Ioannis A. Kakadiaris George Paliouras Anastasia Krithara November 2018

Brussels, Belgium

Association for Computational Linguistics http://www.aclweb.org/anthology/W18-53 book BioASQ:2018 AnastasiosNentidis AnastasiaKrithara KonstantinosBougiatiotis GeorgiosPaliouras IoannisKakadiaris Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 1–10 http://www.aclweb.org/anthology/W18-5301 This paper presents the results of the sixth edition inproceedings nentidis-EtAl:2018:BioASQ FabianEckert MarianaNeves Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 11–21 http://www.aclweb.org/anthology/W18-5302 Question answering (QA) systems usually rely on advanced natural language processing components to precisely understand the questions and extract the answers. Semantic role labeling (SRL) is known to boost performance for QA, but its use for biomedical texts has not yet been fully studied. We analyzed the performance of three SRL tools (BioKIT, BIOSMILE and PathLSTM) on 1776 questions inproceedings eckert-neves:2018:BioASQ DiegoMolla Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 22–29 http://www.aclweb.org/anthology/W18-5303 This paper describes Macquarie University's contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document summarisation. In particular, this paper focuses on the experiments related to the deep learning and reinforcement learning approaches used in the submitted runs. The best run used a deep learning model under a regression-based framework. The deep learning architecture used features derived from the output of LSTM chains on word embeddings, plus features based on similarity with the query, and sentence position. The reinforcement learning approach was a proof-of-concept prototype that trained a global policy using REINFORCE. The global policy was implemented as a neural network that used tf.idf features encoding the candidate sentence, question, and context. inproceedings molla:2018:BioASQ GeorgeBrokos PolyviosLiosis RyanMcDonald DimitrisPappas IonAndroutsopoulos Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 30–39 http://www.aclweb.org/anthology/W18-5304 We present system details for AUEB’s submissions to the BioASQ 6 Document and Snippet Retrieval challenge (Task 6b Phase A). Our models use novel extensions to deep learning architectures that operate solely over the text of the query and candidate document/snippets. Overall, our systems scored at the top or near the top for all batches and metrics of the challenge, highlighting the effectiveness of deep learning for the task. inproceedings brokos-EtAl:2018:BioASQ AndrésRosso-Mateus Fabio A.González ManuelMontes-y-Gómez Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 40–46 http://www.aclweb.org/anthology/W18-5305 Biomedical Question Answering is concerned with the development of methods and systems that automatically find answers to natural language posed questions. In this work, we describe the system used in the BioASQ Challenge task 6b for document retrieval and snippet retrieval (with particular emphasis in this subtask). The proposed model makes use of semantic similarity patterns that are evaluated and measured by a convolutional neural network architecture. Subsequently, the snippet ranking performance is improved with a pseudo-relevance feedback approach in a later step. Based on the preliminary results, we reached the second position in snippet retrieval sub-task. inproceedings rossomateus-gonzlez-montesygmez:2018:BioASQ QiaoJin BhuwanDhingra WilliamCohen XinghuaLu Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 47–56 http://www.aclweb.org/anthology/W18-5306 There are millions of articles in PubMed database. To facilitate information retrieval, curators in the National Library of Medicine (NLM) assign a set of Medical Subject Headings (MeSH) to each article. MeSH is a hierarchically-organized vocabulary, containing about 28K different concepts, covering the fields from clinical medicine to information sciences. Several automatic MeSH indexing models have been developed to improve the time-consuming and financially expensive manual annotation, including the NLM official tool – Medical Text Indexer, and the winner of BioASQ Task5a challenge – DeepMeSH. However, these models are complex and not interpretable. We propose a novel end-to-end model, AttentionMeSH, which utilizes deep learning and attention mechanism to index MeSH terms to biomedical text. The attention mechanism enables the model to associate textual evidence with annotations, thus providing interpretability at the word level. The model also uses a novel masking mechanism to enhance accuracy and speed. In the final week of BioASQ Chanllenge Task6a, we ranked 2nd by average MiF using an on-construction model. After the contest, we achieve close to state-of-the-art MiF performance of ~0.684 using our final model. Human evaluations show AttentionMeSH also provides high level of interpretability, achieving 0.90$@$20 recall of all expert-labeled relevant words given an MeSH-article pair. inproceedings jin-EtAl:2018:BioASQ YutongLi NicholasGekakis QiuzeWu BoyueLi KhyathiChandu EricNyberg Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 57–65 http://www.aclweb.org/anthology/W18-5307 The growing number of biomedical publications is a challenge for human researchers, who invest considerable effort to search for relevant documents and pinpointed answers. Biomedical Question Answering can automatically generate answers for a user's topic or question, significantly reducing the effort required to locate the most relevant information in a large document corpus. Extractive summarization techniques, which concatenate the most relevant text units drawn from multiple documents, perform well on automatic evaluation metrics like ROUGE, but score poorly on human readability, due to the presence of redundant text and grammatical errors in the answer. inproceedings li-EtAl:2018:BioASQ AbhishekBhandwaldar WlodekZadrozny Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 66–71 http://www.aclweb.org/anthology/W18-5308 A question answering system is a system capable of answering natural language questions. The aim of the system is to tap into the vast unstructured information and aid the researchers by providing a natural language search interface. BioaASQ is a research competition that aims to progress the research in biomedical question answering systems. In this paper, we detail our submission to the BioASQ competition's Biomedical Semantic Question and Answering task. Our system uses extractive summarization techniques to generate answers and has scored highest ROUGE-2 and Rogue-SU4 in all test batch sets. inproceedings bhandwaldar-zadrozny:2018:BioASQ SanjayKamath BrigitteGrau YueMa Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 72–78 http://www.aclweb.org/anthology/W18-5309 BIOASQ Task B Phase B challenge focuses on extracting answers from snippets for a given question. The dataset provided by the organizers contains answers, but not all their variants. Henceforth a manual annotation was performed to extract all forms of correct answers. This article shows the impact of using all occurrences of correct answers for training on the evaluation scores which are improved significantly. inproceedings kamath-grau-ma:2018:BioASQ AshwinNaresh Kumar HariniKesavamoorthy MadhuraDas PramatiKalwad KhyathiChandu TerukoMitamura EricNyberg Proceedings of the 6th BioASQ Workshop A challenge on large-scale biomedical semantic indexing and question answering November 2018

Brussels, Belgium

Association for Computational Linguistics 79–89 http://www.aclweb.org/anthology/W18-5310 The ever-increasing magnitude of biomedical information sources makes it difficult and time-consuming for a human researcher to find the most relevant documents and pinpointed answers for a specific question or topic when using only a traditional search engine. Biomedical Question Answering systems automatically identify the most relevant documents and pinpointed answers, given an information need expressed as a natural language question. Generating a non-redundant, human-readable summary that satisfies the information need of a given biomedical question is focus of the Ideal Answer Generation task, part of the BioASQ challenge. This paper presents a system for ideal answer generation (using ontology-based retrieval and a neural learning-to-rank approach, combined with extractive and abstractive summarization techniques) which achieved the highest ROUGE score of 0.659 on the BioASQ 5b batch 2 test. inproceedings nareshkumar-EtAl:2018:BioASQ