来源:机器之心
作者:Kyubyong Park
本文长度为3071字,建议阅读6分钟
本文为你整理自然语言处理最新深度研究成果。
自然语言处理(NLP)是人工智能研究中极具挑战的一个分支。随着深度学习等技术的引入,NLP 领域正在以前所未有的速度向前发展。但对于初学者来说,这一领域目前有哪些研究和资源是必读的?最近我们整理了一份完整列表。
GitHub 项目链接:
https://github.com/Kyubyong/nlp_tasks
本人从事自然语言处理任务(NLP)的研究已经有很长时间了,有一天我想到,我需要为庞大的 NLP 领域做一个概览,我知道自己肯定不是想要一睹 NLP 任务的全貌的第一个人。
我曾竭尽所能的研究过尽可能多种类型的 NLP 任务,但由于个人知识的局限,我承认还远远没有穷尽整个领域。目前,该项目选取的参考文献都偏重最新的深度学习研究成果。我希望这些能为想要深入钻研一个 NLP 任务的人们提供一个开端。这个项目将持续更新,不过,我更希望与更多人合作。如果你有意愿的话,欢迎对这个项目作出贡献。
回指解析
See Coreference Resolution
(https://github.com/Kyubyong/nlp_tasks#coreference-resolution)
自动作文评分
论文:AutomaticText Scoring Using Neural Networks
(https://arxiv.org/abs/1606.04289)
论文:ANeural Approach to Automated Essay Scoring
(http://www.aclweb.org/old_anthology/D/D16/D16-1193.pdf)
竞赛:Kaggle:The Hewlett Foundation: Automated Essay Scoring
(https://www.kaggle.com/c/asap-aes)
项目:EnhancedAI Scoring Engine
(https://github.com/edx/ease)
自动语音识别
WIKI Speech recognition
(https://en.wikipedia.org/wiki/Speech_recognition)
论文:DeepSpeech 2: End-to-End Speech Recognition in English and Mandarin
(https://arxiv.org/abs/1512.02595)
论文:WaveNet:A Generative Model for Raw Audio
(https://arxiv.org/abs/1609.03499)
项目:A TensorFlow implementation of Baidu's DeepSpeech architecture
(https://github.com/mozilla/DeepSpeech)
项目:Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition using DeepMind's WaveNet
(https://github.com/buriburisuri/speech-to-text-wavenet)
竞赛:The 5thCHiME Speech Separation and Recognition Challenge
(http://spandh.dcs.shef.ac.uk/chime_challenge/)
资源:The 5thCHiME Speech Separation and Recognition Challenge
(http://spandh.dcs.shef.ac.uk/chime_challenge/download.html)
资源:CSTRVCTK Corpus
(http://homepages.inf.ed.ac.uk/jyamagis/page3/page58/page58.html)
资源:LibriSpeechASR corpus
(http://www.openslr.org/12/)
资源:Switchboard-1Telephone Speech Corpus
(https://catalog.ldc.upenn.edu/ldc97s62)
资源:TED-LIUMCorpus
(http://www-lium.univ-lemans.fr/en/content/ted-lium-corpus)
自动摘要
WIKI Automatic summarization
(https://en.wikipedia.org/wiki/Automatic_summarization)
书籍:AutomaticText Summarization
(https://www.amazon.com/Automatic-Text-Summarization-Juan-Manuel-Torres-Moreno/dp/1848216688/ref=sr_1_1?s=books&ie=UTF8&qid=1507782304&sr=1-1&keywords=Automatic+Text+Summarization)
论文:TextSummarization Using Neural Networks
(http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.823.8025&rep=rep1&type=pdf)
论文:Rankingwith Recursive Neural Networks and Its Application to Multi-DocumentSummarization
(https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/viewFile/9414/9520)
资源:TextAnalytics Conferences(TAC)
(https://tac.nist.gov/data/index.html)
资源:DocumentUnderstanding Conferences (DUC)
(http://www-nlpir.nist.gov/projects/duc/data.html)
指代消解
INFO Coreference Resolution
(https://nlp.stanford.edu/projects/coref.shtml)
论文:DeepReinforcement Learning for Mention-Ranking Coreference Models
(https://arxiv.org/abs/1609.08667)
论文:ImprovingCoreference Resolution by Learning Entity-Level Distributed Representations
