scispace - formally typeset

Topic

Question answering

About: Question answering is a(n) research topic. Over the lifetime, 14024 publication(s) have been published within this topic receiving 375482 citation(s). The topic is also known as: QA & question-answering.
Papers
More filters

Proceedings ArticleDOI
11 Oct 2018-
Abstract: We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a; Radford et al., 2018), BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5 (7.7 point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

24,672 citations


Proceedings ArticleDOI
Matthew E. Peters1, Mark Neumann1, Mohit Iyyer2, Matt Gardner1  +3 moreInstitutions (4)
15 Feb 2018-
Abstract: We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus. We show that these representations can be easily added to existing models and significantly improve the state of the art across six challenging NLP problems, including question answering, textual entailment and sentiment analysis. We also present an analysis showing that exposing the deep internals of the pre-trained network is crucial, allowing downstream models to mix different types of semi-supervision signals.

6,141 citations


Posted Content
TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
Abstract: We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

4,099 citations


Book
John F. Sowa1Institutions (1)
01 Jul 1983-
TL;DR: This book will not become a unity of the way for you to get amazing benefits at all, but, it will serve something that will let you get the best time and moment to spend for reading the book.
Abstract: It sounds good when knowing the conceptual structures information processing in mind and machine in this website. This is one of the books that many people looking for. In the past, many people ask about this book as their favourite book to read and collect. And now, we present hat you need quickly. It seems to be so happy to offer you this famous book. It will not become a unity of the way for you to get amazing benefits at all. But, it will serve something that will let you get the best time and moment to spend for reading the book.

3,186 citations


Proceedings ArticleDOI
16 Jun 2016-
Abstract: We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency trees. We build a strong logistic regression model, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). However, human performance (86.8%) is much higher, indicating that the dataset presents a good challenge problem for future research. The dataset is freely available at this https URL

3,103 citations


Network Information
Related Topics (5)
Natural language

31.1K papers, 806.8K citations

89% related
Unsupervised learning

22.7K papers, 1M citations

86% related
Recurrent neural network

29.2K papers, 890K citations

86% related
Ontology (information science)

57K papers, 869.1K citations

86% related
Web page

50.3K papers, 975.1K citations

84% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202216
20211,466
20201,517
20191,475
20181,113
2017858