Marie-Francine Moens

ECAI Conference 2025 Conference Paper

CCMPlus: Leveraging Latent Causal Relationships Among Web Services for Traffic Prediction

• Chang Tian
• Mingzhe Xing
• Zenglin Shi
• Matthew B. Blaschko
• Yinliang Yue
• Marie-Francine Moens

Predicting web service traffic is crucial for system operation tasks including dynamic resource scaling, anomaly detection, and fraud detection. Web service traffic is characterized by frequent and drastic fluctuations over time and are influenced by heterogeneous user behaviors, making accurate prediction a challenging task. Previous research has extensively explored statistical approaches, and neural networks to mine features from preceding service traffic time series for prediction. However, these methods have largely overlooked the latent causal relationships between services. Drawing inspiration from causality in ecological systems, we empirically recognize the causal relationships between web services. To leverage these relationships for improved traffic prediction, we propose an effective neural network module, CCMPlus, designed to extract causal relationship features across services. This module can be seamlessly integrated with existing time series models to consistently enhance the performance of traffic predictions. We theoretically justify that the causal correlation matrix generated by the CCMPlus module captures causal relationships among services. Empirical results on real-world datasets from Microsoft Azure, Alibaba Group, and Ant Group confirm that our method surpasses state-of-the-art approaches in Mean Squared Error and Mean Absolute Error for predicting service traffic time series. These findings highlight the efficacy of feature representations from the CCMPlus module.

NeurIPS Conference 2025 Conference Paper

Consistent Story Generation: Unlocking the Potential of Zigzag Sampling

• Mingxiao Li
• Mang Ning
• Marie-Francine Moens

Text-to-image generation models have made significant progress in producing high-quality images from textual descriptions, yet they continue to struggle with maintaining subject consistency across multiple images, a fundamental requirement for visual storytelling. Existing methods attempt to address this by either fine-tuning models on large-scale story visualization datasets, which is resource-intensive, or by using training-free techniques that share information across generations, which still yield limited success. In this paper, we introduce a novel training-free sampling strategy called Zigzag Sampling with Asymmetric Prompts and Visual Sharing to enhance subject consistency in visual story generation. Our approach proposes a zigzag sampling mechanism that alternates between asymmetric prompting to retain subject characteristics, while a visual sharing module transfers visual cues across generated images to enforce consistency. Experimental results, based on both quantitative metrics and qualitative evaluations, demonstrate that our method significantly outperforms previous approaches in generating coherent and consistent visual stories. The code is available at https: //github. com/Mingxiao-Li/Asymmetry-Zigzag-StoryDiffusion.

AIJ Journal 2025 Journal Article

Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments

• Liesbeth Allein
• Maria Mihaela Truşcǎ
• Marie-Francine Moens

AAAI Conference 2025 Conference Paper

NeuralFlix: A Simple While Effective Framework for Semantic Decoding of Videos from Non-invasive Brain Recordings

• Jingyuan Sun
• Mingxiao Li
• Marie-Francine Moens

In our quest to decode the visual processing of the human brain, we aim to reconstruct dynamic visual experiences from brain activities, a task both challenging and intriguing. Although recent advances have made significant strides in reconstructing static images from non-invasive brain recordings, the translation of continuous brain activities into video formats has not been extensively explored. Our study introduces NeuralFlix, a simple but effective dual-phase framework designed to address the inherent challenges in decoding fMRI data, such as noise, spatial redundancy, and temporal lags. The framework employs spatial and temporal augmentation for contrastive learning of fMRI representations, and a diffusion model enhanced with dependent prior noise for generating videos. Tested on a publicly available fMRI dataset, NeuralFlix demonstrates promising results, significantly outperforming previous state-of-the-art models by margins of 20.97%, 31.00%, and 12.30%, respectively, in decoding the brain activities of three subjects individually, as measured by SSIM.

