Neural Machine Translation
|
|
- Rosalyn Wilson
- 5 years ago
- Views:
Transcription
1 Neural Machine Translation Qun Liu, Peyman Passban ADAPT Centre, Dublin City University 29 January 2018, at DeepHack.Babel, MIPT The ADAPT Centre is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund.
2 Content Background: Machine Translation and Neural Network Transition: From Discrete Spaces to Continuous Spaces Neural Machine Translation: MT in a Continuous Space Implementing Seq2Seq models with PyTorch Conclusion 1
3 Background: Machine Translation and Neural Network Statistical Machine Translation (SMT) Deep Learning (DL) and Neural Network (NN) The Gap between DL and MT 2
4 Parallel Corpus 3
5 Word Alignment 4
6 Phrase Table 5
7 Decoding Process Build translation left to right Select a phrase to translate Maria no dio una bofetada a la bruja verde Mary did not slap the witch green 6
8 Decoding Process Build translation left to right Select a phrase to translate Find the translation for the phrase Maria no dio una bofetada a la bruja verde Mary did not slap the witch green 7
9 Decoding Process Build translation left to right Select a phrase to translate Find the translation for the phrase Add the phrase to the end of the partial translation Maria no dio una bofetada a la bruja verde Mary did not slap the witch green 8
10 Decoding Process Build translation left to right Select a phrase to translate Find the translation for the phrase Add the phrase to the end of the partial translation Mark words as translated Maria no dio una bofetada a la bruja verde Mary did not slap the witch green 9
11 Decoding Process One to many translation Maria no dio una bofetada a la bruja verde Mary did not slap the witch green 10
12 Decoding Process Many to one translation Maria no dio una bofetada a la bruja verde Mary did not slap the witch green 11
13 Decoding Process Many to one translation Maria no dio una bofetada a la bruja verde Mary did not slap the witch green 12
14 Decoding Process Reordering Maria no dio una bofetada a la bruja verde Mary did not slap the witch green 13
15 Decoding Process Translation finished! Maria no dio una bofetada a la bruja verde Mary did not slap the witch green 14
16 Search Space for Phrase-based SMT 约翰 Yuehan 喜欢 xihuan John loves Mary 玛丽 Mali 15
17 Search Space for Phrase-based SMT 约翰 Yuehan 喜欢 xihuan John loves Mary 玛丽 Mali 16 The search is directed by a weighted combination of various features: Translation probability Language model probability
18 Background: Machine Translation and Neural Network Statistical Machine Translation (SMT) Deep Learning (DL) and Neural Network (NN) o (slides taken from Kevin Duh s presentation) The Gap between DL and MT 17
19 Human Neurons - Very Loose Inspiration
20 Perceptrons - Linear Classifiers
21 Logistic Regression (1-layer net) Function model: f(x) = σ(w T x) o Parameters: vector w R d o σ is a non-linearity, e.g. sigmoid: o σ(z) = 1/(1 + exp ( z)) o Non-linearity will be important in expressiveness o multi-layer nets. Other non-linearities, e.g., o tanh (z) = (e z e z )/(e z + e z ) 20 Extracted from Kevin Duh s slides in DL4MT Winter School
22 2-layer Neural Networks Called Multilayer Perceptron (MLP), but more like multilayer logistic regression 21 Extracted from Kevin Duh s slides in DL4MT Winter School
23 Expressive Power of Non-linearity A deeper architecture is more expressive than a shallow one given same number of nodes [Bishop, 1995] o 1-layer nets only model linear hyperplanes o 2-layer nets can model any continuous function (given sufficient nodes) o >3-layer nets can do so with fewer nodes 22 Extracted from Kevin Duh s slides in DL4MT Winter School
24 What is Deep Learning? A family of methods that uses deep architectures to learn high-level feature representations 23 Extracted from Kevin Duh s slides in DL4MT Winter School
25 Automatically Trained Features in FR Automatically trained features make sense! [Lee et al., 2009] Input: Images (raw pixels) Output: Features of Edges, Body Parts, Full Faces 24 Extracted from Kevin Duh s slides in DL4MT Winter School
