Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X,Y) from bornIn(X,Y). Most previous methods infer simple one-hop relational synonyms like this, or use as evidence a multi-hop relational path treated as an atomic feature, like bornIn(X,Z) → containedIn(Z,Y). This paper presents an approach that reasons about conjunctions of multi-hop relations non-atomically, composing the implications of a path using a recurrent neural network (RNN) that takes as inputs vector embeddings of the binary relation in the path. Not only does this allow us to generalize to paths unseen at training time, but also, with a single high-capacity RNN, to predict new relation types not seen when the compositional model was trained (zero-shot learning). We assemble a new dataset of over 52M relational triples, and show that our method improves over a traditional classifier by 11%, and a method leveraging pre-trained embeddings by 7%.

Universal schema builds a knowledge base (KB) of entities and relations by jointly embedding all relation types from input KBs as well as textual patterns expressing relations from raw text. In most previous applications of universal schema, each textual pattern is represented as a single embedding, preventing generalization to unseen patterns. Recent work employs a neural network to capture patterns' compositional semantics, providing generalization to all possible input text. In response, this paper introduces significant further improvements to the coverage and flexibility of universal schema relation extraction: predictions for entities unseen in training and multilingual transfer learning to domains with no annotation. We evaluate our model through extensive experiments on the English and Spanish TAC KBP benchmark, outperforming the top system from TAC 2013 slot-filling using no handwritten patterns or additional annotation. We also consider a multilingual setting in which English training data entities overlap with the seed KB, but Spanish text does not. Despite having no annotation for Spanish data, we train an accurate predictor, with additional improvements obtained by tying word embeddings across languages. Furthermore, we find that multilingual training improves English relation extraction accuracy. Our approach is thus suited to broad-coverage automated knowledge base construction in a variety of languages and domains.

The behavior of deep neural networks (DNNs) is hard to understand. This makes it necessary to explore post hoc explanation methods. We conduct the first comprehensive evaluation of explanation methods for NLP. To this end, we design two novel evaluation paradigms that cover two important classes of NLP problems: small context and large context problems. Both paradigms require no manual annotation and are therefore broadly applicable. We also introduce LIMSSE, an explanation method inspired by LIME that is designed for NLP. We show empirically that LIMSSE, LRP and DeepLIFT are the most effective explanation methods and recommend them for explaining DNNs in NLP.

In this work, we propose a new model for aspect-based sentiment analysis. In contrast to previous approaches, we jointly model the detection of aspects and the classification of their polarity in an end-to-end trainable neural network. We conduct experiments with different neural architectures and word representations on the recent GermEval 2017 dataset. We were able to show considerable performance gains by using the joint modeling approach in all settings compared to pipeline approaches. The combination of a convolutional neural network and fasttext embeddings outperformed the best submission of the shared task in 2017, establishing a new state of the art.

We address relation classification in the context of slot filling, the task of finding and evaluating fillers like "Steve Jobs" for the slot X in "X founded Apple". We propose a convolutional neural network which splits the input sentence into three parts according to the relation arguments and compare it to state-ofthe-art and traditional approaches of relation classification. Finally, we combine different methods and show that the combination is better than individual approaches. We also analyze the effect of genre differences on performance.

We survey recent approaches to noise reduction in distant supervision learning for relation extraction. We group them according to the principles they are based on: at-least-one constraints, topic-based models, or pattern correlations. Besides describing them, we illustrate the fundamental differences and attempt to give an outlook to potentially fruitful further research. In addition, we identify related work in sentiment analysis which could profit from approaches to noise reduction.

No abstract

The devastating diseases of human cancer are mimicked in basic and translational cancer research by a steadily increasing number of tumor models, a situation requiring a platform with standardized reports to share model data. Models in Translational Oncology (MiTO) database was developed as a unique Web platform aiming for a comprehensive overview of preclinical models covering genetically engineered organisms, models of transplantation, chemical/physical induction, or spontaneous development, reviewed here. MiTO serves data entry for metastasis profiles and interventions. Moreover, cell lines and animal lines including tool strains can be recorded. Hyperlinks for connection with other databases and file uploads as supplementary information are supported. Several communication tools are offered to facilitate exchange of information. Notably, intellectual property can be protected prior to publication by inventordefined accessibility of any given model. Data recall is via a highly configurable keyword search. Genome editing is expected to result in changes of the spectrum of model organisms, a reason to open MiTO for species-independent data. Registered users may deposit own model fact sheets (FS). MiTO experts check them for plausibility. Independently, manually curated FS are provided to principle investigators for revision and publication. Importantly, noneditable versions of reviewed FS can be cited in peer-reviewed journals.