For years, Caisse des Depots et Consignations has produced information filtering applications. To be operational, these applications require high filtering performances which are achieved by using rule-based filters. With this technique, an administrator has to tune a set of rules for each topic. However, filters become obsolescent over time. The decrease of their performances is due to diachronic polysemy of terms that involves a loss of precision and to diachronic polymorphism of concepts that involves a loss of recall. To help the administrator to maintain his filters, we have developed a method which automatically detects filtering obsolescence. It consists in making a learning-based control filter using a set of documents which have already been categorised as relevant or not relevant by the rule-based filter. The idea is to supervise this filter by processing a differential comparison of its outcomes with those of the control one. This method has many advantages. It is simple to implement since the training set used by the learning is supplied by the rule-based filter. Thus, both the making and the use of the control filter are fully automatic. With automatic detection of obsolescence, learning-based filtering finds a rich application which offers interesting prospects.
Two classes of methods have been shown to be useful for resolving lexical ambiguity. The first relies on the presence of particular words within some distance of the ambiguous target word; the second uses the pattern of words and part-of-speech tags around the target word. These methods have complementary coverage: the former captures the lexical ``atmosphere'' (discourse topic, tense, etc.), while the latter captures local syntax. Yarowsky has exploited this complementarity by combining the two methods using decision lists. The idea is to pool the evidence provided by the component methods, and to then solve a target problem by applying the single strongest piece of evidence, whatever type it happens to be. This paper takes Yarowsky's work as a starting point, applying decision lists to the problem of context-sensitive spelling correction. Decision lists are found, by and large, to outperform either component method. However, it is found that further improvements can be obtained by taking into account not just the single strongest piece of evidence, but ALL the available evidence. A new hybrid method, based on Bayesian classifiers, is presented for doing this, and its performance improvements are demonstrated.
Marker-less monocular 3D human motion capture (MoCap) with scene interactions is a challenging research topic relevant for extended reality, robotics and virtual avatar generation. Due to the inherent depth ambiguity of monocular settings, 3D motions captured with existing methods often contain severe artefacts such as incorrect body-scene inter-penetrations, jitter and body floating. To tackle these issues, we propose HULC, a new approach for 3D human MoCap which is aware of the scene geometry. HULC estimates 3D poses and dense body-environment surface contacts for improved 3D localisations, as well as the absolute scale of the subject. Furthermore, we introduce a 3D pose trajectory optimisation based on a novel pose manifold sampling that resolves erroneous body-environment inter-penetrations. Although the proposed method requires less structured inputs compared to existing scene-aware monocular MoCap algorithms, it produces more physically-plausible poses: HULC significantly and consistently outperforms the existing approaches in various experiments and on different metrics.
Visual storytelling (VST) is the task of generating a story paragraph that describes a given image sequence. Most existing storytelling approaches have evaluated their models using traditional natural language generation metrics like BLEU or CIDEr. However, such metrics based on n-gram matching tend to have poor correlation with human evaluation scores and do not explicitly consider other criteria necessary for storytelling such as sentence structure or topic coherence. Moreover, a single score is not enough to assess a story as it does not inform us about what specific errors were made by the model. In this paper, we propose 3 evaluation metrics sets that analyses which aspects we would look for in a good story: 1) visual grounding, 2) coherence, and 3) non-redundancy. We measure the reliability of our metric sets by analysing its correlation with human judgement scores on a sample of machine stories obtained from 4 state-of-the-arts models trained on the Visual Storytelling Dataset (VIST). Our metric sets outperforms other metrics on human correlation, and could be served as a learning based evaluation metric set that is complementary to existing rule-based metrics.
Artificial intelligence (AI) has been widely applied to music generation topics such as continuation, melody/harmony generation, genre transfer and music infilling application. Although with the burst interest to apply AI to music, there are still few interfaces for the musicians to take advantage of the latest progress of the AI technology. This makes those tools less valuable in practice and harder to find its advantage/drawbacks without utilizing them in the real scenario. This work builds a max patch for interactive music infilling application with different levels of control, including track density/polyphony/occupation rate and bar tonal tension control. The user can select the melody/bass/harmony track as the infilling content up to 16 bars. The infilling algorithm is based on the author's previous work, and the interface sends/receives messages to the AI system hosted in the cloud. This interface lowers the barrier of AI technology and can generate different variations of the selected content. Those results can give several alternatives to the musicians' composition, and the interactive process realizes the value of the AI infilling system.