(https://arxiv.org/abs/1606.01323)
竞赛:CoNLL2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes
(http://conll.cemantix.org/2012/task-description.html)
竞赛:CoNLL2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes
(http://conll.cemantix.org/2011/task-description.html)
实体链接
见“命名实体消歧”部分
语法错误纠正
论文:NeuralNetwork Translation Models for Grammatical Error Correction
(https://arxiv.org/abs/1606.00189)
竞赛:CoNLL-2013Shared Task: Grammatical Error Correction
(http://www.comp.nus.edu.sg/~nlp/conll13st.html)
竞赛:CoNLL-2014Shared Task: Grammatical Error Correction
(http://www.comp.nus.edu.sg/~nlp/conll14st.html)
资源:NUSNon-commercial research/trial corpus license
(http://www.comp.nus.edu.sg/~nlp/conll14st/nucle_license.pdf)
资源:Lang-8Learner Corpora
(http://cl.naist.jp/nldata/lang-8/)
资源:CornellMovie--Dialogs Corpus
(http://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html)
项目:DeepText Corrector
(https://github.com/atpaino/deep-text-corrector)
产品:deepgrammar
(http://deepgrammar.com/)
字素音素转换
论文:Grapheme-to-PhonemeModels for (Almost) Any Language
(https://pdfs.semanticscholar.org/b9c8/fef9b6f16b92c6859f6106524fdb053e9577.pdf)
论文:PolyglotNeural Language Models: A Case Study in Cross-Lingual Phonetic RepresentationLearning
(https://arxiv.org/pdf/1605.03832.pdf)
论文:MultitaskSequence-to-Sequence Models for Grapheme-to-Phoneme Conversion
(https://pdfs.semanticscholar.org/26d0/09959fa2b2e18cddb5783493738a1c1ede2f.pdf)
项目:Sequence-to-Sequence G2P toolkit
(https://github.com/cmusphinx/g2p-seq2seq)
资源:Multilingual Pronunciation Data
(https://drive.google.com/drive/folders/0B7R_gATfZJ2aWkpSWHpXUklWUmM)
语种猜测
见"语种辨别"部分
语种辨别
WIKI Language identification
(https://en.wikipedia.org/wiki/Language_identification)
论文:AUTOMATICLANGUAGE IDENTIFICATION USING DEEP NEURAL NETWORKS
(https://repositorio.uam.es/bitstream/handle/10486/666848/automatic_lopez-moreno_ICASSP_2014_ps.pdf?sequence=1)
竞赛: 2015Language Recognition Evaluation
(https://www.nist.gov/itl/iad/mig/2015-language-recognition-evaluation)
语言建模
WIKI Language model
(https://en.wikipedia.org/wiki/Language_model)
工具包: KenLMLanguage Model Toolkit
(http://kheafield.com/code/kenlm/)
论文:DistributedRepresentations of Words and Phrases and their Compositionality
(http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf)
论文:Character-AwareNeural Language Models
(https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/viewFile/12489/12017)
资源: PennTreebank
(https://github.com/townie/PTB-dataset-from-Tomas-Mikolov-s-webpage/tree/master/data)
语种识别
见“语种辨别”部分
同一词类
WIKI Lemmatisation
(https://en.wikipedia.org/wiki/Lemmatisation)
论文: JointLemmatization and Morphological Tagging with LEMMING
(http://www.cis.lmu.de/~muellets/pdf/emnlp_2015.pdf)
工具包:WordNet Lemmatizer
(http://www.nltk.org/api/nltk.stem.html#nltk.stem.wordnet.WordNetLemmatizer.lemmatize)
资源:Treebank-3
(https://catalog.ldc.upenn.edu/ldc99t42)
观唇辨意
WIKI Lip reading
(https://en.wikipedia.org/wiki/Lip_reading)
