Showing 1–19 of 19 results for author: Kuebler, S

CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning

Authors: Ayoub Belouadah, Sylvain Kubler, Yves Le Traon

Abstract: Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as Constrained Markov Decision Processes (CMDPs). While primal-dual methods scale well to deep RL, they often suffer from delayed constraint correction, leading to oscillatory behavior and prolonged safety violations. In this paper, we propose Constraint-Sensitive Policy Op… ▽ More Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as Constrained Markov Decision Processes (CMDPs). While primal-dual methods scale well to deep RL, they often suffer from delayed constraint correction, leading to oscillatory behavior and prolonged safety violations. In this paper, we propose Constraint-Sensitive Policy Optimization (CSPO), a first-order primal-dual method that incorporates local constraint sensitivity into policy updates. CSPO augments the primal objective with a constraint-sensitive correction derived from the shortest signed distance to the safety boundary, enabling smarter recovery steps back to safety, compensating for delayed Lagrange multiplier updates, reducing oscillations near the boundary, and preserving the KKT solutions of the original constrained problem. Experiments on navigation and locomotion benchmarks demonstrate that CSPO achieves faster safety recovery and high reward preservation, resulting in higher constrained returns compared to state-of-the-art primal-dual and penalty-based methods △ Less

Submitted 12 June, 2026; originally announced June 2026.

Comments: Accepted as a Spotlight paper at the 43rd International Conference on Machine Learning (ICML 2026)

Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search

Authors: Chaimaa Medjadji, Sylvain Kubler, Yves Le Traon, Guilain Leduc, Sadi Alawadi, Feras M. Awaysheh

Abstract: Federated Learning (FL) enables collaborative model training without centralizing data. However, real-world deployments must simultaneously address statistical heterogeneity across client data (non-IID), system heterogeneity in device capabilities, and communication efficiency. Existing FL approaches mitigate these challenges through improved aggregation, personalization, or knowledge distillation… ▽ More Federated Learning (FL) enables collaborative model training without centralizing data. However, real-world deployments must simultaneously address statistical heterogeneity across client data (non-IID), system heterogeneity in device capabilities, and communication efficiency. Existing FL approaches mitigate these challenges through improved aggregation, personalization, or knowledge distillation, but they almost universally assume a fixed client architecture, limiting adaptability to heterogeneous data complexity and hardware constraints. This architectural constraint often leads to suboptimal trade-offs between accuracy and efficiency in real-world FL systems. This work introduces FedKDNAS, a distillation-driven FL framework that combines client-side neural architecture selection with distillation of server-coordinated knowledge. Each client autonomously selects a lightweight model under accuracy-resource constraints. It then trains it locally using a hybrid objective combining supervised learning and knowledge distillation and shares only predictions on a public reference set. The server then aggregates and smooths these predictions, optionally combining them with a teacher model, to produce stable distillation targets for the next round. Extensive evaluation on six datasets against six representative FL baselines (FedAvg, Ditto, FedMD, FedDF, FedDistill, Local-KD) demonstrates that FedKDNAS consistently achieves superior Pareto efficiency, improving accuracy by up to 15\% under non-IID conditions, reducing client CPU usage by approximately 28\%, and decreasing communication overhead by up to 44 times while maintaining lightweight logit-based communication. △ Less

Submitted 20 May, 2026; originally announced May 2026.

Federated Imputation under Heterogeneous Feature Spaces

Authors: Imane Hocine, Chaimaa Medjadji, Sylvain Kubler, Gregoire Danoy, Yves Le Traon