Understanding document images (e.g., invoices) has been an important research topic and has many applications in document processing automation. Through the latest advances in deep learning-based Optical Character Recognition (OCR), current Visual Document Understanding (VDU) systems have come to be designed based on OCR. Although such OCR-based approach promise reasonable performance, they suffer from critical problems induced by the OCR, e.g., (1) expensive computational costs and (2) performance degradation due to the OCR error propagation. In this paper, we propose a novel VDU model that is end-to-end trainable without underpinning OCR framework. To this end, we propose a new task and a synthetic document image generator to pre-train the model to mitigate the dependencies on large-scale real document images. Our approach achieves state-of-the-art performance on various document understanding tasks in public benchmark datasets and private industrial service datasets. Through extensive experiments and analysis, we demonstrate the effectiveness of the proposed model especially with consideration for a real-world application.
Humans' continual learning (CL) ability is closely related to Stability Versus Plasticity Dilemma that describes how humans achieve ongoing learning capacity and preservation for learned information. The notion of CL has always been present in artificial intelligence (AI) since its births. This paper proposes a comprehensive review of CL. Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism. Analogous to biological counterpart, "smart" AI agents are supposed to i) remember previously learned information (information retrospection); ii) infer on new information continuously (information prospection:); iii) transfer useful information (information transfer), to achieve high-level CL. According to the taxonomy, evaluation metrics, algorithms, applications as well as some open issues are then introduced. Our main contributions concern i) rechecking CL from the level of artificial general intelligence; ii) providing a detailed and extensive overview on CL topics; iii) presenting some novel ideas on the potential development of CL.
Audio segmentation and sound event detection are crucial topics in machine listening that aim to detect acoustic classes and their respective boundaries. It is useful for audio-content analysis, speech recognition, audio-indexing, and music information retrieval. In recent years, most research articles adopt segmentation-by-classification. This technique divides audio into small frames and individually performs classification on these frames. In this paper, we present a novel approach called You Only Hear Once (YOHO), which is inspired by the YOLO algorithm popularly adopted in Computer Vision. We convert the detection of acoustic boundaries into a regression problem instead of frame-based classification. This is done by having separate output neurons to detect the presence of an audio class and predict its start and end points. YOHO obtained a higher F-measure and lower error rate than the state-of-the-art Convolutional Recurrent Neural Network on multiple datasets. As YOHO is purely a convolutional neural network and has no recurrent layers, it is faster during inference. In addition, as this approach is more end-to-end and predicts acoustic boundaries directly, it is significantly quicker during post-processing and smoothing.
A marked Petri net is lucent if there are no two different reachable markings enabling the same set of transitions, i.e., states are fully characterized by the transitions they enable. Characterizing the class of systems that are lucent is a foundational and also challenging question. However, little research has been done on the topic. In this paper, it is shown that all free-choice nets having a home cluster are lucent. These nets have a so-called home marking such that it is always possible to reach this marking again. Such a home marking can serve as a regeneration point or as an end-point. The result is highly relevant because in many applications, we want the system to be lucent and many well-behaved process models fall into the class identified in this paper. Unlike previous work, we do not require the marked Petri net to be live and strongly connected. Most of the analysis techniques for free-choice nets are tailored towards well-formed nets. The approach presented in this paper provides a novel perspective enabling new analysis techniques for free-choice nets that do not need to be well-formed. Therefore, we can also model systems and processes that are terminating and/or have an initialization phase.
The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks. However, a relatively less discussed topic is what if more context information is introduced into current top-scoring tagging systems. Although several existing works have attempted to shift tagging systems from sentence-level to document-level, there is still no consensus conclusion about when and why it works, which limits the applicability of the larger-context approach in tagging tasks. In this paper, instead of pursuing a state-of-the-art tagging system by architectural exploration, we focus on investigating when and why the larger-context training, as a general strategy, can work. To this end, we conduct a thorough comparative study on four proposed aggregators for context information collecting and present an attribute-aided evaluation method to interpret the improvement brought by larger-context training. Experimentally, we set up a testbed based on four tagging tasks and thirteen datasets. Hopefully, our preliminary observations can deepen the understanding of larger-context training and enlighten more follow-up works on the use of contextual information.