选自GitHub
作者:Kyubyong Park
机器之心编译
参与:刘晓坤、李泽南
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,Kyubyong Park 为我们整理了一份完整列表。
GitHub 项目链接:github.com/Kyubyong/nl…
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 (github.com/Kyubyong/nl…)
自动作文评分
- 论文:AutomaticText Scoring Using Neural Networks (arxiv.org/abs/1606.04…)
- 论文:ANeural Approach to Automated Essay Scoring(www.aclweb.org/old_antholo…)
- 竞赛:Kaggle:The Hewlett Foundation: Automated Essay Scoring(www.kaggle.com/c/asap-aes)
- 项目:EnhancedAI Scoring Engine(github.com/edx/ease)
自动语音识别
- WIKI Speech recognition(en.wikipedia.org/wiki/Speech…)
- 论文:DeepSpeech 2: End-to-End Speech Recognition in English and Mandarin(arxiv.org/abs/1512.02…)
- 论文:WaveNet:A Generative Model for Raw Audio (arxiv.org/abs/1609.03…)
- 项目:A TensorFlow implementation of Baidu's DeepSpeech architecture(github.com/mozilla/Dee…)
- 项目:Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition using DeepMind's WaveNet(github.com/buriburisur…)
- 竞赛:The 5thCHiME Speech Separation and Recognition Challenge(spandh.dcs.shef.ac.uk/chime_chall…)
- 资源:The 5thCHiME Speech Separation and Recognition Challenge(spandh.dcs.shef.ac.uk/chime_chall…)
- 资源:CSTRVCTK Corpus(homepages.inf.ed.ac.uk/jyamagis/pa…)
- 资源:LibriSpeechASR corpus (www.openslr.org/12/)
- 资源:Switchboard-1Telephone Speech Corpus (catalog.ldc.upenn.edu/ldc97s62)
- 资源:TED-LIUMCorpus (www-lium.univ-lemans.fr/en/content/…)
自动摘要
- WIKI Automatic summarization (en.wikipedia.org/wiki/Automa…)
- 书籍:AutomaticText Summarization (www.amazon.com/Automatic-T…)
- 论文:TextSummarization Using Neural Networks(citeseerx.ist.psu.edu/viewdoc/dow…)
- 论文:Rankingwith Recursive Neural Networks and Its Application to Multi-DocumentSummarization(www.aaai.org/ocs/index.p…)
- 资源:TextAnalytics Conferences(TAC)(tac.nist.gov/data/index.…)
- 资源:DocumentUnderstanding Conferences (DUC)(www-nlpir.nist.gov/projects/du…)
指代消解
- INFO Coreference Resolution(nlp.stanford.edu/projects/co…)
- 论文:DeepReinforcement Learning for Mention-Ranking Coreference Models(arxiv.org/abs/1609.08…)
- 论文:ImprovingCoreference Resolution by Learning Entity-Level Distributed Representations(arxiv.org/abs/1606.01…)
- 竞赛:CoNLL2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes(conll.cemantix.org/2012/task-d…)
- 竞赛:CoNLL2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes(conll.cemantix.org/2011/task-d…)
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(arxiv.org/abs/1606.00…)
- 竞赛:CoNLL-2013Shared Task: Grammatical Error Correction(www.comp.nus.edu.sg/~nlp/conll1…)
- 竞赛:CoNLL-2014Shared Task: Grammatical Error Correction(www.comp.nus.edu.sg/~nlp/conll1…)
- 资源:NUSNon-commercial research/trial corpus license(www.comp.nus.edu.sg/~nlp/conll1…)
- 资源:Lang-8Learner Corpora(cl.naist.jp/nldata/lang…)
- 资源:CornellMovie--Dialogs Corpus (www.cs.cornell.edu/~cristian/C…)
- 项目:DeepText Corrector(github.com/atpaino/dee…)
- 产品:deepgrammar(deepgrammar.com/)
字素音素转换
- 论文:Grapheme-to-PhonemeModels for (Almost) Any Language(pdfs.semanticscholar.org/b9c8/fef9b6…)