26 Current models are becoming more complex 25 Extracted from Kevin Duh s slides in DL4MT Winter School
27 Background: Machine Translation and Neural Network Statistical Machine Translation (SMT) Deep Learning (DL) and Neural Network (NN) The Gap between DL and MT 26
28 The Gap between DL and MT Discrete symbols Continuous vectors 27
29 Content Background: Machine Translation and Neural Network Transition: From Discrete Spaces to Continuous Spaces Neural Machine Translation: MT in a Continuous Space Implementing Seq2Seq models with PyTorch Conclusion 28
30 Transition From Discrete Space to Continuous Space Word Embedding Express a word in a continuous space Neural Language Model 29
31 Express a word in a continuous space David John play Mary loves like 30
32 Express a word in a continuous space John David Mary loves play like 31
33 One-Hot Vector The dimension of the vector is the vocabulary size Each dimension is correspondent to a word Each word is represented as a vector that: o the element is equal to 1 at the dimension which is correspondent to that word o All the other elements are equal to 0 32
34 One-Hot Vector: Weakness The dimension is very high (equal to the vocabulary size / 100k) Very little information is carried by a one-hot vector o No syntactic information o No semantic information o No lexical information 33
35 Distributional Semantic Models Assumption: Words that are used and occur in the same contexts tend to purport similar meanings A typical model: Context Window: o A word is represented as the sum/average/tf-idf of the one-hot vectors appearing in the windows surrounding its every occurrence in the corpus o Effective for word similarity measurement o LSA can be used to reduce the dimension Weakness o Not compositional o Reverse Mapping is not supported 34
36 Word2Vec: Word Embedding by Neural Networks A word is represented by a dense vector (usually several hundreds dimensions) The Word2Vec matrix are trained by a 2-layer neural network 35 Extracted from Christopher Moody s slides
37 Word2Vec: CBOW context words current word 36 t-vector-representation-vs-output-vectorrepresentation-in-word2vec
38 Word2Vec: Skip-gram current word context words t-vector-representation-vs-output-vectorrepresentation-in-word2vec 37
39 Transition From Discrete Space to Continuous Space Word Embedding Express a word in a continuous space Neural Language Model Express a sentence in a continuous space 38
40 Language Models Given a sentence: w 1 w 2 w 3 w n, a language model is: p(w i w 1 w i 1 ) N-gram Language Model: p(w i w 1 w i 1 ) p(w i w i N+1 w i 1 ) Markov Chain Assumption 39
41 N-Gram Model A part of the parameter matrix of a bigram language model 40
42 N-Gram Model Normalize on all words A part of the parameter matrix of a bigram language model 41
43 Feed Forward Neural Network LM 42 [Bengio et al., 2003]
44 Feed Forward Neural Network LM 43 [Bengio et al., 2003]
45 Feed Forward Neural Network LM softmax layer Normalize on the vocabulary size Computational intensive 44 [Bengio et al., 2003]
46 Feed Forward Neural Network LM One shortcoming of FFNN LM is that it can only take limited length of history, just like N-gram LM An improved NN LM is proposed to solve this problem: Recurrent Neural Network LM 45
47 Recurrent Neural Network LM 46
48 Recurrent Neural Network LM Unfold the RNN LM along the timeline: 47
49 LSTM & GRU: Improved Implementation of RNN Mitigating gradient vanishing and exploding Long distance dependency 48
50 Language Model for Generation Given language model p(w i w 1 w i 1 ) and a history, we can generate the next word with highest LM score: w t = argmax w t V p(w t w 1 w i 1 ) S 49
51 Content Background: Machine Translation and Neural Network Transition: From Discrete Spaces to Continuous Spaces Neural Machine Translation: MT in a Continuous Space Implementing Seq2Seq models with PyTorch Conclusion 50
52 Neural Machine Translation: MT in a Continuous Space 喜欢 约翰 玛丽 Mary John loves Chinese Space English Space 51
53 Neural Machine Translation: MT in a Continuous Space Neural Machine Translation (NMT) Attention-based NMT 52
