Prior work has commonly defined argument retrieval from heterogeneous document collections as a sentence-level classification task. Consequently, argument retrieval suffers both from low recall and from sentence segmentation errors making it difficult for humans and machines to consume the arguments. In this work, we argue that the task should be performed on a more fine-grained level of sequence labeling. For this, we define the task as Argument Unit Recognition and Classification (AURC). We present a dataset of arguments from heterogeneous sources annotated as spans of tokens within a sentence, as well as with a corresponding stance. We show that and how such difficult argument annotations can be effectively collected through crowdsourcing with high inter-annotator agreement. The new benchmark, AURC-8, contains up to 15% more arguments per topic as compared to annotations on the sentence level. We identify a number of methods targeted at AURC sequence labeling, achieving close to human performance on known domains. Further analysis also reveals that, contrary to previous approaches, our methods are more robust against sentence segmentation errors. We publicly release our code and the AURC-8 dataset.1
In our project ReMLAV, funded within the DFG Priority Program RATIO (http://www.spp-ratio.de/), we focus on relational and fine-grained argument mining. In this article, we first introduce the problems we address and then summarize related work. The main part of the article describes our research on argument mining, both coarse-grained and fine-grained methods, and on same-side stance classification, a relational approach to the problem of stance classification. We conclude with an outlook.
Abstract-Control of robot locomotion profits from the use of pre-planned trajectories. This paper presents a way to generalize globally optimal and dynamically consistent trajectories for cyclic bipedal walking. A small task-space consisting of stride-length and step time is mapped to spline parameters which fully define the optimal joint space motion. The paper presents the impact of different machine learning algorithms for velocity and torque optimal trajectories with respect to optimality and feasibility. To demonstrate the usefulness of the trajectories, a control approach is presented that allows general walking including transitions between points in the task-space. I. IntroductionAs many aspects of robotics technology improve, robots cover more tasks such as manipulating objects in complex environments. Often designed with humans in mind, these environments feature challenges like stairs or uneven terrain. It is therefore desirable that robots have matching abilities when it comes to locomotion in these environments. This motivates the use of legged locomotion for our robotic platforms.However, legged locomotion comes with rather complex kinematics and dynamics which still provide plenty of challenges for planning and control. All approaches create a mapping between the task of moving the robot somewhere and a suitable trajectory which deals with the full complexity of the robot. Models of varying complexity [1] are used to create this mapping. Creating a trajectory using a model that contains all degrees of freedom and takes into account the systems limitations is however not feasible when the solution should be created on-line, taking into account the task and the environment.The approach developed in this work, first presented in [2], provides this mapping from the task-space to the trajectory. For this it uses a combined approach of trajectory planning using non-linear optimization and generalization of these results by current machine learning methods. The optimization allows exploitation of the dynamics of the system by using strong models. This paper contains an analysis of the performance of a set of machine learning algorithms in providing this mapping for a successful execution of the task.
No abstract
The performance of a Part-of-speech (POS) tagger is highly dependent on the domain of the processed text, and for many domains there is no or only very little training data available. This work addresses the problem of POS tagging noisy user-generated text using a neural network. We propose an architecture that trains an out-of-domain model on a large newswire corpus, and transfers those weights by using them as a prior for a model trained on the target domain (a data-set of German Tweets) for which there is very little annotations available. The neural network has two standard bidirectional LSTMs at its core. However, we find it crucial to also encode a set of task-specific features, and to obtain reliable (source-domain and target-domain) word representations. Experiments with different regularization techniques such as early stopping, dropout and fine-tuning the domain adaptation prior weights are conducted. Our best model uses external weights from the out-of-domain model, as well as feature embeddings, pretrained word and sub-word embeddings and achieves a tagging accuracy of slightly over 90%, improving on the previous state of the art for this task.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.