- 论文:PolyglotNeural Language Models: A Case Study in Cross-Lingual Phonetic RepresentationLearning (arxiv.org/pdf/1605.03…)
- 论文:MultitaskSequence-to-Sequence Models for Grapheme-to-Phoneme Conversion(pdfs.semanticscholar.org/26d0/09959f…)
- 项目:Sequence-to-Sequence G2P toolkit (github.com/cmusphinx/g…)
- 资源:Multilingual Pronunciation Data(drive.google.com/drive/folde…)
语种猜测
- 见「语种辨别」部分
语种辨别
- WIKI Language identification (en.wikipedia.org/wiki/Langua…)
- 论文:AUTOMATICLANGUAGE IDENTIFICATION USING DEEP NEURAL NETWORKS(repositorio.uam.es/bitstream/h…)
- 竞赛: 2015Language Recognition Evaluation (www.nist.gov/itl/iad/mig…)
语言建模
- WIKI Language model (en.wikipedia.org/wiki/Langua…)
- 工具包: KenLMLanguage Model Toolkit (kheafield.com/code/kenlm/)
- 论文:DistributedRepresentations of Words and Phrases and their Compositionality(papers.nips.cc/paper/5021-…)
- 论文:Character-AwareNeural Language Models(www.aaai.org/ocs/index.p…)
- 资源: PennTreebank (github.com/townie/PTB-…)
语种识别
- 见「语种辨别」部分
同一词类
- WIKI Lemmatisation (en.wikipedia.org/wiki/Lemmat…)
- 论文: JointLemmatization and Morphological Tagging with LEMMING(www.cis.lmu.de/~muellets/p…)
- 工具包:WordNet Lemmatizer(www.nltk.org/api/nltk.st…)
- 资源:Treebank-3 (catalog.ldc.upenn.edu/ldc99t42)
观唇辨意
- WIKI Lip reading (en.wikipedia.org/wiki/Lip_re…)
- 论文:LipReading Sentences in the Wild (arxiv.org/abs/1611.05…)
- 论文:3DConvolutional Neural Networks for Cross Audio-Visual Matching Recognition(arxiv.org/abs/1706.05…)
- 项目: LipReading - Cross Audio-Visual Recognition using 3D Convolutional Neural Networks(github.com/astorfi/lip…)
- 资源: TheGRID audiovisual sentence corpus (spandh.dcs.shef.ac.uk/gridcorpus/)
机器翻译
- 论文:NeuralMachine Translation by Jointly Learning to Align and Translate(arxiv.org/abs/1409.04…)
- 论文:NeuralMachine Translation in Linear Time (arxiv.org/abs/1610.10…)
- 论文:AttentionIs All You Need(arxiv.org/abs/1706.03…)
- 竞赛: ACL2014 NINTH WORKSHOP ON STATISTICAL MACHINE TRANSLATION(www.statmt.org/wmt14/trans…)
- 竞赛: EMNLP2017 SECOND CONFERENCE ON MACHINE TRANSLATION (WMT17)(www.statmt.org/wmt17/trans…)
- 资源:OpenSubtitles2016 (opus.lingfil.uu.se/OpenSubtitl…)
- 资源: WIT3:Web Inventory of Transcribed and Translated Talks (wit3.fbk.eu/)
- 资源: TheQCRI Educational Domain (QED) Corpus(alt.qcri.org/resources/q…)
生成词法变化
- WIKI Inflection (en.wikipedia.org/wiki/Inflec…)
- 论文:MorphologicalInflection Generation Using Character Sequence to Sequence Learning(arxiv.org/abs/1512.06…)
- 竞赛:SIGMORPHON 2016 Shared Task: Morphological Reinflection(ryancotterell.github.io/sigmorphon2…)
- 资源:sigmorphon2016 (github.com/ryancottere…)
命名实体消歧
- WIKI Entity linking (en.wikipedia.org/wiki/Entity…)
- 论文:Robustand Collective Entity Disambiguation through Semantic Embeddings(www.stefanzwicklbauer.info/pdf/Sigir_2…)
命名实体识别
- WIKI Named-entity recognition (en.wikipedia.org/wiki/Named-…)
- 论文:NeuralArchitectures for Named Entity Recognition (arxiv.org/abs/1603.01…)
- 项目: OSUTwitter NLP Tools (github.com/aritter/twi…)
- 竞赛: NamedEntity Recognition in Twitter (noisy-text.github.io/2016/ner-sh…)