Abstract: Federated Learning (FL) enables collaborative training across decentralized clients, but most methods assume aligned feature schemas, an assumption that rarely holds in tabular settings where clients observe only partially overlapping feature subsets. In these heterogeneous feature spaces, parameter-averaging methods (e.g., FedAvg) transfer little information across weakly overlapping or disjoint… ▽ More Federated Learning (FL) enables collaborative training across decentralized clients, but most methods assume aligned feature schemas, an assumption that rarely holds in tabular settings where clients observe only partially overlapping feature subsets. In these heterogeneous feature spaces, parameter-averaging methods (e.g., FedAvg) transfer little information across weakly overlapping or disjoint feature groups, limiting their effectiveness for federated imputation. To overcome this, we propose \textbf{FedHF-Impute}, a federated imputation framework that separates structural feature unavailability from conventional missingness and uses a shared global feature graph to propagate information across statistically related features through message passing. This enables indirect cross-client knowledge transfer, even when features are never jointly observed locally, while preserving standard federated communication. Under simulated partial schema overlap on the SECOM and AirQuality datasets, FedHF-Impute improves imputation accuracy (RMSE) over FL baselines by 26.9\%, and 8.4\% respectively, while achieving comparable performance on PhysioNET, with only a 0.3\% difference relative to the best baseline. △ Less

Submitted 15 May, 2026; originally announced May 2026.

Centralized vs Decentralized Federated Learning: A trade-off performance analysis

Authors: Chaimaa Medjadji, Guilain Leduc, Sylvain Kubler, Yves Le Traon

Abstract: Federated Learning (FL) has emerged as a promising paradigm for collaborative model training across distributed edge devices while preserving data privacy especially with the huge increase amount of data due to the adoption of technologies which contributes to the growing number of IoT devices. Storing this amount of data centrally is challenging due to issues like limited communication, privacy,… ▽ More Federated Learning (FL) has emerged as a promising paradigm for collaborative model training across distributed edge devices while preserving data privacy especially with the huge increase amount of data due to the adoption of technologies which contributes to the growing number of IoT devices. Storing this amount of data centrally is challenging due to issues like limited communication, privacy, and regulations. FL can be Centralized (CFL), Decentralized (DFL), and Semi-decentralized (SDFL). Choosing the right FL architecture depends on the application's needs. However, very few research studies have experimentally compared these three types of architectures to not only understand the respective strengths and limitations, but also trade-offs between different performance indicators. This paper overcome this lack of analysis, conducting experimental analyses using the Fedstellar simulator, MNIST dataset, and MLP classifier. △ Less

Submitted 15 May, 2026; originally announced May 2026.

Multimodal Analysis of State-Funded News Coverage of the Israel-Hamas War on YouTube Shorts

Authors: Daniel Miehling, Sandra Kuebler

Abstract: YouTube Shorts have become central to news consumption on the platform, yet research on how geopolitical events are represented in this format remains limited. To address this gap, we present a multimodal pipeline that combines automatic transcription, aspect-based sentiment analysis (ABSA), and semantic scene classification. The pipeline is first assessed for feasibility and then applied to analy… ▽ More YouTube Shorts have become central to news consumption on the platform, yet research on how geopolitical events are represented in this format remains limited. To address this gap, we present a multimodal pipeline that combines automatic transcription, aspect-based sentiment analysis (ABSA), and semantic scene classification. The pipeline is first assessed for feasibility and then applied to analyze short-form coverage of the Israel-Hamas war by state-funded outlets. Using over 2,300 conflict-related Shorts and more than 94,000 visual frames, we systematically examine war reporting across major international broadcasters. Our findings reveal that the sentiment expressed in transcripts regarding specific aspects differs across outlets and over time, whereas scene-type classifications reflect visual cues consistent with real-world events. Notably, smaller domain-adapted models outperform large transformers and even LLMs for sentiment analysis, underscoring the value of resource-efficient approaches for humanities research. The pipeline serves as a template for other short-form platforms, such as TikTok and Instagram, and demonstrates how multimodal methods, combined with qualitative interpretation, can characterize sentiment patterns and visual cues in algorithmically driven video environments. △ Less

Submitted 1 April, 2026; originally announced April 2026.