论文:LipReading Sentences in the Wild
(https://arxiv.org/abs/1611.05358)
论文:3DConvolutional Neural Networks for Cross Audio-Visual Matching Recognition
(https://arxiv.org/abs/1706.05739)
项目: LipReading - Cross Audio-Visual Recognition using 3D Convolutional Neural Networks
(https://github.com/astorfi/lip-reading-deeplearning)
资源: TheGRID audiovisual sentence corpus
(http://spandh.dcs.shef.ac.uk/gridcorpus/)
机器翻译
论文:NeuralMachine Translation by Jointly Learning to Align and Translate
(https://arxiv.org/abs/1409.0473)
论文:NeuralMachine Translation in Linear Time
(https://arxiv.org/abs/1610.10099)
论文:AttentionIs All You Need
(https://arxiv.org/abs/1706.03762)
竞赛: ACL2014 NINTH WORKSHOP ON STATISTICAL MACHINE TRANSLATION
(http://www.statmt.org/wmt14/translation-task.html#download)
竞赛: EMNLP2017 SECOND CONFERENCE ON MACHINE TRANSLATION (WMT17)
(http://www.statmt.org/wmt17/translation-task.html)
资源:OpenSubtitles2016
(http://opus.lingfil.uu.se/OpenSubtitles2016.php)
资源: WIT3:Web Inventory of Transcribed and Translated Talks
(https://wit3.fbk.eu/)
资源: TheQCRI Educational Domain (QED) Corpus
(http://alt.qcri.org/resources/qedcorpus/)
生成词法变化
WIKI Inflection
(https://en.wikipedia.org/wiki/Inflection)
论文:MorphologicalInflection Generation Using Character Sequence to Sequence Learning
(https://arxiv.org/abs/1512.06110)
竞赛:SIGMORPHON 2016 Shared Task: Morphological Reinflection
(http://ryancotterell.github.io/sigmorphon2016/)
资源 : sigmorphon2016
(https://github.com/ryancotterell/sigmorphon2016)
命名实体消歧
WIKI Entity linking
(https://en.wikipedia.org/wiki/Entity_linking)
论文:Robustand Collective Entity Disambiguation through Semantic Embeddings
(http://www.stefanzwicklbauer.info/pdf/Sigir_2016.pdf)
命名实体识别
WIKI Named-entity recognition
(https://en.wikipedia.org/wiki/Named-entity_recognition)
论文:NeuralArchitectures for Named Entity Recognition
(https://arxiv.org/abs/1603.01360)
项目: OSUTwitter NLP Tools
(https://github.com/aritter/twitter_nlp)
竞赛: NamedEntity Recognition in Twitter
(https://noisy-text.github.io/2016/ner-shared-task.html)
竞赛: CoNLL2002 Language-Independent Named Entity Recognition
(https://www.clips.uantwerpen.be/conll2002/ner/)
竞赛:Introduction to the CoNLL-2003 Shared Task: Language-Independent Named EntityRecognition
(http://aclweb.org/anthology/W03-0419)
资源:CoNLL-2002 NER corpus
(https://github.com/teropa/nlp/tree/master/resources/corpora/conll2002)
资源:CoNLL-2003 NER corpus
(https://github.com/synalp/NER/tree/master/corpus/CoNLL-2003)
资源: NUTNamed Entity Recognition in Twitter Shared task
(https://github.com/aritter/twitter_nlp/tree/master/data/annotated/wnut16)
释义检测
论文:DynamicPooling and Unfolding Recursive Autoencoders for Paraphrase Detection
(http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.650.7199&rep=rep1&type=pdf)
项目:Paralex: Paraphrase-Driven Learning for Open Question Answering
(http://knowitall.cs.washington.edu/paralex/)
资源:Microsoft Research Paraphrase Corpus
(https://www.microsoft.com/en-us/download/details.aspx?id=52398)