- 竞赛: CoNLL2002 Language-Independent Named Entity Recognition(www.clips.uantwerpen.be/conll2002/n…)
- 竞赛:Introduction to the CoNLL-2003 Shared Task: Language-Independent Named EntityRecognition (aclweb.org/anthology/W…)
- 资源:CoNLL-2002 NER corpus(github.com/teropa/nlp/…)
- 资源:CoNLL-2003 NER corpus (github.com/synalp/NER/…)
- 资源: NUTNamed Entity Recognition in Twitter Shared task(github.com/aritter/twi…)
释义检测
- 论文:DynamicPooling and Unfolding Recursive Autoencoders for Paraphrase Detection(citeseerx.ist.psu.edu/viewdoc/dow…)
- 项目:Paralex: Paraphrase-Driven Learning for Open Question Answering(knowitall.cs.washington.edu/paralex/)
- 资源:Microsoft Research Paraphrase Corpus (www.microsoft.com/en-us/downl…)
- 资源:Microsoft Research Video Description Corpus (www.microsoft.com/en-us/downl…)
- 资源: PascalDataset (nlp.cs.illinois.edu/Hockenmaier…)
- 资源:Flicker Dataset (nlp.cs.illinois.edu/Hockenmaier…)
- 资源: TheSICK data set (clic.cimec.unitn.it/composes/si…)
- 资源: PPDB:The Paraphrase Database (www.cis.upenn.edu/~ccb/ppdb/)
- 资源:WikiAnswers Paraphrase Corpus(knowitall.cs.washington.edu/paralex/wik…)
语法分析
- WIKI Parsing (en.wikipedia.org/wiki/Parsin…)
- 工具包: TheStanford Parser: A statistical parser (nlp.stanford.edu/software/le…)
- 工具包: spaCyparser (spacy.io/docs/usage/…)
- 论文:A fastand accurate dependency parser using neural networks(www.aclweb.org/anthology/D…)
- 竞赛: CoNLL2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (universaldependencies.org/conll17/)
- 竞赛: CoNLL2016 Shared Task: Multilingual Shallow Discourse Parsing(www.cs.brandeis.edu/~clp/conll1…)
- 竞赛: CoNLL2015 Shared Task: Shallow Discourse Parsing(www.cs.brandeis.edu/~clp/conll1…)
- 竞赛:SemEval-2016 Task 8: The meaning representations may be abstract, but this taskis concrete! (alt.qcri.org/semeval2016…)
词性标记
- WIKI Part-of-speech tagging (en.wikipedia.org/wiki/Part-o…)
- 论文:MultilingualPart-of-Speech Tagging with Bidirectional Long Short-Term Memory Models andAuxiliary Loss (arxiv.org/pdf/1604.05…)
- 论文:UnsupervisedPart-Of-Speech Tagging with Anchor Hidden Markov Models(transacl.org/ojs/index.p…)
- 资源:Treebank-3 (catalog.ldc.upenn.edu/ldc99t42)
- 工具包:nltk.tag package (www.nltk.org/api/nltk.ta…)
拼音-中文转换
- 论文:NeuralNetwork Language Model for Chinese Pinyin Input Method Engine(aclweb.org/anthology/Y…)
- 项目: NeuralChinese Transliterator(github.com/Kyubyong/ne…)
问答系统
- WIKI Question answering (en.wikipedia.org/wiki/Questi…)
- 论文:Ask MeAnything: Dynamic Memory Networks for Natural Language Processing(www.thespermwhale.com/jaseweston/…)
- 论文:DynamicMemory Networks for Visual and Textual Question Answering(proceedings.mlr.press/v48/xiong16…)
- 竞赛: TRECQuestion Answering Task (trec.nist.gov/data/qamain…)
- 竞赛:NTCIR-8: Advanced Cross-lingual Information Access (ACLIA)(aclia.lti.cs.cmu.edu/ntcir8/Home)
- 竞赛: CLEFQuestion Answering Track (nlp.uned.es/clef-qa/)
- 竞赛:SemEval-2017 Task 3: Community Question Answering(alt.qcri.org/semeval2017…)
- 资源: MSMARCO: Microsoft MAchine Reading COmprehension Dataset(www.msmarco.org/)
- 资源:Maluuba NewsQA (github.com/Maluuba/new…)
