检索结果-内蒙古大学图书馆

SJTU at MRP 2019: A transition-based multi-task parser for cross-framework meaning representation parsing 23

学校读者我要写书评

暂无评论

SJTU at MRP 2019: A transition-based multi-task parser for c...

2019 Shared Task on Cross-Framework Meaning Representation Parsing, MRP 2019 at the 23rd Conference for Computational Language Learning, CoNLL 2019

作者： Bai, Hongxiao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

ISBN: (纸本)9781950737604

This paper describes the system of our team SJTU for our participation in the CoNLL 2019 Shared Task: Cross-Framework Meaning Representation Parsing. The goal of the task is to advance data-driven parsing into graph-structured representations of sentence meaning. This task includes five meaning representation frameworks: DM, PSD, EDS, UCCA, and AMR. These frameworks have different properties and structures. To tackle all the frameworks in one model, it is needed to find out the commonality of them. In our work, we define a set of the transition actions to once-for-all tackle all the frameworks and train a transition-based model to parse the meaning representation. The adopted multi-task model also can allow learning for one framework to benefit the others. In the final official evaluation of the shared task, our system achieves 42% F1 unified MRP metric score. © 2019 Association for Computational Linguistics

关键词： Syntactics

Self- And Pseudo-self-supervised prediction of speaker and key-utterance for multi-party dialogue reading comprehension

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Yiyang Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University

Multi-party dialogue machine reading comprehension (MRC) brings tremendous challenge since it involves multiple speakers at one dialogue, resulting in intricate speaker information flows and noisy dialogue contexts. To alleviate such difficulties, previous models focus on how to incorporate these information using complex graph-based modules and additional manually labeled data, which is usually rare in real scenarios. In this paper, we design two labour-free self- and pseudo-self-supervised prediction tasks on speaker and key-utterance to implicitly model the speaker information flows, and capture salient clues in a long dialogue. Experimental results on two benchmark datasets have justified the effectiveness of our method over competitive baselines and current state-of-the-art models1 Copyright © 2021, The Authors. All rights reserved.

关键词： Graphic methods

Graph-free multi-hop reading comprehension: A select-to-guide strategy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Bohong Zhang, Zhuosheng Zhao, Hai The Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University

Multi-hop reading comprehension (MHRC) requires not only to predict the correct answer span in the given passage, but also to provide a chain of supporting evidences for reasoning interpretability. It is natural to model such a process into graph structure by understanding multi-hop reasoning as jumping over entity nodes, which has made graph modelling dominant on this task. Recently, there have been dissenting voices about whether graph modelling is indispensable due to the inconvenience of the graph building, however existing state-of-the-art graph-free attempts suffer from huge performance gap compared to graph-based ones. This work presents a novel graph-free alternative which firstly outperform all graph models on MHRC. In detail, we exploit a select-to-guide (S2G) strategy to accurately retrieve evidence paragraphs in a coarse-to-fine manner, incorporated with two novel attention mechanisms, which surprisingly shows conforming to the nature of multi-hop reasoning. Our graph-free model achieves significant and consistent performance gain over strong baselines and the current new state-of-the-art on the MHRC benchmark, HotpotQA, among all the published works. Copyright © 2021, The Authors. All rights reserved.

关键词： Graphic methods

Neural Correlates of Perceiving Animacy in Robotic Objects

学校读者我要写书评

暂无评论

Research Square

Research Square 2024年

作者： Yizhar, Or Maimon, Amber Tal, Zohar Wald, Iddo Yehoshua Erel, Hadas Friedman, Doron Zuckerman, Oren Amedi, Amir The Baruch Ivcher Institute for Brain Cognition and Technology Baruch Ivcher School of Psychology Reichman University Herzliya Israel Max Planck Institute for Human Development Research Group Adaptive Memory and Decision Making Germany Berlin Germany Computational Psychiatry and Neurotechnology Lab Department of Brain and Cognitive Sciences Ben Gurion University Be’er Sheva Israel Digital Media Lab Department of Mathematics and Computer Science University of Bremen Bremen Germany Proaction Laboratory Faculty of Psychology and Educational Sciences University of Coimbra Coimbra Portugal Media Innovation Lab Sammy Ofer School of Communications Reichman University Herzliya Israel Advanced Reality Lab Sammy Ofer School of Communications Reichman University Herzliya Israel

