Recent studies on AMR-to-text generation often formalize the task as a sequence-tosequence (seq2seq) learning problem by converting an Abstract Meaning Representation (AMR) graph into a word sequence. Graph structures are further modeled into the seq2seq framework in order to utilize the structural information in the AMR graphs. However, previous approaches only consider the relations between directly connected concepts while ignoring the rich structure in AMR graphs. In this paper we eliminate such a strong limitation and propose a novel structure-aware selfattention approach to better modeling the relations between indirectly connected concepts in the state-of-the-art seq2seq model, i.e., the Transformer. In particular, a few different methods are explored to learn structural representations between two concepts. Experimental results on English AMR benchmark datasets show that our approach significantly outperforms the state of the art with 29.66 and 31.82 BLEU scores on LDC2015E86 and LDC2017T10, respectively. To the best of our knowledge, these are the best results achieved so far by supervised models on the benchmarks.

This article describes our work on the BioCreative-V chemical–disease relation (CDR) extraction task, which employed a maximum entropy (ME) model and a convolutional neural network model for relation extraction at inter- and intra-sentence level, respectively. In our work, relation extraction between entity concepts in documents was simplified to relation extraction between entity mentions. We first constructed pairs of chemical and disease mentions as relation instances for training and testing stages, then we trained and applied the ME model and the convolutional neural network model for inter- and intra-sentence level, respectively. Finally, we merged the classification results from mention level to document level to acquire the final relations between chemical and disease concepts. The evaluation on the BioCreative-V CDR corpus shows the effectiveness of our proposed approach. Database URL: http://www.biocreative.org/resources/corpora/biocreative-v-cdr-corpus/

Understanding the relations between chemicals and diseases is crucial in various biomedical tasks such as new drug discoveries and new therapy developments. While manually mining these relations from the biomedical literature is costly and time-consuming, such a procedure is often difficult to keep up-to-date. To address these issues, the BioCreative-V community proposed a challenging task of automatic extraction of chemical-induced disease (CID) relations in order to benefit biocuration. This article describes our work on the CID relation extraction task on the BioCreative-V tasks. We built a machine learning based system that utilized simple yet effective linguistic features to extract relations with maximum entropy models. In addition to leveraging various features, the hypernym relations between entity concepts derived from the Medical Subject Headings (MeSH)-controlled vocabulary were also employed during both training and testing stages to obtain more accurate classification models and better extraction performance, respectively. We demoted relation extraction between entities in documents to relation extraction between entity mentions. In our system, pairs of chemical and disease mentions at both intra- and inter-sentence levels were first constructed as relation instances for training and testing, then two classification models at both levels were trained from the training examples and applied to the testing examples. Finally, we merged the classification results from mention level to document level to acquire final relations between chemicals and diseases. Our system achieved promising F-scores of 60.4% on the development dataset and 58.3% on the test dataset using gold-standard entity annotations, respectively.Database URL: https://github.com/JHnlp/BC5CIDTask

This paper proposes a new approach to dynamically determine the tree span for tree kernel-based semantic relation extraction. It exploits constituent dependencies to keep the nodes and their head children along the path connecting the two entities, while removing the noisy information from the syntactic parse tree, eventually leading to a dynamic syntactic parse tree. This paper also explores entity features and their combined features in a unified parse and semantic tree, which integrates both structured syntactic parse information and entity-related semantic information. Evaluation on the ACE RDC 2004 corpus shows that our dynamic syntactic parse tree outperforms all previous tree spans, and the composite kernel combining this tree kernel with a linear state-of-the-art feature-based kernel, achieves the so far best performance.

There is a surge of research interest in protein-protein interaction (PPI) extraction from biomedical literature. While most of the state-of-the-art PPI extraction systems focus on dependency-based structured information, the rich structured information inherent in constituent parse trees has not been extensively explored for PPI extraction. In this paper, we propose a novel approach to tree kernel-based PPI extraction, where the tree representation generated from a constituent syntactic parser is further refined using the shortest dependency path between two proteins derived from a dependency parser. Specifically, all the constituent tree nodes associated with the nodes on the shortest dependency path are kept intact, while other nodes are removed safely to make the constituent tree concise and precise for PPI extraction. Compared with previously used constituent tree setups, our dependency-motivated constituent tree setup achieves the best results across five commonly used PPI corpora. Moreover, our tree kernel-based method outperforms other single kernel-based ones and performs comparably with some multiple kernel ones on the most commonly tested AIMed corpus.