Test Time Training for AC Power Flow Surrogates via Physics and Operational Constraint Refinement

Authors: Panteleimon Dogoulis, Mohammad Iman Alizadeh, Sylvain Kubler, Maxime Cordy

Abstract: Power Flow (PF) calculation based on machine learning (ML) techniques offer significant computational advantages over traditional numerical methods but often struggle to maintain full physical consistency. This paper introduces a physics-informed test-time training (PI-TTT) framework that enhances the accuracy and feasibility of ML-based PF surrogates by enforcing AC power flow equalities and oper… ▽ More Power Flow (PF) calculation based on machine learning (ML) techniques offer significant computational advantages over traditional numerical methods but often struggle to maintain full physical consistency. This paper introduces a physics-informed test-time training (PI-TTT) framework that enhances the accuracy and feasibility of ML-based PF surrogates by enforcing AC power flow equalities and operational constraints directly at inference time. The proposed method performs a lightweight self-supervised refinement of the surrogate outputs through few gradient-based updates, enabling local adaptation to unseen operating conditions without requiring labeled data. Extensive experiments on the IEEE 14-, 118-, and 300-bus systems and the PEGASE 1354-bus network show that PI-TTT reduces power flow residuals and operational constraint violations by one to two orders of magnitude compared with purely ML-based models, while preserving their computational advantage. The results demonstrate that PI-TTT provides fast, accurate, and physically reliable predictions, representing a promising direction for scalable and physics-consistent learning in power system analysis. △ Less

Submitted 27 November, 2025; originally announced November 2025.

Counterfactual Explainable AI (XAI) Method for Deep Learning-Based Multivariate Time Series Classification

Authors: Alan G. Paredes Cetina, Kaouther Benguessoum, Raoni Lourenço, Sylvain Kubler

Abstract: Recent advances in deep learning have improved multivariate time series (MTS) classification and regression by capturing complex patterns, but their lack of transparency hinders decision-making. Explainable AI (XAI) methods offer partial insights, yet often fall short of conveying the full decision space. Counterfactual Explanations (CE) provide a promising alternative, but current approaches typi… ▽ More Recent advances in deep learning have improved multivariate time series (MTS) classification and regression by capturing complex patterns, but their lack of transparency hinders decision-making. Explainable AI (XAI) methods offer partial insights, yet often fall short of conveying the full decision space. Counterfactual Explanations (CE) provide a promising alternative, but current approaches typically prioritize either accuracy, proximity or sparsity -- rarely all -- limiting their practical value. To address this, we propose CONFETTI, a novel multi-objective CE method for MTS. CONFETTI identifies key MTS subsequences, locates a counterfactual target, and optimally modifies the time series to balance prediction confidence, proximity and sparsity. This method provides actionable insights with minimal changes, improving interpretability, and decision support. CONFETTI is evaluated on seven MTS datasets from the UEA archive, demonstrating its effectiveness in various domains. CONFETTI consistently outperforms state-of-the-art CE methods in its optimization objectives, and in six other metrics from the literature, achieving $\geq10\%$ higher confidence while improving sparsity in $\geq40\%$. △ Less

Submitted 24 November, 2025; v1 submitted 17 November, 2025; originally announced November 2025.

Comments: Accepted in AAAI 2026 Technical Main Track

FedSparQ: Adaptive Sparse Quantization with Error Feedback for Robust & Efficient Federated Learning

Authors: Chaimaa Medjadji, Sadi Alawadi, Feras M. Awaysheh, Guilain Leduc, Sylvain Kubler, Yves Le Traon

Abstract: Federated Learning (FL) enables collaborative model training across decentralized clients while preserving data privacy by keeping raw data local. However, FL suffers from significant communication overhead due to the frequent exchange of high-dimensional model updates over constrained networks. In this paper, we present FedSparQ, a lightweight compression framework that dynamically sparsifies the… ▽ More Federated Learning (FL) enables collaborative model training across decentralized clients while preserving data privacy by keeping raw data local. However, FL suffers from significant communication overhead due to the frequent exchange of high-dimensional model updates over constrained networks. In this paper, we present FedSparQ, a lightweight compression framework that dynamically sparsifies the gradient of each client through an adaptive threshold, applies half-precision quantization to retained entries and integrates residuals from error feedback to prevent loss of information. FedSparQ requires no manual tuning of sparsity rates or quantization schedules, adapts seamlessly to both homogeneous and heterogeneous data distributions, and is agnostic to model architecture. Through extensive empirical evaluation on vision benchmarks under independent and identically distributed (IID) and non-IID data, we show that FedSparQ substantially reduces communication overhead (reducing by 90% of bytes sent compared to FedAvg) while preserving or improving model accuracy (improving by 6% compared to FedAvg non-compressed solution or to state-of-the-art compression models) and enhancing convergence robustness (by 50%, compared to the other baselines). Our approach provides a practical, easy-to-deploy solution for bandwidth-constrained federated deployments and lays the groundwork for future extensions in adaptive precision and privacy-preserving protocols. △ Less