ICLR Conference 2024 Conference Paper

Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps

• Mingxiao Li 0002
• Tingyu Qu
• Ruicong Yao
• Wei Sun 0046
• Marie-Francine Moens

Diffusion Probabilistic Models (DPM) have shown remarkable efficacy in the synthesis of high-quality images. However, their inference process characteristically requires numerous, potentially hundreds, of iterative steps, which could exaggerate the problem of exposure bias due to the training and inference discrepancy. Previous work has attempted to mitigate this issue by perturbing inputs during training, which consequently mandates the retraining of the DPM. In this work, we conduct a systematic study of exposure bias in DPM and, intriguingly, we find that the exposure bias could be alleviated with a novel sampling method that we propose, without retraining the model. We empirically and theoretically show that, during inference, for each backward time step t and corresponding state ˆxt, there might exist another time step $t_s$ which exhibits superior coupling with $\hat{x}_t$. Based on this finding, we introduce a sampling method named Time-Shift Sampler. Our framework can be seamlessly integrated to existing sampling algorithms, such as DDPM, DDIM and other high-order solvers, inducing merely minimal additional computations. Experimental results show our method brings significant and consistent improvements in FID scores on different datasets and sampling methods. For example, integrating Time-Shift Sampler to F-PNDM yields a FID=3.88, achieving 44.49% improvements as compared to F-PNDM, on CIFAR-10 with 10 sampling steps, which is more performant than the vanilla DDIM with 100 sampling steps. Our code is available at https://github.com/Mingxiao-Li/TS-DPM.

NeurIPS Conference 2023 Conference Paper

Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities

• Jingyuan Sun
• Mingxiao Li
• Zijiao Chen
• Yunhao Zhang
• Shaonan Wang
• Marie-Francine Moens

Decoding visual stimuli from neural responses recorded by functional Magnetic Resonance Imaging (fMRI) presents an intriguing intersection between cognitive neuroscience and machine learning, promising advancements in understanding human visual perception. However, the task is challenging due to the noisy nature of fMRI signals and the intricate pattern of brain visual representations. To mitigate these challenges, we introduce a two-phase fMRI representation learning framework. The first phase pre-trains an fMRI feature learner with a proposed Double-contrastive Mask Auto-encoder to learn denoised representations. The second phase tunes the feature learner to attend to neural activation patterns most informative for visual reconstruction with guidance from an image auto-encoder. The optimized fMRI feature learner then conditions a latent diffusion model to reconstruct image stimuli from brain activities. Experimental results demonstrate our model's superiority in generating high-resolution and semantically accurate images, substantially exceeding previous state-of-the-art methods by 39. 34% in the 50-way-top-1 semantic classification accuracy. The code implementations is available at https: //github. com/soinx0629/vis dec neurips/.

ECAI Conference 2023 Conference Paper

Decoding Realistic Images from Brain Activity with Contrastive Self-Supervision and Latent Diffusion

• Jingyuan Sun
• Mingxiao Li 0002
• Marie-Francine Moens

Reconstructing visual stimuli from human brain activities provides a promising opportunity to advance our understanding of the brain’s visual system and its connection with computer vision models. Although deep generative models have been employed for this task, the challenge of generating high-quality images with accurate semantics persists due to the intricate underlying representations of brain signals and the limited availability of parallel data. In this paper, we propose a two-phase framework named Contrast and Diffuse (CnD) to decode realistic images from functional magnetic resonance imaging (fMRI) recordings. In the first phase, we acquire representations of fMRI data through self-supervised contrastive learning. In the second phase, the encoded fMRI representations condition the diffusion model to reconstruct visual stimulus through our proposed concept-aware conditioning method. Experimental results show that CnD reconstructs highly plausible images on challenging benchmarks. We also provide a quantitative interpretation of the connection between the latent diffusion model (LDM) components and the human brain’s visual system. In summary, we present an effective approach for reconstructing visual stimuli based on human brain activity and offer a novel framework to understand the relationship between the diffusion model and the human brain visual system. The code is released at https: //github. com/Mingxiao-Li/BrainDecoding.

IJCAI Conference 2023 Conference Paper

Fine-tuned vs. Prompt-tuned Supervised Representations: Which Better Account for Brain Language Representations?

