自然語言處理領域重要論文&資源全索引

劉曉坤發表於2017-10-14
自然語言處理(NLP)是人工智慧研究中極具挑戰的一個分支。隨著深度學習等技術的引入,NLP 領域正在以前所未有的速度向前發展。但對於初學者來說,這一領域目前有哪些研究和資源是必讀的?最近,Kyubyong Park 為我們整理了一份完整列表。

 

GitHub 專案連結:https://github.com/Kyubyong/nlp_tasks

 

本人從事自然語言處理任務(NLP)的研究已經有很長時間了,有一天我想到,我需要為龐大的 NLP 領域做一個概覽,我知道自己肯定不是想要一睹 NLP 任務的全貌的第一個人。

 

我曾竭盡所能的研究過儘可能多種型別的 NLP 任務,但由於個人知識的侷限,我承認還遠遠沒有窮盡整個領域。目前,該專案選取的參考文獻都偏重最新的深度學習研究成果。我希望這些能為想要深入鑽研一個 NLP 任務的人們提供一個開端。這個專案將持續更新,不過,我更希望與更多人合作。如果你有意願的話,歡迎對這個專案作出貢獻。

 

回指解析

 

  • See Coreference Resolution (https://github.com/Kyubyong/nlp_tasks#coreference-resolution)

 

自動作文評分

 

  • 論文:AutomaticText Scoring Using Neural Networks (https://arxiv.org/abs/1606.04289)
  • 論文:ANeural Approach to Automated Essay Scoring (http://www.aclweb.org/old_anthology/D/D16/D16-1193.pdf)
  • 競賽:Kaggle:The Hewlett Foundation: Automated Essay Scoring (https://www.kaggle.com/c/asap-aes)
  • 專案:EnhancedAI Scoring Engine(https://github.com/edx/ease)

 

自動語音識別

 

  • WIKI Speech recognition(https://en.wikipedia.org/wiki/Speech_recognition)
  • 論文:DeepSpeech 2: End-to-End Speech Recognition in English and Mandarin (https://arxiv.org/abs/1512.02595)
  • 論文:WaveNet:A Generative Model for Raw Audio (https://arxiv.org/abs/1609.03499)
  • 專案:A TensorFlow implementation of Baidu's DeepSpeech architecture (https://github.com/mozilla/DeepSpeech)
  • 專案:Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition using DeepMind's WaveNet(https://github.com/buriburisuri/speech-to-text-wavenet)
  • 競賽:The 5thCHiME Speech Separation and Recognition Challenge (http://spandh.dcs.shef.ac.uk/chime_challenge/)
  • 資源:The 5thCHiME Speech Separation and Recognition Challenge (http://spandh.dcs.shef.ac.uk/chime_challenge/download.html)
  • 資源:CSTRVCTK Corpus (http://homepages.inf.ed.ac.uk/jyamagis/page3/page58/page58.html)
  • 資源:LibriSpeechASR corpus (http://www.openslr.org/12/)
  • 資源:Switchboard-1Telephone Speech Corpus (https://catalog.ldc.upenn.edu/ldc97s62)
  • 資源:TED-LIUMCorpus (http://www-lium.univ-lemans.fr/en/content/ted-lium-corpus)

 

自動摘要

 

  • WIKI Automatic summarization (https://en.wikipedia.org/wiki/Automatic_summarization)
  • 書籍: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)
  • 論文:TextSummarization Using Neural Networks (http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.823.8025&rep=rep1&type=pdf)
  • 論文:Rankingwith Recursive Neural Networks and Its Application to Multi-DocumentSummarization (https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/viewFile/9414/9520)
  • 資源:TextAnalytics Conferences(TAC)(https://tac.nist.gov/data/index.html)
  • 資源: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)
  • 論文:DeepReinforcement Learning for Mention-Ranking Coreference Models (https://arxiv.org/abs/1609.08667)
  • 論文:ImprovingCoreference Resolution by Learning Entity-Level Distributed Representations(https://arxiv.org/abs/1606.01323)
  • 競賽:CoNLL2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes(http://conll.cemantix.org/2012/task-description.html)
  • 競賽:CoNLL2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes (http://conll.cemantix.org/2011/task-description.html)