The prevalence of robots in modern society calls for gaining a fundamental understanding of the underlying principles of human-robot interaction. In particular, we need to understand how people perceive robots and how different physical and social characteristics affect this perception. Here, we examined the neural correlates of observing simple gestures performed by a non-humanoid social robot, focusing on the role of the Ventral Occipitotemporal (VOT) cortex in processing perceived animacy. Our results reveal that a broad bilateral cortical network is activated, comprising areas related to action observation, the social brain, and the visual cortex, including the VOT. We also found a correlation between the level of neural responses in the VOT, especially in the left hemisphere, and individual animacy ratings of the robotic object. This correlation provides a physical basis for such subjective ratings. These results suggest a complex representation of perceived animacy across the lateral-medial axis of the VOT, explained by spatial cortical location and the amplitude of neural responses. Furthermore, we discuss the implications of these findings for understanding how people perceive robots, their behaviors and intentions, which are crucial for developing social robots that can interact with humans more naturally. © 2024, CC BY.

关键词： human robot interaction

Multisensory Approaches to human-Food interaction 20

学校读者我要写书评

暂无评论

Multisensory Approaches to Human-Food Interaction

22nd ACM International Conference on Multimodal interaction, ICMI 2020

作者： Velasco, Carlos Nijholt, Anton Spence, Charles Narumi, Takuji Motoki, Kosuke Huisman, Gijs Obrist, Marianna Department of Marketing Bi Norwegian Business School Oslo Norway University of Twente Human Media Interaction Enschede Netherlands Department of Experimental Psychology University of Oxford Oxford United Kingdom Graduate School of Information Science and Technology University of Tokyo Tokyo Japan Department of Food Science and Business Miyagi University Sendai Japan Digital Society School Amsterdam University of Applied Sciences Amsterdam Netherlands Department of Computer Science University College London London United Kingdom

ISBN: (纸本)9781450375818

Here, we present the outcome of the 4th workshop on Multisensory Approaches to human-Food interaction (MHFI), developed in collaboration with ICMI 2020 in Utrecht, The Netherlands. Capitalizing on the increasing interest on multisensory aspects of human-food interaction and the unique contribution that our community offers, we developed a space to discuss ideas ranging from mechanisms of multisensory food perception, through multisensory technologies, to new applications of systems in the context of MHFI. All in all, the workshop involved 11 contributions, which will hopefully further help shape the basis of a field of inquiry that grows as we see progress in our understanding of the senses and the development of new technologies in the context of food. © 2020 ACM.

关键词： human-food interaction technology senses multisensory

Grammatical Error Correction as GAN-like sequence labeling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Parnow, Kevin Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

In Grammatical Error Correction (GEC), sequence labeling models enjoy fast inference compared to sequence-to-sequence models;however, inference in sequence labeling GEC models is an iterative process, as sentences are passed to the model for multiple rounds of correction, which exposes the model to sentences with progressively fewer errors at each round. Traditional GEC models learn from sentences with fixed error rates. Coupling this with the iterative correction process causes a mismatch between training and inference that affects final performance. In order to address this mismatch, we propose a GAN-like sequence labeling model, which consists of a grammatical error detector as a discriminator and a grammatical error labeler with Gumbel-Softmax sampling as a generator. By sampling from real error distributions, our errors are more genuine compared to traditional synthesized GEC errors, thus alleviating the aforementioned mismatch and allowing for better training. Our results on several evaluation benchmarks demonstrate that our proposed approach is effective and improves the previous state-of-the-art baseline. Copyright © 2021, The Authors. All rights reserved.