资源:Microsoft Research Video Description Corpus
(https://www.microsoft.com/en-us/download/details.aspx?id=52422&from=http%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fdownloads%2F38cf15fd-b8df-477e-a4e4-a4680caa75af%2F)
资源: PascalDataset
(http://nlp.cs.illinois.edu/HockenmaierGroup/pascal-sentences/index.html)
资源:Flicker Dataset
(http://nlp.cs.illinois.edu/HockenmaierGroup/8k-pictures.html)
资源: TheSICK data set
(http://clic.cimec.unitn.it/composes/sick.html)
资源: PPDB:The Paraphrase Database
(http://www.cis.upenn.edu/~ccb/ppdb/)
资源:WikiAnswers Paraphrase Corpus
(http://knowitall.cs.washington.edu/paralex/wikianswers-paraphrases-1.0.tar.gz)
语法分析
WIKI Parsing
(https://en.wikipedia.org/wiki/Parsing)
工具包: TheStanford Parser: A statistical parser
(https://nlp.stanford.edu/software/lex-parser.shtml)
工具包 : spaCyparser
(https://spacy.io/docs/usage/dependency-parse)
论文:A fastand accurate dependency parser using neural networks
(http://www.aclweb.org/anthology/D14-1082)
竞赛: CoNLL2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
(http://universaldependencies.org/conll17/)
竞赛: CoNLL2016 Shared Task: Multilingual Shallow Discourse Parsing
(http://www.cs.brandeis.edu/~clp/conll16st/)
竞赛: CoNLL2015 Shared Task: Shallow Discourse Parsing
(http://www.cs.brandeis.edu/~clp/conll15st/)
竞赛:SemEval-2016 Task 8: The meaning representations may be abstract, but this taskis concrete!
(http://alt.qcri.org/semeval2016/task8/)
词性标记
WIKI Part-of-speech tagging
(https://en.wikipedia.org/wiki/Part-of-speech_tagging)
论文:MultilingualPart-of-Speech Tagging with Bidirectional Long Short-Term Memory Models andAuxiliary Loss
(https://arxiv.org/pdf/1604.05529.pdf)
论文:UnsupervisedPart-Of-Speech Tagging with Anchor Hidden Markov Models
(https://transacl.org/ojs/index.php/tacl/article/viewFile/837/192)
资源:Treebank-3
(https://catalog.ldc.upenn.edu/ldc99t42)
工具包:nltk.tag package
(http://www.nltk.org/api/nltk.tag.html)
拼音-中文转换
论文:NeuralNetwork Language Model for Chinese Pinyin Input Method Engine
(http://aclweb.org/anthology/Y15-1052)
项目: NeuralChinese Transliterator
(https://github.com/Kyubyong/neural_chinese_transliterator)
问答系统
WIKI Question answering
(https://en.wikipedia.org/wiki/Question_answering)
论文:Ask MeAnything: Dynamic Memory Networks for Natural Language Processing
(http://www.thespermwhale.com/jaseweston/ram/papers/paper_21.pdf)
论文:DynamicMemory Networks for Visual and Textual Question Answering
(http://proceedings.mlr.press/v48/xiong16.pdf)
竞赛: TRECQuestion Answering Task
(http://trec.nist.gov/data/qamain.html)
竞赛:NTCIR-8: Advanced Cross-lingual Information Access (ACLIA
(http://aclia.lti.cs.cmu.edu/ntcir8/Home)
竞赛: CLEFQuestion Answering Track
(http://nlp.uned.es/clef-qa/)
竞赛:SemEval-2017 Task 3: Community Question Answering
(http://alt.qcri.org/semeval2017/task3/)
资源: MSMARCO: Microsoft MAchine Reading COmprehension Dataset
(http://www.msmarco.org/)
资源:Maluuba NewsQA
(https://github.com/Maluuba/newsqa)
资源: SQuAD:100,000+ Questions for Machine Comprehension of Text
