Multiple Intentions Research Articles

A Segment Augmentation and Prediction Consistency Framework for Multi-Label Unknown Intent Detection

Multi-label unknown intent detection is a challenging task where each utterance may contain not only multiple known but also unknown intents. To tackle this challenge, pioneers proposed to predict the intent number of the utterance first, then compare it with the results of known intent matching to decide whether the utterence contains unknown intent(s). Though they have made remarkable progress on this task, their methods still suffer from two important issues: (1) It is inadequate to extract multiple intents using only utterance encoding; (2) Optimizing two sub-tasks (intent number prediction and known intent matching) independently leads to inconsistent predictions. In this article, we propose to incorporate segment augmentation rather than only use utterance encoding to better detect multiple intents. We also design a prediction consistency module to bridge the gap between the two sub-tasks. Empirical results on MultiWOZ2.3 and MixSNIPS datasets show that our method achieves state-of-the-art performance and significantly improves the best baseline.

The Role of Journals in Reporting Sex and Gender-Based Outcomes: Should We Adopt Guidelines, and What Else Can We Do to Improve Reporting?

➤ Sex and gender are inconsistently reported in musculoskeletal research. A panel of journal editors and other interested parties who participated in The Journal of Bone and Joint Surgery Sex and Gender Reporting in Musculoskeletal Research Symposium met in 2023 to help define the roles of journals and other stakeholders in addressing this issue.➤ This report summarizes the resulting recommendations and presents several different ways in which orthopaedic journals may elect to introduce to their readers, reviewers, and authors the importance of considering sex and gender in orthopaedic research.➤ Many current sex and gender-related funding agency mandates as well as the Sex and Gender Equity in Research (SAGER) guidelines are most readily applied to prospective research and/or randomized controlled trials.➤ The panel was supportive of endorsing SAGER or a similar set of guidelines as a tool that can help authors to consider the most effective means of evaluating the influences of sex and gender within the context of orthopaedic research.➤ Engaging readers, reviewers, and authors on multiple fronts, with purpose and intention, is likely the most important approach to increase awareness and to enhance the quality of evidence utilized to support clinical decisions in orthopaedic surgery.

MBCFNet: A Multimodal Brain–Computer Fusion Network for human intention recognition

Accurate recognition of human intent is crucial for effective human–computer speech interaction. Numerous intent understanding studies were based on speech-to-text transcription, which often overlook the influence of paralinguistic cues (such as speaker’s emotion, attitude, etc.), leading to misunderstandings, especially when identical textual content conveys multiple intents by means of different paralinguistic information. Considering that interaction intent is produced from the human brain, we propose a novel Multimodal Brain–Computer Fusion Network (MBCFNet) to discriminate the different intents carried by the identical textual information, in which the acoustic-textual representation was adapted by brain functional information through a cross-modal transformer. In the output module, a joint multi-task learning method was used to optimize both the primary task of intent recognition and the auxiliary task of emotion recognition of the speaker. To evaluate the model performance, we constructed a multimodal dataset CMSLIU that consists of acoustic, textual, and electroencephalograph (EEG) data of the same Chinese texts with varying intents. Experimental results on the self-constructed dataset indicate that the proposed model achieves state-of-the-art (SOTA) performance compared with other competing models. Ablation experiment results reveal that the model performance declines without information from EEG or audio modality, and also when the auxiliary task of emotion recognition is removed. All these results suggest the effectiveness of the proposed information fusion strategy in spoken language intent recognition and the brain–computer information fusion idea can also be extended to other similar fields.

The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Model

Image search is an essential and user-friendly method to explore vast galleries of digital images. However, existing image search methods heavily rely on proximity measurements like tag matching or image similarity, requiring precise user inputs for satisfactory results. To meet the growing demand for a contemporary image search engine that enables accurate comprehension of users' search intentions, we introduce an innovative user intent expansion framework. Our framework leverages visual-language models to parse and compose multi-modal user inputs to provide more accurate and satisfying results. It comprises two-stage processes: 1) a parsing stage that incorporates a language parsing module with large language models to enhance the comprehension of textual inputs, along with a visual parsing module that integrates an interactive segmentation module to swiftly identify detailed visual elements within images; and 2) a logic composition stage that combines multiple user search intents into a unified logic expression for more sophisticated operations in complex searching scenarios. Moreover, the intent expansion framework enables users to perform flexible contextualized interactions with the search results to further specify or adjust their detailed search intents iteratively. We implemented the framework into an image search system for NFT (non-fungible token) search and conducted a user study to evaluate its usability and novel properties. The results indicate that the proposed framework significantly improves users' image search experience. Particularly the parsing and contextualized interactions prove useful in allowing users to express their search intents more accurately and engage in a more enjoyable iterative search experience.