Submitted 5 November, 2025; originally announced November 2025.

Towards a Framework for Supporting the Ethical and Regulatory Certification of AI Systems

Authors: Fabian Kovac, Sebastian Neumaier, Timea Pahi, Torsten Priebe, Rafael Rodrigues, Dimitrios Christodoulou, Maxime Cordy, Sylvain Kubler, Ali Kordia, Georgios Pitsiladis, John Soldatos, Petros Zervoudakis

Abstract: Artificial Intelligence has rapidly become a cornerstone technology, significantly influencing Europe's societal and economic landscapes. However, the proliferation of AI also raises critical ethical, legal, and regulatory challenges. The CERTAIN (Certification for Ethical and Regulatory Transparency in Artificial Intelligence) project addresses these issues by developing a comprehensive framework… ▽ More Artificial Intelligence has rapidly become a cornerstone technology, significantly influencing Europe's societal and economic landscapes. However, the proliferation of AI also raises critical ethical, legal, and regulatory challenges. The CERTAIN (Certification for Ethical and Regulatory Transparency in Artificial Intelligence) project addresses these issues by developing a comprehensive framework that integrates regulatory compliance, ethical standards, and transparency into AI systems. In this position paper, we outline the methodological steps for building the core components of this framework. Specifically, we present: (i) semantic Machine Learning Operations (MLOps) for structured AI lifecycle management, (ii) ontology-driven data lineage tracking to ensure traceability and accountability, and (iii) regulatory operations (RegOps) workflows to operationalize compliance requirements. By implementing and validating its solutions across diverse pilots, CERTAIN aims to advance regulatory compliance and to promote responsible AI innovation aligned with European standards. △ Less

Submitted 30 September, 2025; originally announced October 2025.

Comments: Accepted for publication in the proceedings of the Workshop on AI Certification, Fairness and Regulations, co-located with the Austrian Symposium on AI and Vision (AIRoV 2025)

Science Out of Its Ivory Tower: Improving Accessibility with Reinforcement Learning

Authors: Haining Wang, Jason Clark, Hannah McKelvey, Leila Sterman, Zheng Gao, Zuoyu Tian, Sandra Kübler, Xiaozhong Liu

Abstract: A vast amount of scholarly work is published daily, yet much of it remains inaccessible to the general public due to dense jargon and complex language. To address this challenge in science communication, we introduce a reinforcement learning framework that fine-tunes a language model to rewrite scholarly abstracts into more comprehensible versions. Guided by a carefully balanced combination of wor… ▽ More A vast amount of scholarly work is published daily, yet much of it remains inaccessible to the general public due to dense jargon and complex language. To address this challenge in science communication, we introduce a reinforcement learning framework that fine-tunes a language model to rewrite scholarly abstracts into more comprehensible versions. Guided by a carefully balanced combination of word- and sentence-level accessibility rewards, our language model effectively substitutes technical terms with more accessible alternatives, a task which models supervised fine-tuned or guided by conventional readability measures struggle to accomplish. Our best model adjusts the readability level of scholarly abstracts by approximately six U.S. grade levels -- in other words, from a postgraduate to a high school level. This translates to roughly a 90% relative boost over the supervised fine-tuning baseline, all while maintaining factual accuracy and high-quality language. An in-depth analysis of our approach shows that balanced rewards lead to systematic modifications in the base model, likely contributing to smoother optimization and superior performance. We envision this work as a step toward bridging the gap between scholarly research and the general public, particularly younger readers and those without a college degree. △ Less

Submitted 16 April, 2025; v1 submitted 22 October, 2024; originally announced October 2024.