 

實體連結

 

  • 見「命名實體消歧」部分

 

語法錯誤糾正

 

  • 論文:NeuralNetwork Translation Models for Grammatical Error Correction (https://arxiv.org/abs/1606.00189)
  • 競賽:CoNLL-2013Shared Task: Grammatical Error Correction (http://www.comp.nus.edu.sg/~nlp/conll13st.html)
  • 競賽:CoNLL-2014Shared Task: Grammatical Error Correction (http://www.comp.nus.edu.sg/~nlp/conll14st.html)
  • 資源:NUSNon-commercial research/trial corpus license (http://www.comp.nus.edu.sg/~nlp/conll14st/nucle_license.pdf)
  • 資源:Lang-8Learner Corpora(http://cl.naist.jp/nldata/lang-8/)
  • 資源:CornellMovie--Dialogs Corpus (http://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html)
  • 專案:DeepText Corrector(https://github.com/atpaino/deep-text-corrector)
  • 產品:deepgrammar(http://deepgrammar.com/)

 

字素音素轉換

 

  • 論文:Grapheme-to-PhonemeModels for (Almost) Any Language (https://pdfs.semanticscholar.org/b9c8/fef9b6f16b92c6859f6106524fdb053e9577.pdf)
  • 論文:PolyglotNeural Language Models: A Case Study in Cross-Lingual Phonetic RepresentationLearning (https://arxiv.org/pdf/1605.03832.pdf)
  • 論文:MultitaskSequence-to-Sequence Models for Grapheme-to-Phoneme Conversion (https://pdfs.semanticscholar.org/26d0/09959fa2b2e18cddb5783493738a1c1ede2f.pdf)
  • 專案:Sequence-to-Sequence G2P toolkit (https://github.com/cmusphinx/g2p-seq2seq)
  • 資源:Multilingual Pronunciation Data (https://drive.google.com/drive/folders/0B7R_gATfZJ2aWkpSWHpXUklWUmM)

 

語種猜測

 

  • 見「語種辨別」部分

 

語種辨別

 

  • WIKI Language identification (https://en.wikipedia.org/wiki/Language_identification)
  • 論文:AUTOMATICLANGUAGE IDENTIFICATION USING DEEP NEURAL NETWORKS (https://repositorio.uam.es/bitstream/handle/10486/666848/automatic_lopez-moreno_ICASSP_2014_ps.pdf?sequence=1)
  • 競賽: 2015Language Recognition Evaluation (https://www.nist.gov/itl/iad/mig/2015-language-recognition-evaluation)

 

語言建模

 

  • WIKI Language model (https://en.wikipedia.org/wiki/Language_model)
  • 工具包: KenLMLanguage Model Toolkit (http://kheafield.com/code/kenlm/)
  • 論文:DistributedRepresentations of Words and Phrases and their Compositionality (http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf)
  • 論文:Character-AwareNeural Language Models (https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/viewFile/12489/12017)
  • 資源: PennTreebank (https://github.com/townie/PTB-dataset-from-Tomas-Mikolov-s-webpage/tree/master/data)

 

語種識別

 

  • 見「語種辨別」部分

 

同一詞類

 

  • WIKI Lemmatisation (https://en.wikipedia.org/wiki/Lemmatisation)
  • 論文: 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)
  • 資源:Treebank-3 (https://catalog.ldc.upenn.edu/ldc99t42)

 

觀唇辨意

 

  • WIKI Lip reading (https://en.wikipedia.org/wiki/Lip_reading)
  • 論文:LipReading Sentences in the Wild (https://arxiv.org/abs/1611.05358)
  • 論文:3DConvolutional Neural Networks for Cross Audio-Visual Matching Recognition (https://arxiv.org/abs/1706.05739)
  • 專案: LipReading - Cross Audio-Visual Recognition using 3D Convolutional Neural Networks(https://github.com/astorfi/lip-reading-deeplearning)
  • 資源: TheGRID audiovisual sentence corpus (http://spandh.dcs.shef.ac.uk/gridcorpus/)