- 资源: SQuAD:100,000+ Questions for Machine Comprehension of Text(rajpurkar.github.io/SQuAD-explo…)
- 资源:GraphQuestions: A Characteristic-rich Question Answering Dataset(github.com/ysu1989/Gra…)
- 资源: StoryCloze Test and ROCStories Corpora (cs.rochester.edu/nlp/rocstor…)
- 资源:Microsoft Research WikiQA Corpus (www.microsoft.com/en-us/downl…)
- 资源:DeepMind Q&A Dataset (cs.nyu.edu/~kcho/DMQA/)
- 资源: QASent(cs.stanford.edu/people/meng…)
关系提取
- WIKI Relationship extraction (en.wikipedia.org/wiki/Relati…)
- 论文:A deeplearning approach for relationship extraction from interaction context insocial manufacturing paradigm(www.sciencedirect.com/science/art…)
语义角色标注
- WIKI Semantic role labeling (en.wikipedia.org/wiki/Semant…)
- 书籍:Semantic Role Labeling (www.amazon.com/Semantic-La…)
- 论文:End-to-endLearning of Semantic Role Labeling Using Recurrent Neural Networks(www.aclweb.org/anthology/P…)
- 论文:NeuralSemantic Role Labeling with Dependency Path Embeddi ngs(arxiv.org/abs/1605.07…)
- 竞赛:CoNLL-2005 Shared Task: Semantic Role Labeling(www.cs.upc.edu/~srlconll/s…)
- 竞赛:CoNLL-2004 Shared Task: Semantic Role Labeling(www.cs.upc.edu/~srlconll/s…)
- 工具包:Illinois Semantic Role Labeler (SRL)(cogcomp.org/page/softwa…)
- 资源:CoNLL-2005 Shared Task: Semantic Role Labeling(www.cs.upc.edu/~srlconll/s…)
语句边界消歧
- WIKI Sentence boundary disambiguation(en.wikipedia.org/wiki/Senten…)
- 论文:AQuantitative and Qualitative Evaluation of Sentence Boundary Detection for theClinical Domain (www.ncbi.nlm.nih.gov/pmc/article…)
- 工具包: NLTKTokenizers (www.nltk.org/_modules/nl…)
- 资源: TheBritish National Corpus (www.natcorp.ox.ac.uk/)
- 资源:Switchboard-1 Telephone Speech Corpus (catalog.ldc.upenn.edu/ldc97s62)
情绪分析
- WIKI Sentiment analysis (en.wikipedia.org/wiki/Sentim…)
- INFO Awesome Sentiment Analysis (github.com/xiamx/aweso…)
- 竞赛:Kaggle: UMICH SI650 - Sentiment Classification(www.kaggle.com/c/si650wint…)
- 竞赛:SemEval-2017 Task 4: Sentiment Analysis in Twitter(alt.qcri.org/semeval2017…)
- 竞赛:SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogsand News (alt.qcri.org/semeval2017…)
- 项目:SenticNet (sentic.net/about/)
- 资源:Multi-Domain Sentiment Dataset (version2.0)(www.cs.jhu.edu/~mdredze/da…)
- 资源:Stanford Sentiment Treebank (nlp.stanford.edu/sentiment/c…)
- 资源:Twitter Sentiment Corpus (www.sananalytics.com/lab/twitter…)
- 资源:Twitter Sentiment Analysis Training Corpus (thinknook.com/twitter-sen…)
- 资源: AFINN:List of English words rated for valence(www2.imm.dtu.dk/pubdb/views…)
源分离
- WIKI Source separation (en.wikipedia.org/wiki/Source…)
- 论文:FromBlind to Guided Audio Source Separation (hal-univ-rennes1.archives-ouvertes.fr/hal-0092237…)
- 论文:JointOptimization of Masks and Deep Recurrent Neural Networks for Monaural SourceSeparation (arxiv.org/abs/1502.04…)
- 竞赛: SignalSeparation Evaluation Campaign (SiSEC)(sisec.inria.fr/)
- 竞赛: CHiMESpeech Separation and Recognition Challenge(spandh.dcs.shef.ac.uk/chime_chall…)
说话人认证
- 见「说话人识别」部分
语音身份分离
- WIKI Speaker diarisation (en.wikipedia.org/wiki/Speake…)