• Jingyuan Sun
• Marie-Francine Moens

To decipher the algorithm underlying the human brain's language representation, previous work probed brain responses to language input with pre-trained artificial neural network (ANN) models fine-tuned on NLU tasks. However, full fine-tuning generally updates the entire parametric space and distorts pre-trained features, cognitively inconsistent with the brain's robust multi-task learning ability. Prompt-tuning, in contrast, protects pre-trained weights and learns task-specific embeddings to fit a task. Could prompt-tuning generate representations that better account for the brain's language representations than fine-tuning? If so, what kind of NLU task leads a pre-trained model to better decode the information represented in the human brain? We investigate these questions by comparing prompt-tuned and fine-tuned representations in neural decoding, that is predicting the linguistic stimulus from the brain activities evoked by the stimulus. We find that on none of the 10 NLU tasks, full fine-tuning significantly outperforms prompt-tuning in neural decoding, implicating that a more brain-consistent tuning method yields representations that better correlate with brain data. Moreover, we identify that tasks dealing with fine-grained concept meaning yield representations that better decode brain activation patterns than other tasks, especially the syntactic chunking task. This indicates that our brain encodes more fine-grained concept information than shallow syntactic information when representing languages.

ECAI Conference 2023 Conference Paper

Investigating Neural Fit Approaches for Sentence Embedding Model Paradigms

• Helena Balabin
• Antonietta Gabriella Liuzzi
• Jingyuan Sun
• Patrick Dupont
• Rik Vandenberghe
• Marie-Francine Moens

In recent years, representations from brain activity patterns and pre-trained language models have been linked to each other based on neural fits to validate hypotheses about language processing. Nonetheless, open questions remain about what intrinsic properties of language processing these neural fits reflect and whether they differ across neural fit approaches, brain networks, and models. In this study, we use parallel sentence and functional magnetic resonance imaging data to perform a comprehensive analysis of four paradigms (masked language modeling, pragmatic coherence, semantic comparison, and contrastive learning) representing linguistic hypotheses about sentence processing. We include three sentence embedding models for each paradigm, resulting in a total of 12 models, and examine differences in their neural fit to four different brain networks using regression-based neural encoding and Representational Similarity Analysis (RSA). Among the different models tested, GPT-2, SkipThoughts, and S-RoBERTa yielded the strongest correlations with language network patterns, whereas contrastive learning-based models resulted in overall low neural fits. Our findings demonstrate that neural fits vary across brain networks and models representing the same linguistic hypothesis (e. g. , GPT-2 and GPT-3). More importantly, we show the need for both neural encoding and RSA as complementary methods to provide full understanding of neural fits. All code used in the analysis is publicly available: https: //github. com/lcn-kul/sentencefmricomparison.

AAAI Conference 2023 Conference Paper

Layout-Aware Dreamer for Embodied Visual Referring Expression Grounding

• Mingxiao Li
• Zehao Wang
• Tinne Tuytelaars
• Marie-Francine Moens

In this work, we study the problem of Embodied Referring Expression Grounding, where an agent needs to navigate in a previously unseen environment and localize a remote object described by a concise high-level natural language instruction. When facing such a situation, a human tends to imagine what the destination may look like and to explore the environment based on prior knowledge of the environmental layout, such as the fact that a bathroom is more likely to be found near a bedroom than a kitchen. We have designed an autonomous agent called Layout-aware Dreamer (LAD), including two novel modules, that is, the Layout Learner and the Goal Dreamer to mimic this cognitive decision process. The Layout Learner learns to infer the room category distribution of neighboring unexplored areas along the path for coarse layout estimation, which effectively introduces layout common sense of room-to-room transitions to our agent. To learn an effective exploration of the environment, the Goal Dreamer imagines the destination beforehand. Our agent achieves new state-of-the-art performance on the public leaderboard of REVERIE dataset in challenging unseen test environments with improvement on navigation success rate (SR) by 4.02% and remote grounding success (RGS) by 3.43% comparing to previous previous state of the art. The code is released at https://github.com/zehao-wang/LAD.

