Neural Semantic Encoders. Munkhdalai, T & Yu, H. In European Chapter of the Association for Computational Linguistics 2017 (EACL), volume 1, pages 397–407, April, 2017. ![Neural Semantic Encoders [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through readp̌hantom\\, compose and write operations. NSE can also access multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.
@inproceedings{munkhdalai_neural_2017,
title = {Neural {Semantic} {Encoders}},
volume = {1},
url = {https://arxiv.org/pdf/1607.04315v2.pdf},
abstract = {We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read\vphantom{\{}\}, compose and write operations. NSE can also access multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.},
booktitle = {European {Chapter} of the {Association} for {Computational} {Linguistics} 2017 ({EACL})},
author = {Munkhdalai, T and Yu, Hong},
month = apr,
year = {2017},
pmid = {29081578 PMCID: PMC5657452},
pages = {397--407},
}
Downloads: 0
{"_id":"8j3bkXxmLcxMwrdjR","bibbaseid":"munkhdalai-yu-neuralsemanticencoders-2017","author_short":["Munkhdalai, T","Yu, H."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Neural Semantic Encoders","volume":"1","url":"https://arxiv.org/pdf/1607.04315v2.pdf","abstract":"We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through readp̌hantom\\\\, compose and write operations. NSE can also access multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.","booktitle":"European Chapter of the Association for Computational Linguistics 2017 (EACL)","author":[{"propositions":[],"lastnames":["Munkhdalai"],"firstnames":["T"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]}],"month":"April","year":"2017","pmid":"29081578 PMCID: PMC5657452","pages":"397–407","bibtex":"@inproceedings{munkhdalai_neural_2017,\n\ttitle = {Neural {Semantic} {Encoders}},\n\tvolume = {1},\n\turl = {https://arxiv.org/pdf/1607.04315v2.pdf},\n\tabstract = {We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read\\vphantom{\\{}\\}, compose and write operations. NSE can also access multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.},\n\tbooktitle = {European {Chapter} of the {Association} for {Computational} {Linguistics} 2017 ({EACL})},\n\tauthor = {Munkhdalai, T and Yu, Hong},\n\tmonth = apr,\n\tyear = {2017},\n\tpmid = {29081578 PMCID: PMC5657452},\n\tpages = {397--407},\n}\n\n","author_short":["Munkhdalai, T","Yu, H."],"key":"munkhdalai_neural_2017","id":"munkhdalai_neural_2017","bibbaseid":"munkhdalai-yu-neuralsemanticencoders-2017","role":"author","urls":{"Paper":"https://arxiv.org/pdf/1607.04315v2.pdf"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"http://fenway.cs.uml.edu/papers/pubs-all.bib","dataSources":["TqaA9miSB65nRfS5H"],"keywords":[],"search_terms":["neural","semantic","encoders","munkhdalai","yu"],"title":"Neural Semantic Encoders","year":2017}