OCNLI: Original Chinese Natural Language Inference

Authors: Hai Hu, Kyle Richardson, Liang Xu, Lu Li, Sandra Kuebler, Lawrence S. Moss

Abstract: Despite the tremendous recent progress on natural language inference (NLI), driven largely by large-scale investment in new datasets (e.g., SNLI, MNLI) and advances in modeling, most progress has been limited to English due to a lack of reliable datasets for most of the world's languages. In this paper, we present the first large-scale NLI dataset (consisting of ~56,000 annotated sentence pairs) f… ▽ More Despite the tremendous recent progress on natural language inference (NLI), driven largely by large-scale investment in new datasets (e.g., SNLI, MNLI) and advances in modeling, most progress has been limited to English due to a lack of reliable datasets for most of the world's languages. In this paper, we present the first large-scale NLI dataset (consisting of ~56,000 annotated sentence pairs) for Chinese called the Original Chinese Natural Language Inference dataset (OCNLI). Unlike recent attempts at extending NLI to other languages, our dataset does not rely on any automatic translation or non-expert annotation. Instead, we elicit annotations from native speakers specializing in linguistics. We follow closely the annotation protocol used for MNLI, but create new strategies for eliciting diverse hypotheses. We establish several baseline results on our dataset using state-of-the-art pre-trained models for Chinese, and find even the best performing models to be far outpaced by human performance (~12% absolute performance gap), making it a challenging new resource that we hope will help to accelerate progress in Chinese NLU. To the best of our knowledge, this is the first human-elicited MNLI-style corpus for a non-English language. △ Less

Submitted 12 October, 2020; originally announced October 2020.

Comments: Findings of EMNLP 2020

MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity

Authors: Hai Hu, Qi Chen, Kyle Richardson, Atreyee Mukherjee, Lawrence S. Moss, Sandra Kuebler

Abstract: We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus. In contrast to existing logic-based approaches, our system is intentionally designed to be as lightweight as possible, and operates using a small set of well-known (surface-level) monotonicity facts about quantifiers, lexical items and to… ▽ More We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus. In contrast to existing logic-based approaches, our system is intentionally designed to be as lightweight as possible, and operates using a small set of well-known (surface-level) monotonicity facts about quantifiers, lexical items and tokenlevel polarity information. Despite its simplicity, we find our approach to be competitive with other logic-based NLI models on the SICK benchmark. We also use MonaLog in combination with the current state-of-the-art model BERT in a variety of settings, including for compositional data augmentation. We show that MonaLog is capable of generating large amounts of high-quality training data for BERT, improving its accuracy on SICK. △ Less

Submitted 19 October, 2019; originally announced October 2019.

Comments: accepted to SCIL 2020

UM-IU@LING at SemEval-2019 Task 6: Identifying Offensive Tweets Using BERT and SVMs

Authors: Jian Zhu, Zuoyu Tian, Sandra Kübler

Abstract: This paper describes the UM-IU@LING's system for the SemEval 2019 Task 6: OffensEval. We take a mixed approach to identify and categorize hate speech in social media. In subtask A, we fine-tuned a BERT based classifier to detect abusive content in tweets, achieving a macro F1 score of 0.8136 on the test data, thus reaching the 3rd rank out of 103 submissions. In subtasks B and C, we used a linear… ▽ More This paper describes the UM-IU@LING's system for the SemEval 2019 Task 6: OffensEval. We take a mixed approach to identify and categorize hate speech in social media. In subtask A, we fine-tuned a BERT based classifier to detect abusive content in tweets, achieving a macro F1 score of 0.8136 on the test data, thus reaching the 3rd rank out of 103 submissions. In subtasks B and C, we used a linear SVM with selected character n-gram features. For subtask C, our system could identify the target of abuse with a macro F1 score of 0.5243, ranking it 27th out of 65 submissions. △ Less

Submitted 6 April, 2019; originally announced April 2019.