Pedagogical intentions behind teacher written feedback: The perspectives and practices of an English language teacher educator in Argentina

This paper examines, with specific reference to English language teacher education in Argentina, the pedagogical intentions which underlie and inform the written feedback practices of an L2 writing teacher educator. The study is part of a larger exploratory-interpretive investigation which adopted a within-site, embedded, multiple-case design, and used data obtained from document analysis and a range of interview types (background interviews, stimulated recall interviews, and reflective interviews). The findings demonstrate the influence of multiple pedagogical intentions on the teacher educator's written feedback practices, some with immediate relevance to L2 writing and others which extended beyond this field. This reinforces the conclusions drawn in previous studies that discuss the impact of pedagogical intentions which are broader than the specific content being taught. Additionally, however, the results expand on our current understanding of how pedagogical intentions operate at different levels by illustrating how micro-level, discipline-specific technicalities are embedded within and signified by macro-level pedagogical intentions. The findings thus highlight the need to imbue feedback with educational principles that go beyond feedback itself, and have implications for L2 writing instruction and assessment, and L2 teacher education.

Towards Multi-Intent Spoken Language Understanding via Hierarchical Attention and Optimal Transport

Multi-Intent spoken language understanding (SLU) can handle complicated utterances expressing multiple intents, which has attracted increasing attention from researchers. Although existing models have achieved promising performance, most of them still suffer from two leading problems: (1) each intent has its specific scope and the semantic information outside the scope might potentially hinder accurate predictions, i.e. scope barrier; (2) only the guidance from intent to slot is modeled but the guidance from slot to intent is often neglected, i.e. unidirectional guidance. In this paper, we propose a novel Multi-Intent SLU framework termed HAOT, which utilizes hierarchical attention to divide the scopes of each intent and applies optimal transport to achieve the mutual guidance between slot and intent. Experiments demonstrate that our model achieves state-of-the-art performance on two public Multi-Intent SLU datasets, obtaining the 3.4 improvement on MixATIS dataset compared to the previous best models in overall accuracy.

Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction

So far, multi-intent spoken language understanding (SLU) has become a research hotspot in the field of natural language processing (NLP) due to its ability to recognize and extract multiple intents expressed and annotate corresponding sequence slot tags within a single utterance. Previous research has primarily concentrated on the token-level intent-slot interaction to model joint intent detection and slot filling, which resulted in a failure to fully utilize anisotropic intent-guiding information during joint training. In this work, we present a novel architecture by modeling the multi-intent SLU as a multi-view intent-slot interaction. The architecture resolves the kernel bottleneck of unified multi-intent SLU by effectively modeling the intent-slot relations with utterance, chunk, and token-level interaction. We further develop a neural framework, namely Uni-MIS, in which the unified multi-intent SLU is modeled as a three-view intent-slot interaction fusion to better capture the interaction information after special encoding. A chunk-level intent detection decoder is used to sufficiently capture the multi-intent, and an adaptive intent-slot graph network is used to capture the fine-grained intent information to guide final slot filling. We perform extensive experiments on two widely used benchmark datasets for multi-intent SLU, where our model bets on all the current strong baselines, pushing the state-of-the-art performance of unified multi-intent SLU. Additionally, the ChatGPT benchmark that we have developed demonstrates that there is a considerable amount of potential research value in the field of multi-intent SLU.

Strategic Intent: A Conceptual Approach

Strategic Intent is an active management process representing an organization’s succinct and cohesive vision of its aspired direction of growth. Firms may have one central vision but many multiple intents. Intense competition and rapid technological changes require managers to continually review and refine the nature of their strategic intentions. The proposed conceptual model seeks to generate robust avenues and directions for researchers to improve the theory and inform practice. The research propositions integrate the top management team with intrapersonal and dominant functional diversity to examine Strategic Intent from multiple perspectives.