ICLR Conference 2023 Conference Paper

Online Bias Correction for Task-Free Continual Learning

• Aristotelis Chrysakis
• Marie-Francine Moens

Task-free continual learning is the machine-learning setting where a model is trained online with data generated by a nonstationary stream. Conventional wisdom suggests that, in this setting, models are trained using an approach called experience replay, where the risk is computed both with respect to current stream observations and to a small subset of past observations. In this work, we explain both theoretically and empirically how experience replay biases the outputs of the model towards recent stream observations. Moreover, we propose a simple approach to mitigate this bias online, by changing how the output layer of the model is optimized. We show that our approach improves significantly the learning performance of experience-replay approaches over different datasets. Our findings suggest that, when performing experience replay, the output layer of the model should be optimized separately from the preceding layers.

ECAI Conference 2023 Conference Paper

Tuning in to Neural Encoding: Linking Human Brain and Artificial Supervised Representations of Language

• Jingyuan Sun
• Xiaohan Zhang
• Marie-Francine Moens

To understand the algorithm that supports the human brain’s language representation, previous research has attempted to predict neural responses to linguistic stimuli using embeddings generated by artificial neural networks (ANNs), a process known as neural encoding. However, most of these studies have focused on probing neural representations of Germanic languages, such as English, with unsupervised ANNs. In this paper, we propose to bridge the gap between human brain and supervised ANN representations of the Chinese language. Specifically, we investigate how task tuning influences a pretained Transformer for neural encoding and which tasks lead to the best encoding performances. We generate supervised representations on eight Natural Language Understanding (NLU) tasks using prompt-tuning, a technique that is seldom explored in neural encoding for language. We demonstrate that prompt-tuning yields representations that better predict neural responses to Chinese stimuli than traditional fine-tuning on four tasks. Furthermore, we discover that tasks that require a fine-grained processing of concepts and entities lead to representations that are most predictive of brain activation patterns. Additionally, we reveal that the proportion of tuned parameters highly influences the neural encoding performance of fine-tuned models. Overall, our experimental findings could help us better understand the relationship between supervised artificial and brain language representations.

EAAI Journal 2022 Journal Article

Corrigendum to “Giving commands to a self-driving car: How to deal with uncertain situations?” [Eng. Appl. Artif. Intell. 103 (2021) 104257]

• Thierry Deruyttere
• Victor Milewski
• Marie-Francine Moens

AAAI Conference 2022 Conference Paper

Dynamic Key-Value Memory Enhanced Multi-Step Graph Reasoning for Knowledge-Based Visual Question Answering

• Mingxiao Li
• Marie-Francine Moens

Knowledge-based visual question answering (VQA) is a vision-language task that requires an agent to correctly answer image-related questions using knowledge that is not presented in the given image. It is not only a more challenging task than regular VQA but also a vital step towards building a general VQA system. Most existing knowledge-based VQA systems process knowledge and image information similarly and ignore the fact that the knowledge base (KB) contains complete information about a triplet, while the extracted image information might be incomplete as the relations between two objects are missing or wrongly detected. In this paper, we propose a novel model named dynamic knowledge memory enhanced multi-step graph reasoning (DMMGR), which performs explicit and implicit reasoning over a key-value knowledge memory module and a spatial-aware image graph, respectively. Specifically, the memory module learns a dynamic knowledge representation and generates a knowledge-aware question representation at each reasoning step. Then, this representation is used to guide a graph attention operator over the spatial-aware image graph. Our model achieves new stateof-the-art accuracy on the KRVQR and FVQA datasets. We also conduct ablation experiments to prove the effectiveness of each component of the proposed model.