 

機器翻譯

 

  • 論文:NeuralMachine Translation by Jointly Learning to Align and Translate (https://arxiv.org/abs/1409.0473)
  • 論文:NeuralMachine Translation in Linear Time (https://arxiv.org/abs/1610.10099)
  • 論文:AttentionIs All You Need (https://arxiv.org/abs/1706.03762)
  • 競賽: ACL2014 NINTH WORKSHOP ON STATISTICAL MACHINE TRANSLATION (http://www.statmt.org/wmt14/translation-task.html#download)
  • 競賽: EMNLP2017 SECOND CONFERENCE ON MACHINE TRANSLATION (WMT17)(http://www.statmt.org/wmt17/translation-task.html)
  • 資源:OpenSubtitles2016 (http://opus.lingfil.uu.se/OpenSubtitles2016.php)
  • 資源: WIT3:Web Inventory of Transcribed and Translated Talks (https://wit3.fbk.eu/)
  • 資源: TheQCRI Educational Domain (QED) Corpus (http://alt.qcri.org/resources/qedcorpus/)

 

生成詞法變化

 

  • WIKI Inflection (https://en.wikipedia.org/wiki/Inflection)
  • 論文:MorphologicalInflection Generation Using Character Sequence to Sequence Learning (https://arxiv.org/abs/1512.06110)
  • 競賽:SIGMORPHON 2016 Shared Task: Morphological Reinflection (http://ryancotterell.github.io/sigmorphon2016/)
  • 資源:sigmorphon2016 (https://github.com/ryancotterell/sigmorphon2016)

 

命名實體消歧

 

  • WIKI Entity linking (https://en.wikipedia.org/wiki/Entity_linking)
  • 論文:Robustand Collective Entity Disambiguation through Semantic Embeddings (http://www.stefanzwicklbauer.info/pdf/Sigir_2016.pdf)

 

命名實體識別

 

  • WIKI Named-entity recognition (https://en.wikipedia.org/wiki/Named-entity_recognition)
  • 論文:NeuralArchitectures for Named Entity Recognition (https://arxiv.org/abs/1603.01360)
  • 專案: OSUTwitter NLP Tools (https://github.com/aritter/twitter_nlp)
  • 競賽: NamedEntity Recognition in Twitter (https://noisy-text.github.io/2016/ner-shared-task.html)
  • 競賽: CoNLL2002 Language-Independent Named Entity Recognition (https://www.clips.uantwerpen.be/conll2002/ner/)
  • 競賽:Introduction to the CoNLL-2003 Shared Task: Language-Independent Named EntityRecognition (http://aclweb.org/anthology/W03-0419)
  • 資源:CoNLL-2002 NER corpus (https://github.com/teropa/nlp/tree/master/resources/corpora/conll2002)
  • 資源:CoNLL-2003 NER corpus (https://github.com/synalp/NER/tree/master/corpus/CoNLL-2003)
  • 資源: NUTNamed Entity Recognition in Twitter Shared task (https://github.com/aritter/twitter_nlp/tree/master/data/annotated/wnut16)

 

釋義檢測

 

  • 論文: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)
  • 專案:Paralex: Paraphrase-Driven Learning for Open Question Answering (http://knowitall.cs.washington.edu/paralex/)
  • 資源:Microsoft Research Paraphrase Corpus (https://www.microsoft.com/en-us/download/details.aspx?id=52398)
  • 資源: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)
  • 資源: PascalDataset (http://nlp.cs.illinois.edu/HockenmaierGroup/pascal-sentences/index.html)
  • 資源:Flicker Dataset (http://nlp.cs.illinois.edu/HockenmaierGroup/8k-pictures.html)
  • 資源: TheSICK data set (http://clic.cimec.unitn.it/composes/sick.html)
  • 資源: PPDB:The Paraphrase Database (http://www.cis.upenn.edu/~ccb/ppdb/)
  • 資源:WikiAnswers Paraphrase Corpus (http://knowitall.cs.washington.edu/paralex/wikianswers-paraphrases-1.0.tar.gz)