(https://rajpurkar.github.io/SQuAD-explorer/)
资源:GraphQuestions: A Characteristic-rich Question Answering Dataset
(https://github.com/ysu1989/GraphQuestions)
资源: StoryCloze Test and ROCStories Corpora
(http://cs.rochester.edu/nlp/rocstories/)
资源:Microsoft Research WikiQA Corpus
(https://www.microsoft.com/en-us/download/details.aspx?id=52419&from=http%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fdownloads%2F4495da01-db8c-4041-a7f6-7984a4f6a905%2Fdefault.aspx)
资源:DeepMind Q&A Dataset
(http://cs.nyu.edu/~kcho/DMQA/)
资源: QASent
(http://cs.stanford.edu/people/mengqiu/data/qg-emnlp07-data.tgz)
关系提取
WIKI Relationship extraction
(https://en.wikipedia.org/wiki/Relationship_extraction)
论文:A deeplearning approach for relationship extraction from interaction context insocial manufacturing paradigm
(http://www.sciencedirect.com/science/article/pii/S0950705116001210)
语义角色标注
WIKI Semantic role labeling
(https://en.wikipedia.org/wiki/Semantic_role_labeling)
书籍:Semantic Role Labeling
(https://www.amazon.com/Semantic-Labeling-Synthesis-Lectures-Technologies/dp/1598298313/ref=sr_1_1?s=books&ie=UTF8&qid=1507776173&sr=1-1&keywords=Semantic+Role+Labeling)
论文:End-to-endLearning of Semantic Role Labeling Using Recurrent Neural Networks
(http://www.aclweb.org/anthology/P/P15/P15-1109.pdf)
论文:NeuralSemantic Role Labeling with Dependency Path Embeddi ngs
(https://arxiv.org/abs/1605.07515)
竞赛:CoNLL-2005 Shared Task: Semantic Role Labeling
(http://www.cs.upc.edu/~srlconll/st05/st05.html)
竞赛:CoNLL-2004 Shared Task: Semantic Role Labeling
(http://www.cs.upc.edu/~srlconll/st04/st04.html)
工具包:Illinois Semantic Role Labeler (SRL
(http://cogcomp.org/page/software_view/SRL)
资源:CoNLL-2005 Shared Task: Semantic Role Labeling
(http://www.cs.upc.edu/~srlconll/soft.html)
语句边界消歧
WIKI Sentence boundary disambiguation
(https://en.wikipedia.org/wiki/Sentence_boundary_disambiguation)
论文:AQuantitative and Qualitative Evaluation of Sentence Boundary Detection for theClinical Domain
(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5001746/)
工具包: NLTKTokenizers
(http://www.nltk.org/_modules/nltk/tokenize.html)
资源: TheBritish National Corpus
(http://www.natcorp.ox.ac.uk/)
资源:Switchboard-1 Telephone Speech Corpus
(https://catalog.ldc.upenn.edu/ldc97s62)
情绪分析
WIKI Sentiment analysis
(https://en.wikipedia.org/wiki/Sentiment_analysis)
INFO Awesome Sentiment Analysis
(https://github.com/xiamx/awesome-sentiment-analysis)
竞赛:Kaggle: UMICH SI650 - Sentiment Classification
(https://www.kaggle.com/c/si650winter11#description)
竞赛:SemEval-2017 Task 4: Sentiment Analysis in Twitter
(http://alt.qcri.org/semeval2017/task4/)
竞赛:SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogsand News
(http://alt.qcri.org/semeval2017/task5/)
项目:SenticNet
(http://sentic.net/about/)
资源:Multi-Domain Sentiment Dataset (version2.0
(http://www.cs.jhu.edu/~mdredze/datasets/sentiment/)
资源:Stanford Sentiment Treebank
(https://nlp.stanford.edu/sentiment/code.html)