54 Neural Machine Translation The same things with SMT: o Trained with a parallel corpus o The input and output are word sequences The difference with SMT: o A single, large neural network o All the internal computing is conducted on real values without symbols o No word-alignment o No phrase table or rule table o No n-gram language model 53
55 Neural Machine Translation <bos> 54
56 Neural Machine Translation: MT in a Continuous Space Neural Machine Translation (NMT) Attention-based NMT 55
57 Weakness of the simple NMT model The only connection between the source sentence and the target sentence is the single vector representation of the source sentence It is hard for this fix-length vector to capture the meaning of the variable-length sentence, especially when the sentence is very long When the sentence becomes longer, the translation quality drops dramatically 56
58 Attention-based Model: Improvement Keep the states for all words rather than the final state only Use bi-directional RNN to replace single directional RNN Use an attention mechanism as a soft alignment between the source words and target words 57
59 Bi-directional RNN 58 on-neural-machine-translation-gpus-part-3/
60 Bi-directional RNN The representation for the word in the context on-neural-machine-translation-gpus-part-3/
61 Bi-directional RNN It contains the context information of the word in both sides 60 on-neural-machine-translation-gpus-part-3/
62 Attention for NMT 61 on-neural-machine-translation-gpus-part-3/
63 Attention for NMT 62 on-neural-machine-translation-gpus-part-3/
64 Attention for NMT 63 on-neural-machine-translation-gpus-part-3/
65 Soft Alignments by Attention Mechanism 64 on-neural-machine-translation-gpus-part-3/
66 Attention-based NMT The attention-based NMT is very successful It s performance has outperformed the SoA of SMT Attention mechanism is used in many DL tasks, such as image caption generation 65
67 Content Background: Machine Translation and Neural Network Transition: From Discrete Spaces to Continuous Spaces Neural Machine Translation: MT in a Continuous Space Implementing Seq2Seq models with PyTorch Conclusion 66
68 Implementing Seq2Seq models with PyTorch Encoder-Decoder Model 67
69 cat Encoding
70 cat Encoding context
71 cat sat Encoding context
72 cat sat on Encoding context
73 cat sat on the Encoding context
74 cat sat on the mat Encoding context
75 cat sat on the mat EOS Encoding (Done!) context
76 cat sat on the mat EOS Encoding (Done!) context Encoder
77 cat sat on the mat EOS gorbeh Decoding context Encoder
78 cat sat on the mat EOS gorbeh ruyeh Decoding context Encoder
79 cat sat on the mat EOS gorbeh ruyeh hasir Decoding context Encoder
80 cat sat on the mat EOS gorbeh ruyeh hasir neshast Decoding context Encoder
81 cat sat on the mat EOS gorbeh ruyeh hasir neshast EOS Decoding context Encoder
82 cat sat on the mat EOS gorbeh ruyeh hasir neshast EOS Decoding (Done!) context Encoder Decoder
83 cat sat on the mat EOS gorbeh ruyeh Attention! context α 1 α 2 α 3 α 4 α 5 α 6
84 cat sat on the mat EOS Attention! α 1 α 2 α 3 α 4 α 5 α 6 + context
85 Encoder
86 Encoder
87 Encoder
88 Encoder w.com/questions/ /what-doessuper-do-in-python
89 Encoder embedding # Unique Source Words w_i
90 Encoder input-th embedding
91 Encoder input-th embedding h_(t-1) h_t output_t input h output
92 Encoder input h
93 Decoder+Attention
94 Decoder+Attention
95 Decoder+Attention Two embedding tables!?
96 Decoder+Attention
97 Decoder+Attention index (digit)
98 Decoder+Attention 1 x 1-1
99 Decoder+Attention 1 x 1-1 embedded: 1 x 1 x -1 embedded[0]: 1 x -1
100 Decoder+Attention 1 x 1-1 embedded: 1 x 1 x -1 embedded[0]: 1 x -1 hidden[0]: 1 x -1
101 Decoder+Attention decoder s state: embedded[0] ; hidden[0] ;
102 Decoder+Attention decoder s state: embedded[0] ; hidden[0] ;
103 Decoder+Attention Softmax ( ) 1 x max_length
104 cat sat on the mat EOS Attention! α 1 α 2 α 3 α 4 α 5 α 6 + context
105 Decoder+Attention 1 x max_length unsqueeze(0) 1 x 1 x max_length
106 Decoder+Attention 1 x max_length x embed
107 Decoder+Attention context: 1 x 1 x embed
108 Decoder+Attention Learning Phrase Representations using RNN Encoder Decoder for Statistical Machine Translation, EMNLP, 2014.
