NCU-IISR: Using a Pre-trained Language Model and Logistic Regression Model for BioASQ Task 8b Phase B
Explore this paper's citation graph
Summary
A pre-trained biomedical language model, BioBERT, is employed to generate “exact” answers for the questions, and a logistic regression model with the sentence embedding to construct the top-n sentences/snippets as a prediction for “ideal” answers.
- Type
- article
- Published
- 2020-01-01
- Cited by
- 2
- References
- 20
- OpenAlex
- https://openalex.org/W3096122783
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:225074032
Keywords
Logistic regression, Task (project management), Computer science, Artificial intelligence, Phase (matter)
References
- An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition
- Distributed Representations of Words and Phrases and their Compositionality
- ROUGE: A Package for Automatic Evaluation of Summaries
- GloVe: Global Vectors for Word Representation
- Deep learning with word embeddings improves biomedical named entity recognition
- Deep Contextualized Word Representations
- Know What You Don’t Know: Unanswerable Questions for SQuAD
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- PubMedQA: A Dataset for Biomedical Research Question Answering
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- Pre-trained Language Model for Biomedical Question Answering
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Classification Betters Regression in Query-based Multi-document Summarisation Techniques for Question Answering: Macquarie University at BioASQ7b
- Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Cited by
- NCU-IISR/AS-GIS: Results of Various Pre-trained Biomedical Language Models and Linear Regression Model in BioASQ Task 9b Phase B
- Query-Focused Extractive Summarisation for Finding Ideal Answers to Biomedical and COVID-19 Questions
- Query-Focused Extractive Summarisation for Finding Ideal Answers to Biomedical and COVID-19 Questions
Related papers
No related papers recorded.