 

語法分析

 

  • 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)
  • 論文:A fastand accurate dependency parser using neural networks (http://www.aclweb.org/anthology/D14-1082)
  • 競賽: CoNLL2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (http://universaldependencies.org/conll17/)
  • 競賽: CoNLL2016 Shared Task: Multilingual Shallow Discourse Parsing (http://www.cs.brandeis.edu/~clp/conll16st/)
  • 競賽: CoNLL2015 Shared Task: Shallow Discourse Parsing (http://www.cs.brandeis.edu/~clp/conll15st/)
  • 競賽:SemEval-2016 Task 8: The meaning representations may be abstract, but this taskis concrete! (http://alt.qcri.org/semeval2016/task8/)

 

詞性標記

 

  • WIKI Part-of-speech tagging (https://en.wikipedia.org/wiki/Part-of-speech_tagging)
  • 論文:MultilingualPart-of-Speech Tagging with Bidirectional Long Short-Term Memory Models andAuxiliary Loss (https://arxiv.org/pdf/1604.05529.pdf)
  • 論文:UnsupervisedPart-Of-Speech Tagging with Anchor Hidden Markov Models (https://transacl.org/ojs/index.php/tacl/article/viewFile/837/192)
  • 資源:Treebank-3 (https://catalog.ldc.upenn.edu/ldc99t42)
  • 工具包:nltk.tag package (http://www.nltk.org/api/nltk.tag.html)

 

拼音-中文轉換

 

  • 論文:NeuralNetwork Language Model for Chinese Pinyin Input Method Engine (http://aclweb.org/anthology/Y15-1052)
  • 專案: NeuralChinese Transliterator (https://github.com/Kyubyong/neural_chinese_transliterator)

 

問答系統

 

  • WIKI Question answering (https://en.wikipedia.org/wiki/Question_answering)
  • 論文:Ask MeAnything: Dynamic Memory Networks for Natural Language Processing (http://www.thespermwhale.com/jaseweston/ram/papers/paper_21.pdf)
  • 論文:DynamicMemory Networks for Visual and Textual Question Answering (http://proceedings.mlr.press/v48/xiong16.pdf)
  • 競賽: TRECQuestion Answering Task (http://trec.nist.gov/data/qamain.html)
  • 競賽:NTCIR-8: Advanced Cross-lingual Information Access (ACLIA)(http://aclia.lti.cs.cmu.edu/ntcir8/Home)
  • 競賽: CLEFQuestion Answering Track (http://nlp.uned.es/clef-qa/)
  • 競賽:SemEval-2017 Task 3: Community Question Answering (http://alt.qcri.org/semeval2017/task3/)
  • 資源: MSMARCO: Microsoft MAchine Reading COmprehension Dataset (http://www.msmarco.org/)
  • 資源:Maluuba NewsQA (https://github.com/Maluuba/newsqa)
  • 資源: SQuAD:100,000+ Questions for Machine Comprehension of Text (https://rajpurkar.github.io/SQuAD-explorer/)
  • 資源:GraphQuestions: A Characteristic-rich Question Answering Dataset (https://github.com/ysu1989/GraphQuestions)
  • 資源: StoryCloze Test and ROCStories Corpora (http://cs.rochester.edu/nlp/rocstories/)
  • 資源: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)
  • 資源:DeepMind Q&A Dataset (http://cs.nyu.edu/~kcho/DMQA/)
  • 資源: QASent(http://cs.stanford.edu/people/mengqiu/data/qg-emnlp07-data.tgz)

 

關係提取

 

