[转]NLP Tasks

Natural Language Processing Tasks and Selected References

I've been working on several natural language processing tasks for a long time. One day, I felt like drawing a map of the NLP field where I earn a living. I'm sure I'm not the only person who wants to see at a glance which tasks are in NLP.

I did my best to cover as many as possible tasks in NLP, but admittedly this is far from exhaustive purely due to my lack of knowledge. And selected references are biased towards recent deep learning accomplishments. I expect these serve as a starting point when you're about to dig into the task. I'll keep updating this repo myself, but what I really hope is you collaborate on this work. Don't hesitate to send me a pull request!

Oct. 13, 2017.

by Kyubyong

Reviewed and updated by YJ Choe on Oct. 18, 2017.

Anaphora Resolution

Automated Essay Scoring

Automatic Speech Recognition

Automatic Summarisation

Coreference Resolution

Entity Linking

Grammatical Error Correction

Grapheme To Phoneme Conversion

Humor and Sarcasm Detection

Language Grounding

Language Guessing

Language Identification

Language Modeling

Language Recognition

Lemmatisation

Lip-reading

Machine Translation

Morphological Inflection Generation

Named Entity Disambiguation

Named Entity Recognition

Paraphrase Detection

Paraphrase Generation

Parsing

Part-of-speech Tagging

Pinyin-To-Chinese Conversion

Question Answering

Relationship Extraction

Semantic Role Labeling

Sentence Boundary Disambiguation

Sentiment Analysis

Singing Voice Synthesis

Social Science Applications

Source Separation

Speaker Authentication

Speaker Diarisation

Speaker Recognition

Speech Reading

Speech Recognition

Speech Segmentation

Speech Synthesis

Speech Enhancement

Speech-To-Text

Spoken Term Detection

Stemming

Term Extraction

Text Similarity

Text Simplification

Text-To-Speech

Textual Entailment

Transliteration

Voice Conversion

Voice Recognition

Word Embeddings

Word Prediction

Word Segmentation

Word Sense Disambiguation

— Language Models, Segmentation
— Morphological Analysis, POS Tagging and Sequence Labeling
— Syntactic and Semantic Parsing
— Lexical and Compositional Semantics
— Discourse and Coreference
— Dialogue and Interactive Systems
— Narrative Understanding and Commonsense Reasoning
— Spoken Language Processing
— Text Mining
— Sentiment Analysis and Opinion Mining
— Information Retrieval, Question Answering
— Information Extraction
— Summarization
— Natural Language Generation
— Machine Translation
— Multilinguality and Cross-linguality
— Linguistic Theories and Resources
— Computational Psycholinguistics
— Multimodal and Grounded Language Processing
— Machine Learning for NLP
— Web, Social Media and Computational Social Science
— Ethics and Fairness in NLP
— Other NLP Applications

CSTR语音克隆英语多说话人语料库工具包 概述 这个CSTR VCTK语料库包含了109个以不同口音为母语的英语使用者的语音数据。 每位演讲者要朗读大约400句句子,其中大部分是从报纸上挑选出来的,再加上彩虹段落和一段旨在识别演讲者口音的启事段落。 这些报纸文本是在先驱时报集团(Herald & Times Group)的许可下,从格拉斯哥的《先驱报》(The Herald)上摘取的。 每位演讲者阅读一组不同的报纸句子,每组句子都是通过贪婪算法选择的,该算法旨在最大限度地扩大上下文和语音覆盖范围。 彩虹段落和启发性段落对所有演讲者都是一样的。 彩虹之旅可以在国际英语方言档案(http://web.ku.edu/~idea/readings/rainbow.htm)中找到。 引出段落与用于语音重音存档(http://accent.gmu.edu)的段落相同。 语音口音档案的细节可以在http://www.ualberta.ca/~aacl2009/PDFs/WeinbergerKunath2009AACL.pdf上找到 所有的语音数据都是使用相同的录音设置记录的:一个全向头戴式麦克风(DPA 4035),采样频率为96kHz, 24位,在爱丁堡大学的半暗室中。 所有录音均换为16位,基于STPK下采样至48 kHz,并手动端点。 该语料库的录制是为了构建基于hmm的文本-语音合成系统,特别是用于使用多个发言者训练的平均语音模型和发言者自适应技术构建基于发言者自适应的语音合成系统。 复制 该语料库是在开放数据共享署名许可(ODC-By) v1.0下授权的。 http://opendatacommons.org/licenses/by/1.0/ http://opendatacommons.org/licenses/by/summary/ 下载 http://dx.doi.org/10.7488/ds/1994 确认 CSTR VCTK语料库由: Christophe Veaux(爱丁堡大学) Junichi Yamagishi(爱丁堡大学) 克里斯汀•麦克唐纳 导致这些结果的研究部分得到了EPSRC EP/I031022/1 (NST)和EP/J002526/1 (CAF)的资助,来自RSE-NSFC的资助(61111130120)和JST CREST (uDialogue)的资助。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值