- 论文:DNN-basedspeaker clustering for speaker diarisation(eprints.whiterose.ac.uk/109281/1/mi…)
- 论文:UnsupervisedMethods for Speaker Diarization: An Integrated and Iterative Approach(groups.csail.mit.edu/sls/publica…)
- 论文:Audio-VisualSpeaker Diarization Based on Spatiotemporal Bayesian Fusion(arxiv.org/pdf/1603.09…)
- 竞赛: RichTranscription Evaluation (www.nist.gov/itl/iad/mig…)
说话人识别
- WIKI Speaker recognition (en.wikipedia.org/wiki/Speake…)
- 论文:A NOVELSCHEME FOR SPEAKER RECOGNITION USING A PHONETICALLY-AWARE DEEP NEURAL NETWORK(pdfs.semanticscholar.org/204a/ff8e21…)
- 论文:DEEPNEURAL NETWORKS FOR SMALL FOOTPRINT TEXT-DEPENDENT SPEAKER VERIFICATION(static.googleusercontent.com/media/resea…)
- 竞赛: NISTSpeaker Recognition Evaluation (SRE)(www.nist.gov/itl/iad/mig…)
- INFO Are there any suggestions for free databases for speakerrecognition?(www.researchgate.net/post/Are_th…)
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 (en.wikipedia.org/wiki/Speech…)
- 论文:WordSegmentation by 8-Month-Olds: When Speech Cues Count More Than Statistics(www.utm.toronto.edu/infant-chil…)
- 论文:UnsupervisedWord Segmentation and Lexicon Discovery Using Acoustic Word Embeddings (arxiv.org/abs/1603.02…)
- 论文:UnsupervisedLexicon Discovery from Acoustic Inpu(www.aclweb.org/old_antholo…)
- 论文:Weaklysupervised spoken term discovery using cross-lingual side information(www.research.ed.ac.uk/portal/file…)
- 资源:CALLHOME Spanish Speech (catalog.ldc.upenn.edu/ldc96s35)
语音合成
- WIKI Speech synthesis (en.wikipedia.org/wiki/Speech…)
- 论文:WaveNet:A Generative Model for Raw Audio (arxiv.org/abs/1609.03…)
- 论文:Tacotron:Towards End-to-End Speech Synthesis (arxiv.org/abs/1703.10…)
- 论文:DeepVoice 2: Multi-Speaker Neural Text-to-Speech(arxiv.org/abs/1705.08…)
- 资源: TheWorld English Bible (github.com/Kyubyong/ta…)
- 资源: LJSpeech Dataset (github.com/keithito/ta…)
- 资源: LessacData (www.cstr.ed.ac.uk/projects/bl…)
- 竞赛:Blizzard Challenge 2017 (synsig.org/index.php/B…)
- PRODUCT Lyrebird (lyrebird.ai/)
- 项目: TheFestvox project (www.festvox.org/index.html)
- 工具包:Merlin: The Neural Network (NN) based Speech Synthesis System(github.com/CSTR-Edinbu…)
语音增强
- WIKI Speech enhancement (en.wikipedia.org/wiki/Speech…)
- 书籍: Speechenhancement: theory and practice (www.amazon.com/Speech-Enha…)
- 论文 AnExperimental Study on Speech Enhancement BasedonDeepNeuralNetwork(staff.ustc.edu.cn/~jundu/Spee…)
- 论文: ARegression Approach to Speech Enhancement BasedonDeepNeuralNetworks(www.researchgate.net/profile/Yon…)
- 论文: SpeechEnhancement Based on Deep Denoising Autoencoder(www.researchgate.net/profile/Yu_…)
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 (en.wikipedia.org/wiki/Stemmi…)
- 论文: ABACKPROPAGATION NEURAL NETWORK TO IMPROVE ARABIC STEMMING(www.jatit.org/volumes/Vol…)
- 工具包: NLTKStemmers (www.nltk.org/howto/stem.…)
术语提取
- WIKI Terminology extraction (en.wikipedia.org/wiki/Termin…)
- 论文: NeuralAttention Models for Sequence Classification: Analysis and Application to KeyTerm Extraction and Dialogue Act Detection (arxiv.org/pdf/1604.00…)
文本简化
