliance on angular metrics, we design an angular-based and centroid-based metric. This involves calculating both an angular distance and a centroid-based geodesic distance, which empowers the model to make more informed selections of relevant answers from a wider perspective. To effectively capture the hierarchical relationships among entities within the KG, we incorporate dynamic moduli, which allows for the representation of the hierarchical structure among entities. Extensive experiments demonstrate that LollipopE surpasses the state-of-the-art geometric methods. Especially, on more hierarchical datasets, LollipopE achieves the most significant improvement.

M 2 DCapsN: Multimodal, Multichannel, and Dual-Step Capsule Network for Natural Language Moment Localization.

Natural language moment localization aims to localize the target moment that matches a given natural language query in an untrimmed video. The key to this challenging task is to capture fine-grained video-language correlations to establish the alignment between the query and target moment. Most existing works establish a single-pass interaction schema to capture correlations between queries and moments. Considering the complex feature space of lengthy video and diverse information between frames, the weight distribution of information interaction flow is prone to dispersion or misalignment, which leads to redundant information flow affecting the final prediction. We address this issue by proposing a capsule-based approach to model the query-video interactions, termed the Multimodal, Multichannel, and Dual-step Capsule Network (M 2 DCapsN), which is derived from the intuition that "multiple people viewing multiple times is better than one person viewing one time." First, we introduce a multimodal capsule network, replacing the single-pass interaction schema of "one person viewing one time" with the iterative interaction schema of "one person viewing multiple times", which cyclically updates cross-modal interactions and modifies potential redundant interactions via its routing-by-agreement. Then, considering that the conventional routing mechanism only learns a single iterative interaction schema, we further propose a multichannel dynamic routing mechanism to learn multiple iterative interaction schemas, where each channel performs independent routing iteration to collectively capture cross-modal correlations from multiple subspaces, that is", multiple people viewing." Moreover, we design a dual-step capsule network structure based on the multimodal, multichannel capsule network, bringing together the query and query-guided key moments to jointly enhance the original video, so as to select the target moments according to the enhanced part. Experimental results on three public datasets demonstrate the superiority of our approach in comparison with state-of-the-art methods, and comprehensive ablation and visualization analysis validate the effectiveness of each component of the proposed model.

Factoid Question Answering with Distant Supervision.

Automatic question answering (QA), which can greatly facilitate the access to information, is an important task in artificial intelligence. Recent years have witnessed the development of QA methods based on deep learning. However, a great amount of data is needed to train deep neural networks, and it is laborious to annotate training data for factoid QA of new domains or languages. In this paper, a distantly supervised method is proposed to automatically generate QA pairs. Additional efforts are paid to let the generated questions reflect the query interests and expression styles of users by exploring the community QA. Specifically, the generated questions are selected according to the estimated probabilities they are asked. Diverse paraphrases of questions are mined from community QA data, considering that the model trained on monotonous synthetic questions is very sensitive to variants of question expressions. Experimental results show that the model solely trained on generated data via the distant supervision and mined paraphrases could answer real-world questions with the accuracy of 49.34%. When limited annotated training data is available, significant improvements could be achieved by incorporating the generated data. An improvement of 1.35 absolute points is still observed on WebQA, a dataset with large-scale annotated training samples.