UniMorph 2.0: Universal Morphology

Authors: Christo Kirov, Ryan Cotterell, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sabrina J. Mielke, Arya D. McCarthy, Sandra Kübler, David Yarowsky, Jason Eisner, Mans Hulden

Abstract: The Universal Morphology UniMorph project is a collaborative effort to improve how NLP handles complex morphology across the world's languages. The project releases annotated morphological data using a universal tagset, the UniMorph schema. Each inflected form is associated with a lemma, which typically carries its underlying lexical meaning, and a bundle of morphological features from our schema.… ▽ More The Universal Morphology UniMorph project is a collaborative effort to improve how NLP handles complex morphology across the world's languages. The project releases annotated morphological data using a universal tagset, the UniMorph schema. Each inflected form is associated with a lemma, which typically carries its underlying lexical meaning, and a bundle of morphological features from our schema. Additional supporting data and tools are also released on a per-language basis when available. UniMorph is based at the Center for Language and Speech Processing (CLSP) at Johns Hopkins University in Baltimore, Maryland and is sponsored by the DARPA LORELEI program. This paper details advances made to the collection, annotation, and dissemination of project resources since the initial UniMorph release described at LREC 2016. lexical resources} } △ Less

Submitted 25 February, 2020; v1 submitted 25 October, 2018; originally announced October 2018.

Comments: LREC 2018

Detecting Syntactic Features of Translated Chinese

Authors: Hai Hu, Wen Li, Sandra Kübler

Abstract: We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features. Using Support Vector Machines (SVMs) as classifier on a genre-balanced corpus in translation studies of Chinese, we find that constituent parse trees and dependency triples as features without lexical information… ▽ More We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features. Using Support Vector Machines (SVMs) as classifier on a genre-balanced corpus in translation studies of Chinese, we find that constituent parse trees and dependency triples as features without lexical information perform very well on the task, with an F-measure above 90%, close to the results of lexical n-gram features, without the risk of learning topic information rather than translation features. Thus, we claim syntactic features alone can accurately distinguish translated from original Chinese. Translated Chinese exhibits an increased use of determiners, subject position pronouns, NP + 'de' as NP modifiers, multiple NPs or VPs conjoined by a Chinese specific punctuation, among other structures. We also interpret the syntactic features with reference to previous translation studies in Chinese, particularly the usage of pronouns. △ Less

Submitted 23 April, 2018; originally announced April 2018.

Comments: Accepted to 2nd Workshop on Stylistic Variation, NAACL 2018

Information Storage and Retrieval using Macromolecules as Storage Media

Authors: M. Mansuripur, P. K. Khulbe, S. M. Kuebler, J. W. Perry, M. S. Giridhar, J. Kevin Erwin, Kibyung Seong, Seth Marder, N. Peyghambarian

Abstract: To store information at extremely high-density and data-rate, we propose to adapt, integrate, and extend the techniques developed by chemists and molecular biologists for the purpose of manipulating biological and other macromolecules. In principle, volumetric densities in excess of 10^21 bits/cm^3 can be achieved when individual molecules having dimensions below a nanometer or so are used to enco… ▽ More To store information at extremely high-density and data-rate, we propose to adapt, integrate, and extend the techniques developed by chemists and molecular biologists for the purpose of manipulating biological and other macromolecules. In principle, volumetric densities in excess of 10^21 bits/cm^3 can be achieved when individual molecules having dimensions below a nanometer or so are used to encode the 0's and 1's of a binary string of data. In practice, however, given the limitations of electron-beam lithography, thin film deposition and patterning technologies, molecular manipulation in submicron dimensions, etc., we believe that volumetric storage densities on the order of 10^16 bits/cm^3 (i.e., petabytes per cubic centimeter) should be readily attainable, leaving plenty of room for future growth. The unique feature of the proposed new approach is its focus on the feasibility of storing bits of information in individual molecules, each only a few angstroms in size. △ Less

Submitted 26 August, 2017; originally announced August 2017.