AAAI Conference 2022 Conference Paper

Predicting Physical World Destinations for Commands Given to Self-Driving Cars

• Dusan Grujicic
• Thierry Deruyttere
• Marie-Francine Moens
• Matthew B. Blaschko

In recent years, we have seen significant steps taken in the development of self-driving cars. Multiple companies are starting to roll out impressive systems that work in a variety of settings. These systems can sometimes give the impression that full self-driving is just around the corner and that we would soon build cars without even a steering wheel. The increase in the level of autonomy and control given to an AI provides an opportunity for new modes of human-vehicle interaction. However, surveys have shown that giving more control to an AI in self-driving cars is accompanied by a degree of uneasiness by passengers. In an attempt to alleviate this issue, recent works have taken a natural language-oriented approach by allowing the passenger to give commands that refer to specific objects in the visual scene. Nevertheless, this is only half the task as the car should also understand the physical destination of the command, which is what we focus on in this paper. We propose an extension in which we annotate the 3D destination that the car needs to reach after executing the given command and evaluate multiple different baselines on predicting this destination location. Additionally, we introduce a model that outperforms the prior works adapted for this particular setting.

EAAI Journal 2021 Journal Article

Giving commands to a self-driving car: How to deal with uncertain situations?

• Thierry Deruyttere
• Victor Milewski
• Marie-Francine Moens

IJCAI Conference 2020 Conference Paper

A Survey on Temporal Reasoning for Temporal Information Extraction from Text (Extended Abstract)

• Artuur Leeuwenberg
• Marie-Francine Moens

Time is deeply woven into how people perceive, and communicate about the world. Almost unconsciously, we provide our language utterances with temporal cues, like verb tenses, and we can hardly produce sentences without such cues. Extracting temporal cues from text, and constructing a global temporal view about the order of described events is a major challenge of automatic natural language understanding. Temporal reasoning, the process of combining different temporal cues into a coherent temporal view, plays a central role in temporal information extraction. This article presents a comprehensive survey of the research from the past decades on temporal reasoning for automatic temporal information extraction from text, providing a case study on the integration of symbolic reasoning with machine learning-based information extraction systems.

NeurIPS Conference 2020 Conference Paper

Convolutional Generation of Textured 3D Meshes

• Dario Pavllo
• Graham Spinks
• Thomas Hofmann
• Marie-Francine Moens
• Aurelien Lucchi

While recent generative models for 2D images achieve impressive visual results, they clearly lack the ability to perform 3D reasoning. This heavily restricts the degree of control over generated objects as well as the possible applications of such models. In this work, we bridge this gap by leveraging recent advances in differentiable rendering. We design a framework that can generate triangle meshes and associated high-resolution texture maps, using only 2D supervision from single-view natural images. A key contribution of our work is the encoding of the mesh and texture as 2D representations, which are semantically aligned and can be easily modeled by a 2D convolutional GAN. We demonstrate the efficacy of our method on Pascal3D+ Cars and CUB, both in an unconditional setting and in settings where the model is conditioned on class labels, attributes, and text. Finally, we propose an evaluation methodology that assesses the mesh and texture quality separately.

ICML Conference 2020 Conference Paper

Online Continual Learning from Imbalanced Data

• Aristotelis Chrysakis
• Marie-Francine Moens

A well-documented weakness of neural networks is the fact that they suffer from catastrophic forgetting when trained on data provided by a non-stationary distribution. Recent work in the field of continual learning attempts to understand and overcome this issue. Unfortunately, the majority of relevant work embraces the implicit assumption that the distribution of observed data is perfectly balanced, despite the fact that, in the real world, humans and animals learn from observations that are temporally correlated and severely imbalanced. Motivated by this remark, we aim to evaluate memory population methods that are used in online continual learning, when dealing with highly imbalanced and temporally correlated streams of data. More importantly, we introduce a new memory population approach, which we call class-balancing reservoir sampling (CBRS). We demonstrate that CBRS outperforms the state-of-the-art memory population algorithms in a considerably challenging learning setting, over a range of different datasets, and for multiple architectures.