关键词： Error correction

Socially Pertinent Robots in Gerontological Healthcare

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Alameda-Pineda, Xavier Addlesee, Angus García, Daniel Hernández Reinke, Chris Arias, Soraya Arrigoni, Federica Auternaud, Alex Blavette, Lauriane Beyan, Cigdem Camara, Luis Gomez Cohen, Ohad Conti, Alessandro Dacunha, Sébastien Dondrup, Christian Ellinson, Yoav Ferro, Francesco Gannot, Sharon Gras, Florian Gunson, Nancie Horaud, Radu D’Incà, Moreno Kimouche, Imad Lemaignan, Séverin Lemon, Oliver Liotard, Cyril Marchionni, Luca Moradi, Mordehay Pajdla, Tomas Pino, Maribel Polic, Michal Py, Matthieu Rado, Ariel Ren, Bin Ricci, Elisa Rigaud, Anne-Sophie Rota, Paolo Romeo, Marta Sebe, Nicu Sieińska, Weronika Tandeitnik, Pinchas Tonini, Francesco Turro, Nicolas Wintz, Timothée Yu, Yanchao RobotLearn Team Inria at Univ. Grenoble Alpes CNRS LJK 655 Avenue de l’Europe Montbonnot38334 France Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Jugoslávských partyzánů 1580/3 Dejvice 160 00 Czech Republic Acoustic Signal Processing Laboratory Bar-Ilan University Ramat-Gan5290002 Israel Department of Information and Computer Science University of Trento Via Sommarive 9 Trento38123 Italy Interaction Lab Mathematical and Computer Sciences Heriot-Watt University EdinburghEH14 4AS United Kingdom ERM Automatismes 561 allée Bellecour Carpentras84200 France PAL Robotics C/ Pujades 77-79 Barcelona08005 Spain Lusage Living Lab Assistance Publique - Hopitaux de Paris 54-56 Rue Pascal Paris75013 France

Despite the many recent achievements in developing and deploying social robotics, there are still many underexplored environments and applications for which systematic evaluation of such systems by end-users is necessary. While several robotic platforms have been used in gerontological healthcare, the question of whether or not an autonomous social interactive robot with multi-modal conversational capabilities will be useful and accepted in real-life facilities is yet to be answered. This paper is an attempt to partially answer this question, via two waves of experiments including patients and companions in a day-care gerontological facility in Paris with a full-sized humanoid robot endowed with social and conversational interaction capabilities. The software architecture, developed during the H2020 SPRING project, together with the experimental protocol, allowed us to evaluate the acceptability (AES) and usability (SUS) with more than 60 end-users. Overall, the users are receptive to this technology, especially when the robot’s perception and action skills are robust to environmental clutter and flexible to handle a plethora of different interactions. We also report and discuss some concerns and general comments of the users. © 2024, CC BY.

关键词： Microrobots

Advances in multi-turn dialogue comprehension: A survey

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Zhuosheng Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

Training machines to understand natural language and interact with humans is an elusive and essential task of artificial intelligence. A diversity of dialogue systems has been designed with the rapid development of deep learning techniques, especially the recent pre-trained language models (PrLMs). Among these studies, the fundamental yet challenging type of task is dialogue comprehension whose role is to teach the machines to read and comprehend the dialogue context before responding. In this paper, we review the previous methods from the technical perspective of dialogue modeling for the dialogue comprehension task. We summarize the characteristics and challenges of dialogue comprehension in contrast to plain-text reading comprehension. Then, we discuss three typical patterns of dialogue modeling. In addition, we categorize dialogue-related pretraining techniques which are employed to enhance PrLMs in dialogue scenarios. Finally, we highlight the technical advances in recent years and point out the lessons from the empirical analysis and the prospects towards a new frontier of researches. Copyright © 2021, The Authors. All rights reserved.

关键词： Speech processing

Defending pre-trained language models from adversarial word substitutions without performance sacrifice

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bao, Rongzhou Wang, Jiayi Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which is one of the most challenging textual adversarial attack methods. Existing defence approaches suffer from notable performance loss and complexities. Thus, this paper presents a compact and performance-preserved framework, Anomaly Detection with Frequency- Aware Randomization (ADFAR). In detail, we design an auxiliary anomaly detection classifier and adopt a multi-task learning procedure, by which PrLMs are able to distinguish adversarial input samples. Then, in order to defend adversarial word substitution, a frequency-aware randomization process is applied to those recognized adversarial input samples. Empirical results show that ADFAR significantly outperforms those newly proposed defense methods over various tasks with much higher inference speed. Remarkably, ADFAR does not impair the overall performance of PrLMs. © 2021, CC BY.

关键词： Anomaly detection