Keyphrase generation is the task of generating phrases (keyphrases) that summarize the main topics of a given document. The generated keyphrases can be either present or absent from the text of the given document. While the extraction of present keyphrases has received much attention in the past, only recently a stronger focus has been placed on the generation of absent keyphrases. However, generating absent keyphrases is very challenging; even the best methods show only a modest degree of success. In this paper, we propose an approach, called keyphrase dropout (or KPDrop), to improve absent keyphrase generation. We randomly drop present keyphrases from the document and turn them into artificial absent keyphrases during training. We test our approach extensively and show that it consistently improves the absent performance of strong baselines in keyphrase generation.
Inter-robot transfer of training data is a little explored topic in learning and vision-based robot control. Thus, we propose a transfer method from a robot with a lower Degree-of-Freedom (DoF) action to one with a higher DoF utilizing an omnidirectional camera. The virtual rotation of the robot camera enables data augmentation in this transfer learning process. In this study, a vision-based control policy for a 6-DoF robot was trained using a dataset collected by a differential wheeled ground robot with only three DoFs. Towards application of robotic manipulations, we also demonstrate a control system of a 6-DoF arm robot using multiple policies with different fields of view to enable object reaching tasks.
Unsupervised domain adaptation (UDA), which is an important topic in transfer learning, aims to predict unlabeled data from target domain with access to labeled data from the source domain. In this work, we propose a novel framework called SIDA (Surrogate Mutual Information Maximization Domain Adaptation) with strong theoretical guarantees. To be specific, SIDA implements adaptation by maximizing mutual information (MI) between features. In the framework, a surrogate joint distribution models the underlying joint distribution of the unlabeled target domain. Our theoretical analysis validates SIDA by bounding the expected risk on target domain with MI and surrogate distribution bias. Experiments show that our approach is comparable with state-of-the-art unsupervised adaptation methods on standard UDA tasks.
We propose MultiDoc2Dial, a new task and dataset on modeling goal-oriented dialogues grounded in multiple documents. Most previous works treat document-grounded dialogue modeling as a machine reading comprehension task based on a single given document or passage. In this work, we aim to address more realistic scenarios where a goal-oriented information-seeking conversation involves multiple topics, and hence is grounded on different documents. To facilitate such a task, we introduce a new dataset that contains dialogues grounded in multiple documents from four different domains. We also explore modeling the dialogue-based and document-based context in the dataset. We present strong baseline approaches and various experimental results, aiming to support further research efforts on such a task.
Machine learning has seen a vast increase of interest in recent years, along with an abundance of learning resources. While conventional lectures provide students with important information and knowledge, we also believe that additional project-based learning components can motivate students to engage in topics more deeply. In addition to incorporating project-based learning in our courses, we aim to develop project-based learning components aligned with real-world tasks, including experimental design and execution, report writing, oral presentation, and peer-reviewing. This paper describes the organization of our project-based machine learning courses with a particular emphasis on the class project components and shares our resources with instructors who would like to include similar elements in their courses.
Explainability of deep neural networks is one of the most challenging and interesting problems in the field. In this study, we investigate the topic focusing on the interpretability of deep learning-based registration methods. In particular, with the appropriate model architecture and using a simple linear projection, we decompose the encoding space, generating a new basis, and we empirically show that this basis captures various decomposed anatomically aware geometrical transformations. We perform experiments using two different datasets focusing on lungs and hippocampus MRI. We show that such an approach can decompose the highly convoluted latent spaces of registration pipelines in an orthogonal space with several interesting properties. We hope that this work could shed some light on a better understanding of deep learning-based registration methods.
In this paper, we propose to combine pretrained language models with the modular dialogue paradigm for open-domain dialogue modeling. Our method, semantic-enhanced finetuning, instantiates conversation understanding, planning, and response generation as a language model finetuning task. At inference, we disentangle semantic and token variations by specifying sampling methods and constraints for each module separately. For training and evaluation, we present X-Weibo, a Chinese multi-turn open-domain dialogue dataset with automatic annotation for emotions, DAs, and topical words. Experiments show that semantic-enhanced finetuning outperforms strong baselines on non-semantic and semantic metrics, improves the human-evaluated relevance, coherence, and informativeness, and exhibits considerable controllability over semantic variables.
Compiling commonsense knowledge is traditionally an AI topic approached by manual labor. Recent advances in web data processing have enabled automated approaches. In this demonstration we will showcase three systems for automated commonsense knowledge base construction, highlighting each time one aspect of specific interest to the data management community. (i) We use Quasimodo to illustrate knowledge extraction systems engineering, (ii) Dice to illustrate the role that schema constraints play in cleaning fuzzy commonsense knowledge, and (iii) Ascent to illustrate the relevance of conceptual modelling. The demos are available online at https://quasimodo.r2.enst.fr, https://dice.mpi-inf.mpg.de and ascent.mpi-inf.mpg.de.
The DiCOVA challenge aims at accelerating research in diagnosing COVID-19 using acoustics (DiCOVA), a topic at the intersection of speech and audio processing, respiratory health diagnosis, and machine learning. This challenge is an open call for researchers to analyze a dataset of sound recordings collected from COVID-19 infected and non-COVID-19 individuals for a two-class classification. These recordings were collected via crowdsourcing from multiple countries, through a website application. The challenge features two tracks, one focuses on using cough sounds, and the other on using a collection of breath, sustained vowel phonation, and number counting speech recordings. In this paper, we introduce the challenge and provide a detailed description of the dataset, task, and present a baseline system for the task.
In this article, we bring together theories of multimodal communication and computational methods to study how primary school science diagrams combine multiple expressive resources. We position our work within the field of digital humanities, and show how annotations informed by multimodality research, which target expressive resources and discourse structure, allow imposing structure on the output of computational methods. We illustrate our approach by analysing two multimodal diagram corpora: the first corpus is intended to support research on automatic diagram processing, whereas the second is oriented towards studying diagrams as a mode of communication. Our results show that multimodally-informed annotations can bring out structural patterns in the diagrams, which also extend across diagrams that deal with different topics.