A multi-intent-aware recommendation algorithm based on interactive graph convolutional networks

In recent years, graph neural networks (GNNs) have been widely applied in recommender systems. However, existing recommendation algorithms based on GNNs still face challenges in node aggregation and feature extraction processes because they often lack the ability to capture the interactions between users and items, as well as users’ multiple intentions. This hinders accurate understanding of users’ needs. To address the aforementioned issues, we propose a recommendation model called multi-intent-aware interactive graph convolutional network (Multi-IAIGCN). This model is capable of integrating multiple user intents and adopts an interactive convolution approach to better capture the information on the interaction between users and items. First, before the interaction between users and items begins, user intents are divided and mapped into a graph. Next, interactive convolutions are applied to the user and item trees. Finally, by aggregating different features of user intents, predictions of user preferences are made. Extensive experiments on three publicly available datasets demonstrate that Multi-IAIGCN outperforms existing state-of-the-art methods or can achieve results comparable to those of existing state-of-the-art methods in terms of recall and NDCG, thus verifying the effectiveness of Multi-IAIGCN.

Translations in Children’s Paradise (1970–1979): the Union’s agendas and the Cold War cultural diplomacy in Hong Kong

During the Cold War era, translation constituted an integral part of the ideological confrontations of US cultural diplomacy. Scholarly discussions on US-associated cultural products have provided insights from the perspective of American patronage, yet have not adequately addressed the diverse role of unofficial agencies in their cultural practices with multiple intentions. This study analyzes Chinese translations in the magazine Children’s Paradise (CP) operated by the Union, an entity involved in the network of American covert cultural diplomatic activities. It delves into the Union’s agenda of furthering a progressive Chinese nation that continues and revitalizes Chinese civilization by analyzing three marked characteristics of the translated texts and their underlying rationales. It finds that, through deliberate omissions, substitutions, and additions, CP demonstrated a relentless commitment to the Union’s China-centric agendas in its domesticated and adapted translations. Despite sharing the anti-communist conviction associated with American interests, CP leveraged localized practices to engage with the social-political issues of the British-ruled Hong Kong of the 1970s. As a result, it generated cultural outcomes exceeding the Cold War polarities, and left a lasting legacy on the younger generation of Hong Kong.

Multiple Discrimination and Substance Use Intention in Late Childhood: Findings From the Adolescent Brain Cognitive Development (ABCD) Study

PurposeThe study aimed to investigate longitudinal, bidirectional associations between discrimination due to multiple reasons (race/ethnicity, sexual orientation, weight; termed multiple discrimination) and substance use (SU) intention in late childhood. These associations were compared across youth with no, single, and multiple (i.e., intersecting) marginalized identities based on race/ethnicity, sexual orientation, and overweight status. MethodsData were drawn from a national sample of youth in the Adolescent Brain Cognitive Development study (N = 8,530; 9–12 years old). Youth reported both their experiences of multiple discrimination (the number of forms of discrimination youth experienced) and SU intention at one-year and two-year follow-ups. Theoretically relevant covariates were included. ResultsCompared to non-marginalized youth (n = 2,689) and youth with single marginalized identities (n = 3,399), youth with intersecting marginalized identities (n = 2,442) reported the highest SU intention and multiple discrimination across waves. Only for this last group, multiple discrimination predicted stronger SU intention subsequently (β = 0.07, 95% confidence interval [0.02, 0.11]), whereas stronger SU intention predicted lower levels of multiple discrimination over time (β = −0.06, 95% confidence interval [-0.09, −0.02]). Sensitivity analyses yielded similar patterns with some nuances among subgroups of youth with varying intersecting marginalized identities. DiscussionMultiple discrimination predicted stronger SU intention over time in late childhood, particularly among youth with intersecting marginalized identities. Policies and practices should consider addressing multiple discrimination to reduce SU disparities among diverse youth.

Impact of Multiple Job Demands on Chinese University Teachers’ Turnover Intentions

Teacher turnover presents a significant challenge in education. Despite recognizing the importance of examining turnover intention to address this issue, exploring the interplay between multiple job demands and turnover intention is lacking within the framework of the job demands-resources theory. To fill this gap, the present study theoretically examined the relationship among personal resources (career adaptability), job burnout, turnover intention, and various job demands (teaching–research and work–family conflicts). Data were collected through an online survey of 875 Chinese university teachers, and the conceptual model was estimated using maximum likelihood estimation. The results revealed that work–family and teaching–research conflicts directly predict teachers’ turnover intentions and that job burnout mediates between multiple job demands and turnover intentions. Furthermore, career adaptability moderates the mediating role of burnout. These findings offer innovative ideas for mitigating and preventing faculty turnover intentions.