  • WIKI Relationship extraction (https://en.wikipedia.org/wiki/Relationship_extraction)
  • 論文:A deeplearning approach for relationship extraction from interaction context insocial manufacturing paradigm (http://www.sciencedirect.com/science/article/pii/S0950705116001210)

 

語義角色標註

 

  • WIKI Semantic role labeling (https://en.wikipedia.org/wiki/Semantic_role_labeling)
  • 書籍: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)
  • 論文:End-to-endLearning of Semantic Role Labeling Using Recurrent Neural Networks (http://www.aclweb.org/anthology/P/P15/P15-1109.pdf)
  • 論文:NeuralSemantic Role Labeling with Dependency Path Embeddi ngs (https://arxiv.org/abs/1605.07515)
  • 競賽:CoNLL-2005 Shared Task: Semantic Role Labeling (http://www.cs.upc.edu/~srlconll/st05/st05.html)
  • 競賽: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)
  • 資源:CoNLL-2005 Shared Task: Semantic Role Labeling (http://www.cs.upc.edu/~srlconll/soft.html)

 

語句邊界消歧

 

  • WIKI Sentence boundary disambiguation (https://en.wikipedia.org/wiki/Sentence_boundary_disambiguation)
  • 論文: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)
  • 資源: TheBritish National Corpus (http://www.natcorp.ox.ac.uk/)
  • 資源:Switchboard-1 Telephone Speech Corpus (https://catalog.ldc.upenn.edu/ldc97s62)

 

情緒分析

 

  • WIKI Sentiment analysis (https://en.wikipedia.org/wiki/Sentiment_analysis)
  • INFO Awesome Sentiment Analysis (https://github.com/xiamx/awesome-sentiment-analysis)
  • 競賽:Kaggle: UMICH SI650 - Sentiment Classification (https://www.kaggle.com/c/si650winter11#description)
  • 競賽:SemEval-2017 Task 4: Sentiment Analysis in Twitter (http://alt.qcri.org/semeval2017/task4/)
  • 競賽:SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogsand News (http://alt.qcri.org/semeval2017/task5/)
  • 專案:SenticNet (http://sentic.net/about/)
  • 資源:Multi-Domain Sentiment Dataset (version2.0)(http://www.cs.jhu.edu/~mdredze/datasets/sentiment/)
  • 資源:Stanford Sentiment Treebank (https://nlp.stanford.edu/sentiment/code.html)
  • 資源:Twitter Sentiment Corpus (http://www.sananalytics.com/lab/twitter-sentiment/)
  • 資源:Twitter Sentiment Analysis Training Corpus (http://thinknook.com/twitter-sentiment-analysis-training-corpus-dataset-2012-09-22/)
  • 資源: AFINN:List of English words rated for valence (http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6010)

 

源分離

 

  • WIKI Source separation (https://en.wikipedia.org/wiki/Source_separation)
  • 論文:FromBlind to Guided Audio Source Separation (https://hal-univ-rennes1.archives-ouvertes.fr/hal-00922378/document)
  • 論文:JointOptimization of Masks and Deep Recurrent Neural Networks for Monaural SourceSeparation (https://arxiv.org/abs/1502.04149)
  • 競賽: SignalSeparation Evaluation Campaign (SiSEC)(https://sisec.inria.fr/)
  • 競賽: CHiMESpeech Separation and Recognition Challenge (http://spandh.dcs.shef.ac.uk/chime_challenge/)

 

說話人認證

 

  • 見「說話人識別」部分

 

語音身份分離

 

  • WIKI Speaker diarisation (https://en.wikipedia.org/wiki/Speaker_diarisation)
  • 論文:DNN-basedspeaker clustering for speaker diarisation (http://eprints.whiterose.ac.uk/109281/1/milner_is16.pdf)
  • 論文:UnsupervisedMethods for Speaker Diarization: An Integrated and Iterative Approach (http://groups.csail.mit.edu/sls/publications/2013/Shum_IEEE_Oct-2013.pdf)
  • 論文:Audio-VisualSpeaker Diarization Based on Spatiotemporal Bayesian Fusion (https://arxiv.org/pdf/1603.09725.pdf)
  • 競賽: RichTranscription Evaluation (https://www.nist.gov/itl/iad/mig/rich-transcription-evaluation)

