Tackling Biomedical Text Summarization: OAQA at BioASQ 5B

Chandu, Khyathi Raghavi; Naik, Aakanksha; Chandrasekar, Aditya; Yang, Zi; Gupta, Niloy; Nyberg, Eric

doi:10.18653/v1/w17-2307

Cited by 27 publications

(32 citation statements)

References 9 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. We achieve state of the art results in automatic evaluation measures for the ideal answer questions in Task 5b of the BioASQ dataset, yielding a 7% improvement over the previous state of the art system (Chandu et al, 2017).…”

Section: Introductionmentioning

confidence: 89%

“…The BioASQ challenge has seen large scale participation from research groups across the world. One of the most prominent among such works is from Chandu et al (2017) who experiment with different biomedical ontologies, agglomerative clustering, Maximum Marginal Relevance (MMR) and sentence compression. However, they only address the ideal answer generation with their model.…”

Section: Relevant Literaturementioning

confidence: 99%

“…We use the Maximum Marginal Relevance (MMR) algorithm (Forst et al, 2009) as the baseline for sentence selection. In contrast to the basic Jaccard similarity metric used in previous work (Chandu et al, 2017), we experimented with other similarity measures which consistently perform better than the Jaccard baseline. MMR ensures the selected set contains non-redundant yet complete information.…”

Section: Mmrmentioning

confidence: 99%

See 2 more Smart Citations

BioAMA: Towards an End to End BioMedical Question Answering System

Sharma¹,

Kulkarni²,

Pranavi³

et al. 2018

Proceedings of the BioNLP 2018 Workshop

Self Cite

View full text Add to dashboard Cite

In this paper, we present a novel Biomedical Question Answering system, BioAMA: "Biomedical Ask Me Anything" on task 5b of the annual BioASQ challenge (Balikas et al., 2015). We focus on a wide variety of question types including factoid, list based, summary and yes/no type questions that generate both exact and wellformed 'ideal' answers. For summarytype questions, we combine effective IRbased techniques for retrieval and diversification of relevant snippets for a question to create an end-to-end system which achieves a ROUGE-2 score of 0.72 and a ROUGE-SU4 score of 0.71 on ideal answer questions (7% improvement over the previous best model). Additionally, we propose a novel Natural Language Inference (NLI) based framework to answer the yes/no questions. To train the NLI model, we also devise a transfer-learning technique by cross-domain projection of word embeddings. Finally, we present a two-stage approach to address the factoid and list type questions by first generating a candidate set using NER taggers and ranking them using both supervised and unsupervised techniques.

show abstract

Section: Introductionmentioning

confidence: 89%

Section: Relevant Literaturementioning

confidence: 99%

Section: Mmrmentioning

confidence: 99%

See 1 more Smart Citation

BioAMA: Towards an End to End BioMedical Question Answering System

Sharma¹,

Kulkarni²,

Pranavi³

et al. 2018

Proceedings of the BioNLP 2018 Workshop

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Carnegie Mellon University team ("OAQA"), focused also on ideal answer generation, building upon previous versions of the "OAQA" system (Chandu et al, 2017). They experimented with ways to improve the generated answer by extracting the most relevant non-redundant sentences from multiple documents and then re-ordering and fusing them to make the resulting text more human-readable and coherent.…”

Section: Task 6bmentioning

confidence: 99%

Results of the sixth edition of the BioASQ Challenge

Nentidis¹,

Krithara²,

Bougiatiotis³

et al. 2018

Proceedings of the 6th BioASQ Workshop a Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering

View full text Add to dashboard Cite

This paper presents the results of the sixth edition of the BioASQ challenge. The BioASQ challenge aims at the promotion of systems and methodologies through the organization of a challenge on two tasks: semantic indexing and question answering. In total, 26 teams with more than 90 systems participated in this year's challenge. As in previous years, the best systems were able to outperform the strong baselines. This suggests that state-of-the-art systems are continuously improving, pushing the frontier of research.

show abstract

“…Our goal is to build an effective BQA system to generate coherent, query-oriented, non-redundant, human-readable summaries for biomedical questions. Our approach is based on an extractive BQA system (Chandu et al, 2017) which performed well on automatic metrics (ROUGE) in the 5th edition of the BioASQ challenge. However, owing to the extractive nature of this system, it suffers from problems in human readability and coherence.…”

Section: Introductionmentioning

confidence: 99%

Extraction Meets Abstraction: Ideal Answer Generation for Biomedical Questions

Li¹,

Gekakis²,

Wu³

et al. 2018

Proceedings of the 6th BioASQ Workshop a Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering

Self Cite

View full text Add to dashboard Cite

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. This work moves toward abstractive summarization, which attempts to distill and present the meaning of the original text in a more coherent way. We incorporate a sentence fusion approach, based on Integer Linear Programming, along with three novel approaches for sentence ordering, in an attempt to improve the human readability of ideal answers. Using an open framework for configuration space exploration (BOOM), we tested over 2000 unique system configurations in order to identify the best-performing combinations for the sixth edition of Phase B of the BioASQ challenge.

show abstract

Tackling Biomedical Text Summarization: OAQA at BioASQ 5B

Cited by 27 publications

References 9 publications

BioAMA: Towards an End to End BioMedical Question Answering System

BioAMA: Towards an End to End BioMedical Question Answering System

Results of the sixth edition of the BioASQ Challenge

Extraction Meets Abstraction: Ideal Answer Generation for Biomedical Questions

Contact Info

Product

Resources

About