- WIKI Text simplification (en.wikipedia.org/wiki/Text_s…)
- 论文:Aligning Sentences from Standard Wikipedia to Simple Wikipedia(ssli.ee.washington.edu/~hannaneh/p…)
- 论文:Problems in Current Text Simplification Research: New Data Can Help(pdfs.semanticscholar.org/2b8d/a01396…)
- 资源:Newsela Data (newsela.com/data/)
文本语音转换
- 见「语音合成」部分
文本蕴涵
- WIKI Textual entailment (en.wikipedia.org/wiki/Textua…)
- 项目:Textual Entailment with TensorFlow (github.com/Steven-Hewi…)
- 论文:Textual Entailment with Structured Attentions and Composition(arxiv.org/pdf/1701.01…)
- 竞赛:SemEval-2014 Task 1: Evaluation of compositional distributional semantic modelson full sentences through semantic relatedness and textual entailment(alt.qcri.org/semeval2014…)
- 竞赛:SemEval-2013 Task 7: The Joint Student Response Analysis and 8th RecognizingTextual Entailment Challenge (www.cs.york.ac.uk/semeval-201…)
声音转换
- 论文:PHONETIC POSTERIORGRAMS FOR MANY-TO-ONE VOICE CONVERSION WITHOUT PARALLEL DATATRAINING(www1.se.cuhk.edu.hk/~hccl/publi…)
- 项目: Animplementation of voice conversion system utilizing phonetic posteriorgrams(github.com/sesenosannk…)
- 竞赛: VoiceConversion Challenge 2016 (www.vc-challenge.org/vcc2016/ind…)
- 竞赛: VoiceConversion Challenge 2018 (www.vc-challenge.org/)
- 资源:CMU_ARCTIC speech synthesis databases (festvox.org/cmu_arctic/)
- 资源: TIMITAcoustic-Phonetic Continuous Speech Corpus(catalog.ldc.upenn.edu/ldc93s1)
声音识别
- 见「说话人识别」部分
词嵌入
- WIKI Word embedding (en.wikipedia.org/wiki/Word_e…)
- 工具包:Gensim: word2vec (radimrehurek.com/gensim/mode…)
- 工具包:fastText (github.com/facebookres…)
- 工具包: GloVe:Global Vectors for Word Representation(nlp.stanford.edu/projects/gl…)
- INFO Where to get a pretrained model (github.com/3Top/word2v…)
- 项目:Pre-trained word vectors of 30+ languages(github.com/Kyubyong/wo…)
- 项目:Polyglot: Distributed word representations for multilingual NLP(sites.google.com/site/rmyeid…)
词预测
- INFO What is Word Prediction? (www2.edc.org/ncip/librar…)
- 论文: Theprediction of character based on recurrent neural network language model(ieeexplore.ieee.org/stamp/stamp…)
- 论文: AnEmbedded Deep Learning based Word Prediction(arxiv.org/abs/1707.01…)
- 论文:Evaluating Word Prediction: Framing Keystroke Savings(aclweb.org/anthology/P…)
- 资源: AnEmbedded Deep Learning based Word Prediction(github.com/Meinwerk/Wo…)
- 项目: WordPrediction using Convolutional Neural Networks—can you do better than iPhone™Keyboard? (github.com/Kyubyong/wo…)
词分割
- WIKI Word segmentation(en.wikipedia.org/wiki/Text_s…)
- 论文: NeuralWord Segmentation Learning for Chinese (arxiv.org/abs/1606.04…)
- 项目:Convolutional neural network for Chinese word segmentation(github.com/chqiwang/co…)
- 工具包:Stanford Word Segmenter (nlp.stanford.edu/software/se…)
- 工具包: NLTKTokenizers (www.nltk.org/_modules/nl…)
词义消歧
- 资源:Word-sense disambiguation (en.wikipedia.org/wiki/Word-s…)
- 论文:Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in MultipleLanguages without Manual Training Data (www.aclweb.org/anthology/D…)
- 资源:Train-O-Matic Data (trainomatic.org/data/train-…)
- 资源:BabelNet (babelnet.org/)