JAIR Journal 2019 Journal Article

A Survey on Temporal Reasoning for Temporal Information Extraction from Text

• Artuur Leeuwenberg
• Marie-Francine Moens

Time is deeply woven into how people perceive, and communicate about the world. Almost unconsciously, we provide our language utterances with temporal cues, like verb tenses, and we can hardly produce sentences without such cues. Extracting temporal cues from text, and constructing a global temporal view about the order of described events is a major challenge of automatic natural language understanding. Temporal reasoning, the process of combining different temporal cues into a coherent temporal view, plays a central role in temporal information extraction. This article presents a comprehensive survey of the research from the past decades on temporal reasoning for automatic temporal information extraction from text, providing a case study on how combining symbolic reasoning with machine learning-based information extraction systems can improve performance. It gives a clear overview of the used methodologies for temporal reasoning, and explains how temporal reasoning can be, and has been successfully integrated into temporal information extraction systems. Based on the distillation of existing work, this survey also suggests currently unexplored research areas. We argue that the level of temporal reasoning that current systems use is still incomplete for the full task of temporal information extraction, and that a deeper understanding of how the various types of temporal information can be integrated into temporal reasoning is required to drive future research in this area.

AAAI Conference 2018 Conference Paper

Acquiring Common Sense Spatial Knowledge Through Implicit Spatial Templates

• Guillem Collell
• Luc Van Gool
• Marie-Francine Moens

Spatial understanding is a fundamental problem with widereaching real-world applications. The representation of spatial knowledge is often modeled with spatial templates, i. e. , regions of acceptability of two objects under an explicit spatial relationship (e. g. , “on”, “below”, etc.). In contrast with prior work that restricts spatial templates to explicit spatial prepositions (e. g. , “glass on table”), here we extend this concept to implicit spatial language, i. e. , those relationships (generally actions) for which the spatial arrangement of the objects is only implicitly implied (e. g. , “man riding horse”). In contrast with explicit relationships, predicting spatial arrangements from implicit spatial language requires significant common sense spatial understanding. Here, we introduce the task of predicting spatial templates for two objects under a relationship, which can be seen as a spatial question-answering task with a (2D) continuous output (“where is the man w. r. t. a horse when the man is walking the horse? ”). We present two simple neural-based models that leverage annotated images and structured text to learn this task. The good performance of these models reveals that spatial locations are to a large extent predictable from implicit spatial language. Crucially, the models attain similar performance in a challenging generalized setting, where the object-relation-object combinations (e. g. ,“man walking dog”) have never been seen before. Next, we go one step further by presenting the models with unseen objects (e. g. , “dog”). In this scenario, we show that leveraging word embeddings enables the models to output accurate spatial predictions, proving that the models acquire solid common sense spatial knowledge allowing for such generalization.

AAAI Conference 2017 Conference Paper

Imagined Visual Representations as Multimodal Embeddings

• Guillem Collell
• Ted Zhang
• Marie-Francine Moens

Language and vision provide complementary information. Integrating both modalities in a single multimodal representation is an unsolved problem with wide-reaching applications to both natural language processing and computer vision. In this paper, we present a simple and effective method that learns a language-to-vision mapping and uses its output visual predictions to build multimodal representations. In this sense, our method provides a cognitively plausible way of building representations, consistent with the inherently reconstructive and associative nature of human memory. Using seven benchmark concept similarity tests we show that the mapped (or imagined) vectors not only help to fuse multimodal information, but also outperform strong unimodal baselines and state-of-the-art multimodal methods, thus exhibiting more human-like judgments. Ultimately, the present work sheds light on fundamental questions of natural language understanding concerning the fusion of vision and language such as the plausibility of more associative and reconstructive approaches.

JAIR Journal 2016 Journal Article

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

• Ivan Vulić
• Marie-Francine Moens

We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, that is, bilingual word embeddings (BWEs). Unlike prior work on inducing BWEs which heavily relied on parallel sentence-aligned corpora and/or readily available translation resources such as dictionaries, the article reveals that BWEs may be learned solely on the basis of document-aligned comparable data without any additional lexical resources nor syntactic information. We present a comparison of our approach with previous state-of-the-art models for learning bilingual word representations from comparable data that rely on the framework of multilingual probabilistic topic modeling (MuPTM), as well as with distributional local context-counting models. We demonstrate the utility of the induced BWEs in two semantic tasks: (1) bilingual lexicon extraction, (2) suggesting word translations in context for polysemous words. Our simple yet effective BWE-based models significantly outperform the MuPTM-based and context-counting representation models from comparable data as well as prior BWE-based models, and acquire the best reported results on both tasks for all three tested language pairs.