Comments: 13 pages, 5 references, 13 figures

Journal ref: Published in Optical Data Storage 2003, Michael O'Neill and Naoyasu Miyagawa, editors; Proceedings of SPIE Vol. 5069, pp231-243 (2003)

CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages

Authors: Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sandra Kübler, David Yarowsky, Jason Eisner, Mans Hulden

Abstract: The CoNLL-SIGMORPHON 2017 shared task on supervised morphological generation required systems to be trained and tested in each of 52 typologically diverse languages. In sub-task 1, submitted systems were asked to predict a specific inflected form of a given lemma. In sub-task 2, systems were given a lemma and some of its specific inflected forms, and asked to complete the inflectional paradigm by… ▽ More The CoNLL-SIGMORPHON 2017 shared task on supervised morphological generation required systems to be trained and tested in each of 52 typologically diverse languages. In sub-task 1, submitted systems were asked to predict a specific inflected form of a given lemma. In sub-task 2, systems were given a lemma and some of its specific inflected forms, and asked to complete the inflectional paradigm by predicting all of the remaining inflected forms. Both sub-tasks included high, medium, and low-resource conditions. Sub-task 1 received 24 system submissions, while sub-task 2 received 3 system submissions. Following the success of neural sequence-to-sequence models in the SIGMORPHON 2016 shared task, all but one of the submissions included a neural component. The results show that high performance can be achieved with small training datasets, so long as models have appropriate inductive bias or make use of additional unlabeled data or synthetic data. However, different biasing and data augmentation resulted in disjoint sets of inflected forms being predicted correctly, suggesting that there is room for future improvement. △ Less

Submitted 4 July, 2017; v1 submitted 27 June, 2017; originally announced June 2017.

Comments: CoNLL 2017

Performing Stance Detection on Twitter Data using Computational Linguistics Techniques

Authors: Gourav G. Shenoy, Erika H. Dsouza, Sandra Kübler

Abstract: As humans, we can often detect from a persons utterances if he or she is in favor of or against a given target entity (topic, product, another person, etc). But from the perspective of a computer, we need means to automatically deduce the stance of the tweeter, given just the tweet text. In this paper, we present our results of performing stance detection on twitter data using a supervised approac… ▽ More As humans, we can often detect from a persons utterances if he or she is in favor of or against a given target entity (topic, product, another person, etc). But from the perspective of a computer, we need means to automatically deduce the stance of the tweeter, given just the tweet text. In this paper, we present our results of performing stance detection on twitter data using a supervised approach. We begin by extracting bag-of-words to perform classification using TIMBL, then try and optimize the features to improve stance detection accuracy, followed by extending the dataset with two sets of lexicons - arguing, and MPQA subjectivity; next we explore the MALT parser and construct features using its dependency triples, finally we perform analysis using Scikit-learn Random Forest implementation. △ Less

Submitted 6 March, 2017; originally announced March 2017.

Comments: 8 pages, 9 figures, 5 tables

ACM Class: I.2.7

Key Factors for Information Dissemination on Communicating Products and Fixed Databases

Authors: Sylvain Kubler, William Derigent, André Thomas, Eric Rondeau

Abstract: Intelligent products carrying their own information are more and more present nowadays. In recent years, some authors argued the usage of such products for the Supply Chain Management Industry. Indeed, a multitude of informational vectors take place in such environments like fixed databases or manufactured products on which we are able to embed significant proportion of data. By considering distri… ▽ More Intelligent products carrying their own information are more and more present nowadays. In recent years, some authors argued the usage of such products for the Supply Chain Management Industry. Indeed, a multitude of informational vectors take place in such environments like fixed databases or manufactured products on which we are able to embed significant proportion of data. By considering distributed database systems, we can allocate specific data fragments to the product useful to manage its own evolution. The paper aims to analyze the Supply Chain performance according to different strategies of information distribution. Thus, different distribution patterns between informational vectors are studied. The purpose is to determine the key factors which lead to improve information distribution performance in term of time properties. △ Less

Submitted 23 June, 2011; originally announced June 2011.

Comments: 12 pages

Journal ref: Service Orientation in Holonic and Multi Agent Manufacturing Control, Paris : France (2011)