The primary challenge in text-video retrieval lies in achieving cross-modal semantic alignment, particularly the discrepancy between the conciseness of textual descriptions, which often fail to fully encapsulate the breadth of video content, and the redundancy in video data, which introduces noise and masks important semantic features. Current methods align text and video by mapping them into a shared feature space. Despite notable advancements, the inherent differences in modality-specific representations create a bottleneck for fixed-point embedding techniques, making models highly sensitive to dataset distribution and hindering their generalization ability. In this paper, we present DomainDiff, a framework that enhances the embedding space through a two-stage process. In the first stage, stochastic domain modeling, we semantically expand text embeddings to explore potential regions aligned with video content. Simultaneously, we filter video segments to reduce redundancy and highlight key frames. In the second stage, the dynamic agent attention diffusion network, we leverage the generative properties of diffusion models to optimize the embedding space by viewing it from a joint probability distribution perspective. An agent attention mechanism dynamically integrates text and video features, ensuring accurate cross-modal alignment. Experimental results demonstrate that DomainDiff significantly improves retrieval performance across five benchmark datasets, with R@1 improvements ranging from 3% to 7.4%. Moreover, DomainDiff outperforms existing methods in handling long videos and complex textual descriptions, showcasing superior semantic robustness and generalization across varying distributions.

In recent years, people are facing with billions of food images, videos and recipes on social medias. An appropriate technology is highly desired to retrieve accurate contents across food images and cooking recipes, like cross-modal retrieval framework. Based on our observations, the order of sequential sentences in recipes and the noises in food images will affect retrieval results. We take into account the sentence-level sequential orders of instructions and ingredients in recipes, and noise portion in food images to propose a new framework for cross-retrieval. In our framework, we propose three new strategies to improve the retrieval accuracy. (1) We encode recipe titles, ingredients, instructions in sentence level, and adopt three attention networks on multi-layer hidden state features separately to capture more semantic information. (2) We apply attention mechanism to select effective features from food images incorporating with recipe embeddings, and adopt an adversarial learning strategy to enhance modality alignment. (3) We design a new triplet loss scheme with an effective sampling strategy to reduce the noise impact on retrieval results. The experimental results show that our framework clearly outperforms the state-of-art methods in terms of median rank and recall rate at top k on the Recipe 1M dataset.

Understanding the expertise of users in social networking sites like Twitter is a key component for many applications such as user recommendation and talent seeking. A range of interactions between users on Twitter can provide important information that implicitly reflects a user's expertise. This paper proposes a learning model that tries to infer a user's topical expertise from Twitter using information such as tweets posted by the user and the characteristics of their followers. The model takes various types of user-related data from Twitter as input and considers their inference consistency in the process of learning. It aims to deliver accurate and effective inference results, even in cases where some types of data are missing for a user, e.g. the user has yet to post any tweets. The experiments reported in the paper were conducted on a large-scale Twitter dataset. Experimental results show that our model outperforms several baseline approaches and outperforms approaches which use only a single type of user data for inference.

Query expansion has been widely adopted in Web search as a way of tackling the ambiguity of queries. Personalized search utilizing folksonomy data has demonstrated an extreme vocabulary mismatch problem that requires even more effective query expansion methods. Co-occurrence statistics, tag-tag relationships, and semantic matching approaches are among those favored by previous research. However, user profiles which only contain a user's past annotation information may not be enough to support the selection of expansion terms, especially for users with limited previous activity with the system. We propose a novel model to construct enriched user profiles with the help of an external corpus for personalized query expansion. Our model integrates the current state-of-the-art text representation learning framework, known as word embeddings, with topic models in two groups of pseudo-aligned documents. Based on user profiles, we build two novel query expansion techniques. These two techniques are based on topical weights-enhanced word embeddings, and the topical relevance between the query and the terms inside a user profile, respectively. The results of an in-depth experimental evaluation, performed on two real-world datasets using different external corpora, show that our approach outperforms traditional techniques, including existing non-personalized and personalized query expansion methods.

The ability to understand the expertise of users in Social Networking Sites (SNSs) is a key component for delivering effective information services such as talent seeking and user recommendation. However, users are often unwilling to make the effort to explicitly provide this information, so existing methods aimed at user expertise discovery in SNSs primarily rely on implicit inference. This work aims to infer a user's expertise based on their posts on the popular micro-blogging site Twitter. The work proposes a sentiment-weighted and topic relation-regularized learning model to address this problem. It first uses the sentiment intensity of a tweet to evaluate its importance in inferring a user's expertise. The intuition is that if a person can forcefully and subjectively express their opinion on a topic, it is more likely that the person has strong knowledge of that topic. Secondly, the relatedness between expertise topics is exploited to model the inference problem. The experiments reported in this paper were conducted on a large-scale dataset with over 10,000 Twitter users and 149 expertise topics. The results demonstrate the success of our proposed approach in user expertise inference and show that the proposed approach outperforms several alternative methods.

Information retrieval (IR) systems exploit relevant information when tailoring search results to individual information needs. However, current search experience becomes poor without considering similar queries entered by previous searchers. In the following paper, we discuss a solution to this problem, which combines collaborative filtering algorithms with traditional IR models to enable EIR. We also present various iterative refinement methods for improving the raw performance of this system. We validate our theories in an experiment using queries extracted from the click-through log of a commercial search engine. According to our results, an IR system employing iteratively refined, collaborative retrieval significantly outperforms various baseline retrieval models.

Professional users of medical information often report difficulties when attempting to locate specific information in lengthy documents. Sometimes these difficulties can be attributed to poorly specified section titles which fail to advertise relevant content. In this paper we describe preliminary work on a software plug-in for a document engineering environment that will assist authors when they formulate section-level headings. We describe two different algorithms which can be used to generate section titles. We compare the performance of these algorithms and correlate our experimental results with an evaluation of title quality performed by domain experts.

The field of information retrieval still strives to develop models which allow semantic information to be integrated in the ranking process to improve performance in comparison to standard bag-of-words based models. Cross-lingual information retrieval is an example of where such a model is required, as content or concepts often need to be matched across languages. To overcome this problem, a conceptual model has been adopted in ranking an entire corpus which normally exploits latent/implicit features of the text. One of the drawbacks of this model is that the computational cost is significant and often intractable in modern test collections. Therefore, approaches utilizing concept-based models for re-ranking initial retrieval results have attracted a considerable amount of study, in particular the latent concept model. However, fitting such a model to a smaller collection is less meaningful than fitting it into the whole corpus. This paper proposes a late fusion method which incorporates scores generated by using external knowledge to enhance the space produced by the latent concept method. This method is further demonstrated to be suitable for multilingual re-ranking purposes. To illustrate the effectiveness of the proposed method, experiments were conducted over test collections across three languages. The results demonstrate that the method can comfortably achieve improvements in retrieval performance over several re-ranking methods.

Previous work has established that specific linguistic markers present in specialised medical documents (clinical guidelines) can be used to support their automatic structuring within a document engineering environment. This technique is commonly used by the French Health Authority (la Haute Autorite de Sante) during elaboration of clinical guidelines to improve the quality of the final document. In this paper, we explore the readability of clinical guidelines. We discuss a structural measure of document readability that exploits the ratio between these linguistic markers (deontic structures) and the remainder of the text. We describe an experiment in which a corpus of 10 French clinical guidelines is scored for structural readability. We correlate these scores with measures of textual cohesion (computed using latent semantic analysis) and the results of a readability survey performed by a panel of domain experts. Our results suggest an association between the density of deontic structures in a clinical guideline and its overall readability. This implies that certain generic readability measures can henceforth be utilised in our document engineering environment.