资源:Twitter Sentiment Corpus
(http://www.sananalytics.com/lab/twitter-sentiment/)
资源:Twitter Sentiment Analysis Training Corpus
(http://thinknook.com/twitter-sentiment-analysis-training-corpus-dataset-2012-09-22/)
资源: AFINN:List of English words rated for valence
(http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6010)
源分离
WIKI Source separation
(https://en.wikipedia.org/wiki/Source_separation)
论文:FromBlind to Guided Audio Source Separation
(https://hal-univ-rennes1.archives-ouvertes.fr/hal-00922378/document)
论文:JointOptimization of Masks and Deep Recurrent Neural Networks for Monaural SourceSeparation
(https://arxiv.org/abs/1502.04149)
竞赛: SignalSeparation Evaluation Campaign (SiSEC)
(https://sisec.inria.fr/)
竞赛: CHiMESpeech Separation and Recognition Challenge
(http://spandh.dcs.shef.ac.uk/chime_challenge/)
说话人认证
见“说话人识别”部分
语音身份分离
WIKI Speaker diarisation
(https://en.wikipedia.org/wiki/Speaker_diarisation)
论文:DNN-basedspeaker clustering for speaker diarisation
(http://eprints.whiterose.ac.uk/109281/1/milner_is16.pdf)
论文:UnsupervisedMethods for Speaker Diarization: An Integrated and Iterative Approach
(http://groups.csail.mit.edu/sls/publications/2013/Shum_IEEE_Oct-2013.pdf)
论文:Audio-VisualSpeaker Diarization Based on Spatiotemporal Bayesian Fusion
(https://arxiv.org/pdf/1603.09725.pdf)
竞赛: RichTranscription Evaluation
(https://www.nist.gov/itl/iad/mig/rich-transcription-evaluation)
说话人识别
WIKI Speaker recognition
(https://en.wikipedia.org/wiki/Speaker_recognition)
论文:A NOVELSCHEME FOR SPEAKER RECOGNITION USING A PHONETICALLY-AWARE DEEP NEURAL NETWORK
(https://pdfs.semanticscholar.org/204a/ff8e21791c0a4113a3f75d0e6424a003c321.pdf)
论文:DEEPNEURAL NETWORKS FOR SMALL FOOTPRINT TEXT-DEPENDENT SPEAKER VERIFICATION
(https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/41939.pdf)
竞赛: NISTSpeaker Recognition Evaluation (SRE
(https://www.nist.gov/itl/iad/mig/speaker-recognition)
INFO Are there any suggestions for free databases for speakerrecognition
(https://www.researchgate.net/post/Are_there_any_suggestions_for_free_databases_for_speaker_recognition)
唇读
见“观唇辨意”部分
语音识别
见“自动语音识别”部分
语音分割
WIKI Speech_segmentation
(https://en.wikipedia.org/wiki/Speech_segmentation)
论文:WordSegmentation by 8-Month-Olds: When Speech Cues Count More Than Statistics
(http://www.utm.toronto.edu/infant-child-centre/sites/files/infant-child-centre/public/shared/elizabeth-johnson/Johnson_Jusczyk.pdf)
论文:UnsupervisedWord Segmentation and Lexicon Discovery Using Acoustic Word Embeddings
(https://arxiv.org/abs/1603.02845)
论文:UnsupervisedLexicon Discovery from Acoustic Inpu
(http://www.aclweb.org/old_anthology/Q/Q15/Q15-1028.pdf)
论文:Weaklysupervised spoken term discovery using cross-lingual side information
(http://www.research.ed.ac.uk/portal/files/29957958/1609.06530v1.pdf)
资源:CALLHOME Spanish Speech
(https://catalog.ldc.upenn.edu/ldc96s35)
语音合成
WIKI Speech synthesis
(https://en.wikipedia.org/wiki/Speech_synthesis)
论文:WaveNet:A Generative Model for Raw Audio
