The ability to conduct logical reasoning is a fundamental aspect of intelligent human behavior, and thus an important problem along the way to human-level artificial intelligence. Traditionally, logic-based symbolic methods from the field of knowledge representation and reasoning have been used to equip agents with capabilities that resemble human logical reasoning qualities. More recently, however, there has been an increasing interest in using machine learning rather than logic-based symbolic formalisms to tackle these tasks. In this paper, we employ state-of-the-art methods for training deep neural networks to devise a novel model that is able to learn how to effectively perform logical reasoning in the form of basic ontology reasoning. This is an important and at the same time very natural logical reasoning task, which is why the presented approach is applicable to a plethora of important real-world problems. We present the outcomes of several experiments, which show that our model is able to learn to perform highly accurate ontology reasoning on very large, diverse, and challenging benchmarks. Furthermore, it turned out that the suggested approach suffers much less from different obstacles that prohibit logic-based symbolic reasoning, and, at the same time, is surprisingly plausible from a biological point of view.

No abstract

This paper introduces a new initialization method for knowledge graph (KG) embedding that can leverage ontological information in knowledge graph completion problems, such as link classification and link prediction. Although the initialization method is general and applicable to different KG embedding approaches in the literature, such as TransE or RESCAL, this paper experiments with deep learning and specifically with the neural tensor network (NTN) model. The experimental results show that the proposed method can improve link classification for a given relation by up to 15%. In a second contribution, the proposed method allows for addressing a problem not studied in the literature and introduced here as "KG completion with fresh entities". This is the use of KG embeddings for KG completion when one or several of the entities in a triple (head, relation, tail) has not been observed in the training phase.

In this paper, we introduce the new task of controllable text edition, in which we take as input a long text, a question, and a target answer, and the output is a minimally modified text, so that it fits the target answer. This task is very important in many situations, such as changing some conditions, consequences, or properties in a legal document, or changing some key information of an event in a news text. This is very challenging, as it is hard to obtain a parallel corpus for training, and we need to first find all text positions that should be changed and then decide how to change them. We constructed the new dataset WIKIBIOCTE for this task based on the existing dataset WIKIBIO (originally created for table-to-text generation). We use WIKIBIOCTE for training, and manually labeled a test set for testing. We also propose novel evaluation metrics and a novel method for solving the new task. Experimental results on the test set show that our proposed method is a good fit for this novel NLP task.

The goal of open information extraction (OIE) is to extract facts from natural language text, and to represent them as structured triples of the form subject, predicate, object . For example, given the sentence »Beethoven composed the Ode to Joy.«, we are expected to extract the triple Beethoven, composed, Ode to Joy . In this work, we systematically compare different neural network architectures and training approaches, and improve the performance of the currently best models on the OIE16 benchmark (Stanovsky and Dagan, 2016) by 0.421 F 1 score and 0.420 AUC-PR, respectively, in our experiments (i.e., by more than 200% in both cases). Furthermore, we show that appropriate problem and loss formulations often affect the performance more than the network architecture.