 

說話人識別

 

  • WIKI Speaker recognition (https://en.wikipedia.org/wiki/Speaker_recognition)
  • 論文:A NOVELSCHEME FOR SPEAKER RECOGNITION USING A PHONETICALLY-AWARE DEEP NEURAL NETWORK (https://pdfs.semanticscholar.org/204a/ff8e21791c0a4113a3f75d0e6424a003c321.pdf)
  • 論文:DEEPNEURAL NETWORKS FOR SMALL FOOTPRINT TEXT-DEPENDENT SPEAKER VERIFICATION (https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/41939.pdf)
  • 競賽: 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)

 

唇讀

 

  • 見「觀唇辨意」部分

 

語音識別

 

  • 見「自動語音識別」部分

 

語音分割

 

  • WIKI Speech_segmentation (https://en.wikipedia.org/wiki/Speech_segmentation)
  • 論文: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)
  • 論文:UnsupervisedWord Segmentation and Lexicon Discovery Using Acoustic Word Embeddings (https://arxiv.org/abs/1603.02845)
  • 論文:UnsupervisedLexicon Discovery from Acoustic Inpu (http://www.aclweb.org/old_anthology/Q/Q15/Q15-1028.pdf)
  • 論文:Weaklysupervised spoken term discovery using cross-lingual side information (http://www.research.ed.ac.uk/portal/files/29957958/1609.06530v1.pdf)
  • 資源:CALLHOME Spanish Speech (https://catalog.ldc.upenn.edu/ldc96s35)

 

語音合成

 

  • WIKI Speech synthesis (https://en.wikipedia.org/wiki/Speech_synthesis)
  • 論文:WaveNet:A Generative Model for Raw Audio (https://arxiv.org/abs/1609.03499)
  • 論文:Tacotron:Towards End-to-End Speech Synthesis (https://arxiv.org/abs/1703.10135)
  • 論文:DeepVoice 2: Multi-Speaker Neural Text-to-Speech (https://arxiv.org/abs/1705.08947)
  • 資源: TheWorld English Bible (https://github.com/Kyubyong/tacotron)
  • 資源: LJSpeech Dataset (https://github.com/keithito/tacotron)
  • 資源: LessacData (http://www.cstr.ed.ac.uk/projects/blizzard/2011/lessac_blizzard2011/)
  • 競賽:Blizzard Challenge 2017 (https://synsig.org/index.php/Blizzard_Challenge_2017)
  • PRODUCT Lyrebird (https://lyrebird.ai/)
  • 專案: 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)

 

語音增強

 

  • WIKI Speech enhancement (https://en.wikipedia.org/wiki/Speech_enhancement)
  • 書籍: 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)
  • 論文 AnExperimental Study on Speech Enhancement BasedonDeepNeuralNetwork (http://staff.ustc.edu.cn/~jundu/Speech%20signal%20processing/publications/SPL2014_Xu.pdf)
  • 論文: 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)
  • 論文: 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)

 

語音文字轉換

 

  • 見「自動語音識別」部分

 

口語的術語檢測

 

  • 見「語音分割」部分

 

詞幹提取

 

  • WIKI Stemming (https://en.wikipedia.org/wiki/Stemming)
  • 論文: 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)

 

術語提取

 

  • WIKI Terminology extraction (https://en.wikipedia.org/wiki/Terminology_extraction)
  • 論文: NeuralAttention Models for Sequence Classification: Analysis and Application to KeyTerm Extraction and Dialogue Act Detection (https://arxiv.org/pdf/1604.00077.pdf)

 

文字簡化

 