(https://arxiv.org/abs/1609.03499)
论文:Tacotron:Towards End-to-End Speech Synthesis
(https://arxiv.org/abs/1703.10135)
论文:DeepVoice 2: Multi-Speaker Neural Text-to-Speech
(https://arxiv.org/abs/1705.08947)
资源: TheWorld English Bible
(https://github.com/Kyubyong/tacotron)
资源: LJSpeech Dataset
(https://github.com/keithito/tacotron)
资源: LessacData
(http://www.cstr.ed.ac.uk/projects/blizzard/2011/lessac_blizzard2011/)
竞赛:Blizzard Challenge 2017
(https://synsig.org/index.php/Blizzard_Challenge_2017)
PRODUCT Lyrebird
(https://lyrebird.ai/)
项目: TheFestvox project
(http://www.festvox.org/index.html)
工具包:Merlin: The Neural Network (NN) based Speech Synthesis System
(https://github.com/CSTR-Edinburgh/merlin)
语音增强
WIKI Speech enhancement
(https://en.wikipedia.org/wiki/Speech_enhancement)
书籍: Speechenhancement: theory and practice
(https://www.amazon.com/Speech-Enhancement-Theory-Practice-Second/dp/1466504218/ref=sr_1_1?ie=UTF8&qid=1507874199&sr=8-1&keywords=Speech+enhancement%3A+theory+and+practice)
论文 AnExperimental Study on Speech Enhancement BasedonDeepNeuralNetwork
(http://staff.ustc.edu.cn/~jundu/Speech%20signal%20processing/publications/SPL2014_Xu.pdf)
论文: ARegression Approach to Speech Enhancement BasedonDeepNeuralNetworks
(https://www.researchgate.net/profile/Yong_Xu63/publication/272436458_A_Regression_Approach_to_Speech_Enhancement_Based_on_Deep_Neural_Networks/links/57fdfdda08aeaf819a5bdd97.pdf)
论文: SpeechEnhancement Based on Deep Denoising Autoencoder
(https://www.researchgate.net/profile/Yu_Tsao/publication/283600839_Speech_enhancement_based_on_deep_denoising_Auto-Encoder/links/577b486108ae213761c9c7f8/Speech-enhancement-based-on-deep-denoising-Auto-Encoder.pdf)
语音文本转换
见“自动语音识别”部分
口语的术语检测
见"语音分割"部分
词干提取
WIKI Stemming
(https://en.wikipedia.org/wiki/Stemming)
论文: ABACKPROPAGATION NEURAL NETWORK TO IMPROVE ARABIC STEMMING
(http://www.jatit.org/volumes/Vol82No3/7Vol82No3.pdf)
工具包: NLTKStemmers
(http://www.nltk.org/howto/stem.html)
术语提取
WIKI Terminology extraction
(https://en.wikipedia.org/wiki/Terminology_extraction)
论文: NeuralAttention Models for Sequence Classification: Analysis and Application to KeyTerm Extraction and Dialogue Act Detection
(https://arxiv.org/pdf/1604.00077.pdf)
文本简化
WIKI Text simplification
(https://en.wikipedia.org/wiki/Text_simplification)
论文:Aligning Sentences from Standard Wikipedia to Simple Wikipedia
(https://ssli.ee.washington.edu/~hannaneh/papers/simplification.pdf)
论文:Problems in Current Text Simplification Research: New Data Can Help
(https://pdfs.semanticscholar.org/2b8d/a013966c0c5e020ebc842d49d8ed166c8783.pdf)
资源:Newsela Data
(https://newsela.com/data/)
文本语音转换
见“语音合成”部分
文本蕴涵
WIKI Textual entailment
(https://en.wikipedia.org/wiki/Textual_entailment)
项目:Textual Entailment with TensorFlow
(https://github.com/Steven-Hewitt/Entailment-with-Tensorflow)
论文:Textual Entailment with Structured Attentions and Composition
(https://arxiv.org/pdf/1701.01126.pdf)
