Large audio-video language models can generate descriptions for both video and audio. However, they sometimes ignore audio content, producing audio descriptions solely reliant on visual information. This paper refers to this as audio hallucinations and analyzes them in large audio-video language models. We gather 1,000 sentences by inquiring about audio information and annotate them whether they contain hallucinations. If a sentence is hallucinated, we also categorize the type of hallucination. The results reveal that 332 sentences are hallucinated with distinct trends observed in nouns and verbs for each hallucination type. Based on this, we tackle a task of audio hallucination classification using pre-trained audio-text models in the zero-shot and fine-tuning settings. Our experimental results reveal that the zero-shot models achieve higher performance (52.2% in F1) than the random (40.3%) and the fine-tuning models achieve 87.9%, outperforming the zero-shot models.
Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation. Recently, pretrained large language models have further enhanced the effectiveness by leveraging richer textual information in user profiles and job descriptions apart from user behavior features and job metadata. However, the general domain-oriented design struggles to capture the unique structural information within user profiles and job descriptions, leading to a loss of latent semantic correlations. We propose TAROT, a hierarchical multitask co-pretraining framework, to better utilize structural and semantic information for informative text embeddings. TAROT targets semi-structured text in profiles and jobs, and it is co-pretained with multi-grained pretraining tasks to constrain the acquired semantic information at each level. Experiments on a real-world LinkedIn dataset show significant performance improvements, proving its effectiveness in person-job fit tasks.
This paper explores sentence-level Multilingual Visual Speech Recognition with a single model for the first time. As the massive multilingual modeling of visual data requires huge computational costs, we propose a novel strategy, processing with visual speech units. Motivated by the recent success of the audio speech unit, the proposed visual speech unit is obtained by discretizing the visual speech features extracted from the self-supervised visual speech model. To correctly capture multilingual visual speech, we first train the self-supervised visual speech model on 5,512 hours of multilingual audio-visual data. Through analysis, we verify that the visual speech units mainly contain viseme information while suppressing non-linguistic information. By using the visual speech units as the inputs of our system, we pre-train the model to predict corresponding text outputs on massive multilingual data constructed by merging several VSR databases. As both the inputs and outputs are discrete, we can greatly improve the training efficiency compared to the standard VSR training. Specifically, the input data size is reduced to 0.016% of the original video inputs. In order to complement the insufficient visual information in speech recognition, we apply curriculum learning where the inputs of the system begin with audio-visual speech units and gradually change to visual speech units. After pre-training, the model is finetuned on continuous features. We set new state-of-the-art multilingual VSR performances by achieving comparable performances to the previous language-specific VSR models, with a single trained model.
Traditional bird classifiers mostly rely on the visual characteristics of birds. Some prior works even train classifiers to be invariant to the background, completely discarding the living environment of birds. Instead, we are the first to explore integrating habitat information, one of the four major cues for identifying birds by ornithologists, into modern bird classifiers. We focus on two leading model types: (1) CNNs and ViTs trained on the downstream bird datasets; and (2) original, multi-modal CLIP. Training CNNs and ViTs with habitat-augmented data results in an improvement of up to +0.83 and +0.23 points on NABirds and CUB-200, respectively. Similarly, adding habitat descriptors to the prompts for CLIP yields a substantial accuracy boost of up to +0.99 and +1.1 points on NABirds and CUB-200, respectively. We find consistent accuracy improvement after integrating habitat features into the image augmentation process and into the textual descriptors of vision-language CLIP classifiers. Code is available at: https://anonymous.4open.science/r/reasoning-8B7E/.
Several metaheuristics use decomposition and pruning strategies to solve large-scale instances of the vehicle routing problem (VRP). Those complexity reduction techniques often rely on simple, problem-specific rules. However, the growth in available data and advances in computer hardware enable data-based approaches that use machine learning (ML) to improve scalability of solution algorithms. We propose a decompose-route-improve (DRI) framework that groups customers using clustering. Its similarity metric incorporates customers' spatial, temporal, and demand data and is formulated to reflect the problem's objective function and constraints. The resulting sub-routing problems can independently be solved using any suitable algorithm. We apply pruned local search (LS) between solved subproblems to improve the overall solution. Pruning is based on customers' similarity information obtained in the decomposition phase. In a computational study, we parameterize and compare existing clustering algorithms and benchmark the DRI against the Hybrid Genetic Search (HGS) of Vidal et al. (2013). Results show that our data-based approach outperforms classic cluster-first, route-second approaches solely based on customers' spatial information. The newly introduced similarity metric forms separate sub-VRPs and improves the selection of LS moves in the improvement phase. Thus, the DRI scales existing metaheuristics to achieve high-quality solutions faster for large-scale VRPs by efficiently reducing complexity. Further, the DRI can be easily adapted to various solution methods and VRP characteristics, such as distribution of customer locations and demands, depot location, and different time window scenarios, making it a generalizable approach to solving routing problems.