  • WIKI Text simplification (https://en.wikipedia.org/wiki/Text_simplification)
  • 論文:Aligning Sentences from Standard Wikipedia to Simple Wikipedia (https://ssli.ee.washington.edu/~hannaneh/papers/simplification.pdf)
  • 論文:Problems in Current Text Simplification Research: New Data Can Help (https://pdfs.semanticscholar.org/2b8d/a013966c0c5e020ebc842d49d8ed166c8783.pdf)
  • 資源:Newsela Data (https://newsela.com/data/)

 

文字語音轉換

 

  • 見「語音合成」部分

 

文字蘊涵

 

  • WIKI Textual entailment (https://en.wikipedia.org/wiki/Textual_entailment)
  • 專案:Textual Entailment with TensorFlow (https://github.com/Steven-Hewitt/Entailment-with-Tensorflow)
  • 論文:Textual Entailment with Structured Attentions and Composition (https://arxiv.org/pdf/1701.01126.pdf)
  • 競賽:SemEval-2014 Task 1: Evaluation of compositional distributional semantic modelson full sentences through semantic relatedness and textual entailment (http://alt.qcri.org/semeval2014/task1/)
  • 競賽:SemEval-2013 Task 7: The Joint Student Response Analysis and 8th RecognizingTextual Entailment Challenge (https://www.cs.york.ac.uk/semeval-2013/task7.html)

 

聲音轉換

 

  • 論文:PHONETIC POSTERIORGRAMS FOR MANY-TO-ONE VOICE CONVERSION WITHOUT PARALLEL DATATRAINING (http://www1.se.cuhk.edu.hk/~hccl/publications/pub/2016_paper_297.pdf)
  • 專案: Animplementation of voice conversion system utilizing phonetic posteriorgrams (https://github.com/sesenosannko/ppg_vc)
  • 競賽: VoiceConversion Challenge 2016 (http://www.vc-challenge.org/vcc2016/index.html)
  • 競賽: VoiceConversion Challenge 2018 (http://www.vc-challenge.org/)
  • 資源:CMU_ARCTIC speech synthesis databases (http://festvox.org/cmu_arctic/)
  • 資源: TIMITAcoustic-Phonetic Continuous Speech Corpus (https://catalog.ldc.upenn.edu/ldc93s1)

 

聲音識別

 

  • 見「說話人識別」部分

 

詞嵌入

 

  • 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)
  • 專案:Pre-trained word vectors of 30+ languages (https://github.com/Kyubyong/wordvectors)
  • 專案:Polyglot: Distributed word representations for multilingual NLP (https://sites.google.com/site/rmyeid/projects/polyglot)

 

詞預測

 

  • INFO What is Word Prediction? (http://www2.edc.org/ncip/library/wp/what_is.htm)
  • 論文: Theprediction of character based on recurrent neural network language model (http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7960065)
  • 論文: AnEmbedded Deep Learning based Word Prediction (https://arxiv.org/abs/1707.01662)
  • 論文:Evaluating Word Prediction: Framing Keystroke Savings (http://aclweb.org/anthology/P08-2066)
  • 資源: AnEmbedded Deep Learning based Word Prediction (https://github.com/Meinwerk/WordPrediction/master.zip)
  • 專案: WordPrediction using Convolutional Neural Networks—can you do better than iPhone™Keyboard? (https://github.com/Kyubyong/word_prediction)

 

詞分割

 

  • WIKI Word segmentation (https://en.wikipedia.org/wiki/Text_segmentation#Segmentation_problems)
  • 論文: NeuralWord Segmentation Learning for Chinese (https://arxiv.org/abs/1606.04300)
  • 專案: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)

 

詞義消歧

 

  • 資源:Word-sense disambiguation (https://en.wikipedia.org/wiki/Word-sense_disambiguation)
  • 論文:Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in MultipleLanguages without Manual Training Data (http://www.aclweb.org/anthology/D17-1008)
  • 資源:Train-O-Matic Data (http://trainomatic.org/data/train-o-matic-data.zip)
  • 資源:BabelNet (http://babelnet.org/)

相關文章