scispace - formally typeset

Topic

Natural language understanding

About: Natural language understanding is a(n) research topic. Over the lifetime, 2577 publication(s) have been published within this topic receiving 51905 citation(s).


Papers
More filters
Proceedings Article
20 Apr 2018
TL;DR: A benchmark of nine diverse NLU tasks, an auxiliary dataset for probing models for understanding of specific linguistic phenomena, and an online platform for evaluating and comparing models, which favors models that can represent linguistic knowledge in a way that facilitates sample-efficient learning and effective knowledge-transfer across tasks.
Abstract: Human ability to understand language is general, flexible, and robust. In contrast, most NLU models above the word level are designed for a specific task and struggle with out-of-domain data. If we aspire to develop models with understanding beyond the detection of superficial correspondences between inputs and outputs, then it is critical to develop a unified model that can execute a range of linguistic tasks across different domains. To facilitate research in this direction, we present the General Language Understanding Evaluation (GLUE, gluebenchmark.com): a benchmark of nine diverse NLU tasks, an auxiliary dataset for probing models for understanding of specific linguistic phenomena, and an online platform for evaluating and comparing models. For some benchmark tasks, training data is plentiful, but for others it is limited or does not match the genre of the test set. GLUE thus favors models that can represent linguistic knowledge in a way that facilitates sample-efficient learning and effective knowledge-transfer across tasks. While none of the datasets in GLUE were created from scratch for the benchmark, four of them feature privately-held test data, which is used to ensure that the benchmark is used fairly. We evaluate baselines that use ELMo (Peters et al., 2018), a powerful transfer learning technique, as well as state-of-the-art sentence representation models. The best models still achieve fairly low absolute scores. Analysis with our diagnostic dataset yields similarly weak performance over all phenomena tested, with some exceptions.

2,120 citations

Book
01 Jan 1987
TL;DR: The text features a new chapter on statistically-based methods using large corpora and an appendix on speech recognition and spoken language understanding and information on semantics that was covered in the first edition has been largely expanded in this edition.
Abstract: From the Publisher: In addition, this title offers coverage of two entirely new subject areas. First, the text features a new chapter on statistically-based methods using large corpora. Second, it includes an appendix on speech recognition and spoken language understanding. Also, the information on semantics that was covered in the first edition has been largely expanded in this edition to include an emphasis on compositional interpretation.

1,438 citations

Proceedings ArticleDOI
01 Nov 2018
Abstract: Human ability to understand language is general, flexible, and robust. In contrast, most NLU models above the word level are designed for a specific task and struggle with out-of-domain data. If we aspire to develop models with understanding beyond the detection of superficial correspondences between inputs and outputs, then it is critical to develop a unified model that can execute a range of linguistic tasks across different domains. To facilitate research in this direction, we present the General Language Understanding Evaluation (GLUE, gluebenchmark.com): a benchmark of nine diverse NLU tasks, an auxiliary dataset for probing models for understanding of specific linguistic phenomena, and an online platform for evaluating and comparing models. For some benchmark tasks, training data is plentiful, but for others it is limited or does not match the genre of the test set. GLUE thus favors models that can represent linguistic knowledge in a way that facilitates sample-efficient learning and effective knowledge-transfer across tasks. While none of the datasets in GLUE were created from scratch for the benchmark, four of them feature privately-held test data, which is used to ensure that the benchmark is used fairly. We evaluate baselines that use ELMo (Peters et al., 2018), a powerful transfer learning technique, as well as state-of-the-art sentence representation models. The best models still achieve fairly low absolute scores. Analysis with our diagnostic dataset yields similarly weak performance over all phenomena tested, with some exceptions.

1,213 citations

Proceedings Article
01 Aug 2013
TL;DR: A sembank of simple, whole-sentence semantic structures will spur new work in statistical natural language understanding and generation, like the Penn Treebank encouraged work on statistical parsing.
Abstract: We describe Abstract Meaning Representation (AMR), a semantic representation language in which we are writing down the meanings of thousands of English sentences. We hope that a sembank of simple, whole-sentence semantic structures will spur new work in statistical natural language understanding and generation, like the Penn Treebank encouraged work on statistical parsing. This paper gives an overview of AMR and tools associated with it.

977 citations

Journal ArticleDOI

947 citations


Network Information
Related Topics (5)
Natural language

31.1K papers, 806.8K citations

88% related
Recurrent neural network

29.2K papers, 890K citations

81% related
Ontology (information science)

57K papers, 869.1K citations

81% related
Graph (abstract data type)

69.9K papers, 1.2M citations

79% related
Deep learning

79.8K papers, 2.1M citations

79% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20223
2021309
2020357
2019273
2018161
2017103