Gradient-Based Optimization for Intent Conflict Resolution

The evolving landscape of network systems necessitates automated tools for streamlined management and configuration. Intent-driven networking (IDN) has emerged as a promising solution for autonomous network management by prioritizing declaratively defined desired outcomes over traditional manual configurations without specifying the implementation details. This paradigm shift towards flexibility, agility, and simplification in network management is particularly crucial in addressing inefficiencies and high costs linked to manual management, notably in the radio access part. This paper explores the concurrent operation of multiple intents, acknowledging the potential for conflicts, and proposes an innovative reformulation of these conflicts to enhance network administration effectiveness. Following the initial detection of conflicts among intents using a gradient-based approach, our work employs the Multiple Gradient Descent Algorithm (MGDA) to minimize all loss functions assigned to each intent simultaneously. In response to the challenge posed by the absence of a closed-form representation for each key performance indicator in a dynamic environment for computing gradient descent, the Stochastic Perturbation Stochastic Approximation (SPSA) is integrated into the MGDA algorithm. The proposed method undergoes initial testing using a commonly employed toy example in the literature before being simulated for conflict scenarios within a mobile network using the ns3 network simulator.

Obstacle Intention Awareness in Automatic Ship Collision Avoidance: Full-Scale Experiments in Confined Waters

In this article, full-scale experiments with a dynamic obstacle intention-aware Collision Avoidance System (CAS) are presented. The CAS consists of the Probabilistic Scenario-Based Model Predictive Control (PSB-MPC) for trajectory planning, dynamic obstacle avoidance, and antigrounding, with a Dynamic Bayesian Network (DBN) used for inferring obstacle intentions online. The novelty of this article lies in the utilization of intention information in deliberate collision-free planning. By inferring multiple different intention states on how and if nearby obstacles adhere to the COLREGS, the PSB-MPC can plan COLREGS-compliant avoidance maneuvers when possible, taking into account its awareness of the situation. The experiments put emphasis on hazardous situations where this intention information is both useful and necessary in order to avoid high collision risk. To the authors’ knowledge, the work is the first field experimental validation of such a probabilistic intention-aware CAS with consideration of multiple intention states. The experimental results demonstrate the validity of the proposed CAS scheme, with adherence to the traffic rules (COLREGS) 7, 8 and 13–17 in a diverse set of situations. The strengths and weaknesses of the proposed CAS are also discussed, giving insights that can be useful for researchers and practitioners in the field. Here, challenges related to detecting obstacle maneuvers and making the intention inference more robust to noise should be addressed as future work to make the scheme better suited for general usage on ships engaged in real traffic.

SSE4Rec: Sequential recommendation with subsequence extraction

Sequential recommendation mines the sequential patterns in user behavior data to recommend items to users. Recent studies have mainly followed the language modeling paradigm, on the premise that the next item depends on the sequence of previous items. Notably, differences exist between user behavior and textual data. One key difference is that behavioral sequences can encompass multiple intentions, unlike sentences that typically express a single intention. Furthermore, behavioral sequences emerge freely from users, whereas sentences conform to grammatical rules. This study highlights the risk of treating behavior sequences as a unified sequence, and the resultant potential for overfitting the observed transitions. We mitigated this risk by using subsequence extraction for recommendation (SSE4Rec). This model employs a subsequence extraction module that disperses items into distinct subsequences and groups of related items. Each subsequence is then processed by an independent downstream sequence model, which discourages the memorization of inconsequential transitions. Both the training and inference strategies are inherently integrated into the model. The proposed method was evaluated on four public datasets, whereby it was demonstrated to outperform publicly available alternatives or deliver competitive results. The properties of the model were also explored, further visualizing the output of the subsequence extraction module.

Label-Aware Calibration and Relation-Preserving in Visual Intention Understanding.

Visual intention understanding is a challenging task that explores the hidden intention behind the images of publishers in social media. Visual intention represents implicit semantics, whose ambiguous definition inevitably leads to label shifting and label blemish. The former indicates that the same image delivers intention discrepancies under different data augmentations, while the latter represents that the label of intention data is susceptible to errors or omissions during the annotation process. This paper proposes a novel method, called Label-aware Calibration and Relation-preserving (LabCR) to alleviate the above two problems from both intra-sample and inter-sample views. First, we disentangle the multiple intentions into a single intention for explicit distribution calibration in terms of the overall and the individual. Calibrating the class probability distributions in augmented instance pairs provides consistent inferred intention to address label shifting. Second, we utilize the intention similarity to establish correlations among samples, which offers additional supervision signals to form correlation alignments in instance pairs. This strategy alleviates the effect of label blemish. Extensive experiments have validated the superiority of the proposed method LabCR in visual intention understanding and pedestrian attribute recognition. Code is available at https://github.com/ShiQingHongYa/LabCR.