109 Decoder+Attention context: 1 x 1 x embed
110 Decoder+Attention context: 1 x 1 x embed
111 Decoder+Attention context: 1 x 1 x embed
112 Decoder+Attention context: 1 x 1 x embed
113 Decoder+Attention context: 1 x 1 x embed
114 Decoder+Attention
115 Putting together
116 Putting together
117 Putting together
118 Putting together pair: [[a, b, c], [a, b, c, d ]]
119 Putting together
120 Putting together training_pair[0]: [a, b, c] training_pair[1]: [a, b, c, d ]
121 Putting together training_pair[0]: [a, b, c] training_pair[1]: [a, b, c, d ]
122 Putting together training_pair[0]: [a, b, c] training_pair[1]: [a, b, c, d ]
123 Putting together
124 Putting together training_pair[0]: [a, b, c] training_pair[1]: [a, b, c, d ]
125 Putting together
126 cat sat on the mat EOS gorbeh ruyeh Decoding context Encoder
127 Putting together training_pair[0]: [a, b, c] training_pair[0][0]: [a] word embedding
128 Putting together init the decoder!
129 Putting together
130 Putting together
131 Putting together
132 Putting together
133 Putting together
134 Putting together
135 Content Background: Machine Translation and Neural Network Transition: From Discrete Spaces to Continuous Spaces Neural Machine Translation: MT in a Continuous Space Implementing Seq2Seq models with PyTorch Conclusion 134
136 Conclusion MT is a task defined in a discrete space In a deep learning framework, the MT is converted to a task defined in a continuous space Word embedding is used to map a word to a vector Recurrent Neural Network is used to model the word sequence Encoder-Decoder (or Sequence-to-Sequence) model is proposed for neural machine translation Attention-based mechanism is used to provide soft alignment for NMT NMT has outperformed SMT and still has huge potential 135
137 Further topics Subword level and character level models o Morphologically rich languages o Out-of-Vocabulary problem Multitask and Multiway models o Sharing parameters among Multiple MT models o Low resource or zero-shot language pairs Pure attention models o Higher performance 136
138 Thanks Q&A Speaker: Qun Liu Speaker: Peyman Passban 137
System Implementation for SemEval-2017 Task 4 Subtask A Based on Interpolated Deep Neural Networks
System Implementation for SemEval-2017 Task 4 Subtask A Based on Interpolated Deep Neural Networks 1 Tzu-Hsuan Yang, 2 Tzu-Hsuan Tseng, and 3 Chia-Ping Chen Department of Computer Science and Engineering
More informationUnsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model
Unsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model Xinying Song, Xiaodong He, Jianfeng Gao, Li Deng Microsoft Research, One Microsoft Way, Redmond, WA 98052, U.S.A.