AAAI Conference 2014 Conference Paper

Forecasting Potential Diabetes Complications

• Yang Yang
• Walter Luyten
• Lu Liu
• Marie-Francine Moens
• Jie Tang
• Juanzi Li

Diabetes complications often afflict diabetes patients seriously: over 68% of diabetes-related mortality is caused by diabetes complications. In this paper, we study the problem of automatically diagnosing diabetes complications from patients’ lab test results. The objective problem has two main challenges: 1) feature sparseness: a patient only undergoes 1. 26% lab tests on average, and 65. 5% types of lab tests are performed on samples from less than 10 patients; 2) knowledge skewness: it lacks comprehensive detailed domain knowledge of the association between diabetes complications and lab tests. To address these challenges, we propose a novel probabilistic model called Sparse Factor Graph Model (SparseFGM). SparseFGM projects sparse features onto a lower-dimensional latent space, which alleviates the problem of sparseness. SparseFGM is also able to capture the associations between complications and lab tests, which help handle the knowledge skewness. We evaluate the proposed model on a large collections of real medical records. SparseFGM outperforms (+20% by F1) baselines significantly and gives detailed associations between diabetes complications and lab tests.

AILAW Journal 2011 Journal Article

Argumentation mining

• Raquel Mochales
• Marie-Francine Moens

Abstract Argumentation mining aims to automatically detect, classify and structure argumentation in text. Therefore, argumentation mining is an important part of a complete argumentation analyisis, i. e. understanding the content of serial arguments, their linguistic structure, the relationship between the preceding and following arguments, recognizing the underlying conceptual beliefs, and understanding within the comprehensive coherence of the specific topic. We present different methods to aid argumentation mining, starting with plain argumentation detection and moving forward to a more structural analysis of the detected argumentation. Different state-of-the-art techniques on machine learning and context free grammars are applied to solve the challenges of argumentation mining. We also highlight fundamental questions found during our research and analyse different issues for future research on argumentation mining.

AILAW Journal 2001 Journal Article

Innovative techniques for legal text retrieval

• Marie-Francine Moens

Legal text retrieval traditionally relies upon external knowledge sources such as thesauri and classification schemes, and an accurate indexing of the documents is often manually done. As a result not all legal documents can be effectively retrieved. However a number of current artificial intelligence techniques are promising for legal text retrieval. They sustain the acquisition of knowledge and the knowledge-rich processing of the content of document texts and information need, and of their matching. Currently, techniques for learning information needs, learning concept attributes of texts, information extraction, text classification and clustering, and text summarization need to be studied in legal text retrieval because of their potential for improving retrieval and decreasing the cost of manual indexing. The resulting query and text representations are semantically much richer than a set of key terms. Their use allows for more refined retrieval models in which some reasoning can be applied. This paper gives an overview of the state of the art of these innovativetechniques and their potential for legal text retrieval.

AILAW Journal 1998 Journal Article

Salomon: Automatic Abstracting of Legal Cases for Effective Access to Court Decisions

• Caroline Uyttendaele
• Marie-Francine Moens
• Jos Dumortier

The SALOMON project is a contribution to the automatic processing of legal texts. Its aim is to automatically summarise Belgian criminal cases in order to improve access to the large number of existing and future cases. Therefore, techniques are developed for identifying and extracting relevant information from the cases. A broader application of these techniques could considerably simplify the work of the legal profession. A double methodology was used when developing SALOMON: the cases are processed by employing additional knowledge to interpret structural patterns and features on the one hand and by way of occurrence statistics of index terms on the other. As a result, SALOMON performs an initial categorisation and structuring of the cases and subsequently extracts the most relevant text units of the alleged offences and of the opinion of the court. The SALOMON techniques do not themselves solve any legal questions, but they do guide the user effectively towards relevant texts.