A Framework for Elastic Adaptation of User Multiple Intents in Sequential Recommendation

A Framework for Elastic Adaptation of User Multiple Intents in Sequential Recommendation

Decoupled Progressive Distillation for Sequential Prediction with Interaction Dynamics

Sequential prediction has great value for resource allocation due to its capability in analyzing intents for next prediction. A fundamental challenge arises from real-world interaction dynamics where similar sequences involving multiple intents may exhibit different next items. More importantly, the character of volume candidate items in sequential prediction may amplify such dynamics, making deep networks hard to capture comprehensive intents. This article presents a sequential prediction framework with Decoupled Progressive Distillation (DePoD), drawing on the progressive nature of human cognition. We redefine target and non-target item distillation according to their different effects in the decoupled formulation. This can be achieved through two aspects: (1) Regarding how to learn, our target item distillation with progressive difficulty increases the contribution of low-confidence samples in the later training phase while keeping high-confidence samples in the earlier phase. And, the non-target item distillation starts from a small subset of non-target items from which size increases according to the item frequency. (2) Regarding whom to learn from, a difference evaluator is utilized to progressively select an expert that provides informative knowledge among items from the cohort of peers. Extensive experiments on four public datasets show DePoD outperforms state-of-the-art methods in terms of accuracy-based metrics.

Research on the Identification of a Winter Olympic Multi-Intent Chinese Problem Based on Multi-Model Fusion

Aiming at addressing the inability of traditional web technologies to effectively respond to Winter-Olympics-related user questions containing multiple intentions, this paper explores a multi-model fusion-based multi-intention recognition model BCNBLMATT to solve this problem. The model is proposed to address the characteristics of complex semantics, strong contextual relevance, and a large number of informative features of the Chinese problem text related to the Winter Olympics, as well as the limitations of the traditional word vector model, such as insufficient expression in the textual representation and the relative concern mechanism of feature expression. The BCNBLMATT model first obtains a comprehensive feature vector representation of the problem text through BERT. Then, a multi-scale text convolutional neural network model and a BiLSTM-Multi-heads attention model (a joint model combining a bidirectional long- and short-term attention network with a multi-head attention mechanism) are used to capture local features at more scales and contextually critical information features at more levels. Finally, the two obtained kinds of features are concatenated and fused to obtain richer and more comprehensive information about the problem text features, which improves the model’s performance in the multi-attention recognition task. Comparative experiments on the Winter Olympics Chinese question dataset and the MixATIS question dataset show that the BCNBLMATT model significantly improves the three metrics of macro-averaged precision, macro-averaged recall, and macro-averaged F1 value and exhibits better generalization. This study provides an effective solution to the multi-intent recognition task for Winter Olympic problems, overcomes the limitations of traditional models, and provides new ideas for improving the performance of multi-intent recognition.

I Know Your Intent

With the booming of smart home market, intelligent Internet of Things (IoT) devices have been increasingly involved in home life. To improve the user experience of smart homes, some prior works have explored how to use machine learning for predicting interactions between users and devices. However, the existing solutions have inferior User Device Interaction (UDI) prediction accuracy, as they ignore three key factors: routine, intent and multi-level periodicity of human behaviors. In this paper, we present SmartUDI, a novel accurate UDI prediction approach for smart homes. First, we propose a Message-Passing-based Routine Extraction (MPRE) algorithm to mine routine behaviors, then the contrastive loss is applied to narrow representations among behaviors from the same routines and alienate representations among behaviors from different routines. Second, we propose an Intent-aware Capsule Graph Attention Network (ICGAT) to encode multiple intents of users while considering complex transitions between different behaviors. Third, we design a Cluster-based Historical Attention Mechanism (CHAM) to capture the multi-level periodicity by aggregating the current sequence and the semantically nearest historical sequence representations through the attention mechanism. SmartUDI can be seamlessly deployed on cloud infrastructures of IoT device vendors and edge nodes, enabling the delivery of personalized device service recommendations to users. Comprehensive experiments on four real-world datasets show that SmartUDI consistently outperforms the state-of-the-art baselines with more accurate and highly interpretable results.