The revolution in materials in the past century was built on a knowledge of the atomic arrangements and the structure-property relationship. The sine qua non for obtaining quantitative structural information is single crystal crystallography. However, increasingly we need to solve structures in cases where the information content in our input signal is significantly degraded, for example, due to orientational averaging of grains, finite size effects due to nanostructure, and mixed signals due to sample heterogeneity. Understanding the structure property relationships in such situations is, if anything, more important and insightful, yet we do not have robust approaches for accomplishing it. In principle, machine learning (ML) and deep learning (DL) are promising approaches since they augment information in the degraded input signal with prior knowledge learned from large databases of already known structures. Here we present a novel ML approach, a variational query-based multi-branch deep neural network that has the promise to be a robust but general tool to address this problem end-to-end. We demonstrate the approach on computed powder x-ray diffraction (PXRD), along with partial chemical composition information, as input. We choose as a structural representation a modified electron density we call the Cartesian mapped electron density (CMED), that straightforwardly allows our ML model to learn material structures across different chemistries, symmetries and crystal systems. When evaluated on theoretically simulated data for the cubic and trigonal crystal systems, the system achieves up to $93.4\%$ average similarity with the ground truth on unseen materials, both with known and partially-known chemical composition information, showing great promise for successful structure solution even from degraded and incomplete input data.
State of the art Named Entity Recognition (NER) models have achieved an impressive ability to extract common phrases from text that belong to labels such as location, organization, time, and person. However, typical NER systems that rely on having seen a specific entity in their training data in order to label an entity perform poorly on rare or unseen entities ta in order to label an entity perform poorly on rare or unseen entities (Derczynski et al., 2017). This paper attempts to improve recognition of person names, a diverse category that can grow any time someone is born or changes their name. In order for downstream tasks to not exhibit bias based on cultural background, a model should perform well on names from a variety of backgrounds. In this paper I experiment with the training data and input structure of an English Bi-LSTM name recognition model. I look at names from 103 countries to compare how well the model performs on names from different cultures, specifically in the context of a downstream task where extracted names will be matched to information on file. I find that a model with combined character and word input outperforms word-only models and may improve on accuracy compared to classical NER models that are not geared toward identifying unseen entity values.
Entity alignment (EA), a pivotal process in integrating multi-source Knowledge Graphs (KGs), seeks to identify equivalent entity pairs across these graphs. Most existing approaches regard EA as a graph representation learning task, concentrating on enhancing graph encoders. However, the decoding process in EA - essential for effective operation and alignment accuracy - has received limited attention and remains tailored to specific datasets and model architectures, necessitating both entity and additional explicit relation embeddings. This specificity limits its applicability, particularly in GNN-based models. To address this gap, we introduce a novel, generalized, and efficient decoding approach for EA, relying solely on entity embeddings. Our method optimizes the decoding process by minimizing Dirichlet energy, leading to the gradient flow within the graph, to promote graph homophily. The discretization of the gradient flow produces a fast and scalable approach, termed Triple Feature Propagation (TFP). TFP innovatively channels gradient flow through three views: entity-to-entity, entity-to-relation, and relation-to-entity. This generalized gradient flow enables TFP to harness the multi-view structural information of KGs. Rigorous experimentation on diverse real-world datasets demonstrates that our approach significantly enhances various EA methods. Notably, the approach achieves these advancements with less than 6 seconds of additional computational time, establishing a new benchmark in efficiency and adaptability for future EA methods.
Collaborative perception allows each agent to enhance its perceptual abilities by exchanging messages with others. It inherently results in a trade-off between perception ability and communication costs. Previous works transmit complete full-frame high-dimensional feature maps among agents, resulting in substantial communication costs. To promote communication efficiency, we propose only transmitting the information needed for the collaborator's downstream task. This pragmatic communication strategy focuses on three key aspects: i) pragmatic message selection, which selects task-critical parts from the complete data, resulting in spatially and temporally sparse feature vectors; ii) pragmatic message representation, which achieves pragmatic approximation of high-dimensional feature vectors with a task-adaptive dictionary, enabling communicating with integer indices; iii) pragmatic collaborator selection, which identifies beneficial collaborators, pruning unnecessary communication links. Following this strategy, we first formulate a mathematical optimization framework for the perception-communication trade-off and then propose PragComm, a multi-agent collaborative perception system with two key components: i) single-agent detection and tracking and ii) pragmatic collaboration. The proposed PragComm promotes pragmatic communication and adapts to a wide range of communication conditions. We evaluate PragComm for both collaborative 3D object detection and tracking tasks in both real-world, V2V4Real, and simulation datasets, OPV2V and V2X-SIM2.0. PragComm consistently outperforms previous methods with more than 32.7K times lower communication volume on OPV2V. Code is available at github.com/PhyllisH/PragComm.
Semantically rich descriptions of manufacturing machines, offered in a machine-interpretable code, can provide interesting benefits in Industry 4.0 scenarios. However, the lack of that type of descriptions is evident. In this paper we present the development effort made to build an ontology, called ExtruOnt, for describing a type of manufacturing machine, more precisely, a type that performs an extrusion process (extruder). Although the scope of the ontology is restricted to a concrete domain, it could be used as a model for the development of other ontologies for describing manufacturing machines in Industry 4.0 scenarios. The terms of the ExtruOnt ontology provide different types of information related with an extruder, which are reflected in distinct modules that constitute the ontology. Thus, it contains classes and properties for expressing descriptions about components of an extruder, spatial connections, features, and 3D representations of those components, and finally the sensors used to capture indicators about the performance of this type of machine. The ontology development process has been carried out in close collaboration with domain experts.