竞赛:SemEval-2014 Task 1: Evaluation of compositional distributional semantic modelson full sentences through semantic relatedness and textual entailment
(http://alt.qcri.org/semeval2014/task1/)
竞赛:SemEval-2013 Task 7: The Joint Student Response Analysis and 8th RecognizingTextual Entailment Challenge
(https://www.cs.york.ac.uk/semeval-2013/task7.html)
声音转换
论文:PHONETIC POSTERIORGRAMS FOR MANY-TO-ONE VOICE CONVERSION WITHOUT PARALLEL DATATRAINING
(http://www1.se.cuhk.edu.hk/~hccl/publications/pub/2016_paper_297.pdf)
项目: Animplementation of voice conversion system utilizing phonetic posteriorgrams
(https://github.com/sesenosannko/ppg_vc)
竞赛: VoiceConversion Challenge 2016
(http://www.vc-challenge.org/vcc2016/index.html)
竞赛: VoiceConversion Challenge 2018
(http://www.vc-challenge.org/)
资源:CMU_ARCTIC speech synthesis databases
(http://festvox.org/cmu_arctic/)
资源: TIMITAcoustic-Phonetic Continuous Speech Corpus
(https://catalog.ldc.upenn.edu/ldc93s1)
声音识别
见“说话人识别”部分
词嵌入
WIKI Word embedding
(https://en.wikipedia.org/wiki/Word_embedding)
工具包:Gensim: word2vec
(https://radimrehurek.com/gensim/models/word2vec.html)
工具包:fastText
(https://github.com/facebookresearch/fastText)
工具包: GloVe:Global Vectors for Word Representation
(https://nlp.stanford.edu/projects/glove/)
INFO Where to get a pretrained model
(https://github.com/3Top/word2vec-api)
项目:Pre-trained word vectors of 30+ languages
(https://github.com/Kyubyong/wordvectors)
项目:Polyglot: Distributed word representations for multilingual NLP
(https://sites.google.com/site/rmyeid/projects/polyglot)
词预测
INFO What is Word Prediction?
(http://www2.edc.org/ncip/library/wp/what_is.htm)
论文: Theprediction of character based on recurrent neural network language model
(http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7960065)
论文: AnEmbedded Deep Learning based Word Prediction
(https://arxiv.org/abs/1707.01662)
论文:Evaluating Word Prediction: Framing Keystroke Savings
(http://aclweb.org/anthology/P08-2066)
资源: AnEmbedded Deep Learning based Word Prediction
(https://github.com/Meinwerk/WordPrediction/master.zip)
项目: WordPrediction using Convolutional Neural Networks—can you do better than iPhone™Keyboard?
(https://github.com/Kyubyong/word_prediction)
词分割
WIKI Word segmentation
(https://en.wikipedia.org/wiki/Text_segmentation#Segmentation_problems)
论文: NeuralWord Segmentation Learning for Chinese
(https://arxiv.org/abs/1606.04300)
项目:Convolutional neural network for Chinese word segmentation
(https://github.com/chqiwang/convseg)
工具包:Stanford Word Segmenter
(https://nlp.stanford.edu/software/segmenter.html)
工具包: NLTKTokenizers
(http://www.nltk.org/_modules/nltk/tokenize.html)
词义消歧
资源:Word-sense disambiguation
(https://en.wikipedia.org/wiki/Word-sense_disambiguation)
论文:Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in MultipleLanguages without Manual Training Data
(http://www.aclweb.org/anthology/D17-1008)
资源:Train-O-Matic Data
(http://trainomatic.org/data/train-o-matic-data.zip)
资源:BabelNet
(http://babelnet.org/)
编辑:文婧