More informationPython Machine Learning
Python Machine Learning Unlock deeper insights into machine learning with this vital guide to cuttingedge predictive analytics Sebastian Raschka [ PUBLISHING 1 open source I community experience distilled
More informationSecond Exam: Natural Language Parsing with Neural Networks
Second Exam: Natural Language Parsing with Neural Networks James Cross May 21, 2015 Abstract With the advent of deep learning, there has been a recent resurgence of interest in the use of artificial neural
More informationA New Perspective on Combining GMM and DNN Frameworks for Speaker Adaptation
A New Perspective on Combining GMM and DNN Frameworks for Speaker Adaptation SLSP-2016 October 11-12 Natalia Tomashenko 1,2,3 natalia.tomashenko@univ-lemans.fr Yuri Khokhlov 3 khokhlov@speechpro.com Yannick
More informationDeep Neural Network Language Models
Deep Neural Network Language Models Ebru Arısoy, Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran IBM T.J. Watson Research Center Yorktown Heights, NY, 10598, USA {earisoy, tsainath, bedk, bhuvana}@us.ibm.com
More informationA Neural Network GUI Tested on Text-To-Phoneme Mapping
A Neural Network GUI Tested on Text-To-Phoneme Mapping MAARTEN TROMPPER Universiteit Utrecht m.f.a.trompper@students.uu.nl Abstract Text-to-phoneme (T2P) mapping is a necessary step in any speech synthesis
More informationA Simple VQA Model with a Few Tricks and Image Features from Bottom-up Attention
A Simple VQA Model with a Few Tricks and Image Features from Bottom-up Attention Damien Teney 1, Peter Anderson 2*, David Golub 4*, Po-Sen Huang 3, Lei Zhang 3, Xiaodong He 3, Anton van den Hengel 1 1
More informationarxiv: v4 [cs.cl] 28 Mar 2016
LSTM-BASED DEEP LEARNING MODELS FOR NON- FACTOID ANSWER SELECTION Ming Tan, Cicero dos Santos, Bing Xiang & Bowen Zhou IBM Watson Core Technologies Yorktown Heights, NY, USA {mingtan,cicerons,bingxia,zhou}@us.ibm.com
More informationResidual Stacking of RNNs for Neural Machine Translation
Residual Stacking of RNNs for Neural Machine Translation Raphael Shu The University of Tokyo shu@nlab.ci.i.u-tokyo.ac.jp Akiva Miura Nara Institute of Science and Technology miura.akiba.lr9@is.naist.jp
More informationLearning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models
Learning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models Stephan Gouws and GJ van Rooyen MIH Medialab, Stellenbosch University SOUTH AFRICA {stephan,gvrooyen}@ml.sun.ac.za
More informationArtificial Neural Networks written examination
1 (8) Institutionen för informationsteknologi Olle Gällmo Universitetsadjunkt Adress: Lägerhyddsvägen 2 Box 337 751 05 Uppsala Artificial Neural Networks written examination Monday, May 15, 2006 9 00-14
More informationProbabilistic Latent Semantic Analysis
Probabilistic Latent Semantic Analysis Thomas Hofmann Presentation by Ioannis Pavlopoulos & Andreas Damianou for the course of Data Mining & Exploration 1 Outline Latent Semantic Analysis o Need o Overview
More informationFramewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures
Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures Alex Graves and Jürgen Schmidhuber IDSIA, Galleria 2, 6928 Manno-Lugano, Switzerland TU Munich, Boltzmannstr.
More informationarxiv: v1 [cs.cv] 10 May 2017
Inferring and Executing Programs for Visual Reasoning Justin Johnson 1 Bharath Hariharan 2 Laurens van der Maaten 2 Judy Hoffman 1 Li Fei-Fei 1 C. Lawrence Zitnick 2 Ross Girshick 2 1 Stanford University
More informationarxiv: v1 [cs.cl] 2 Apr 2017
Word-Alignment-Based Segment-Level Machine Translation Evaluation using Word Embeddings Junki Matsuo and Mamoru Komachi Graduate School of System Design, Tokyo Metropolitan University, Japan matsuo-junki@ed.tmu.ac.jp,
More informationTraining a Neural Network to Answer 8th Grade Science Questions Steven Hewitt, An Ju, Katherine Stasaski
Training a Neural Network to Answer 8th Grade Science Questions Steven Hewitt, An Ju, Katherine Stasaski Problem Statement and Background Given a collection of 8th grade science questions, possible answer
More informationAutoregressive product of multi-frame predictions can improve the accuracy of hybrid models
Autoregressive product of multi-frame predictions can improve the accuracy of hybrid models Navdeep Jaitly 1, Vincent Vanhoucke 2, Geoffrey Hinton 1,2 1 University of Toronto 2 Google Inc. ndjaitly@cs.toronto.edu,
More informationPOS tagging of Chinese Buddhist texts using Recurrent Neural Networks
POS tagging of Chinese Buddhist texts using Recurrent Neural Networks Longlu Qin Department of East Asian Languages and Cultures longlu@stanford.edu Abstract Chinese POS tagging, as one of the most important
More informationModel Ensemble for Click Prediction in Bing Search Ads
Model Ensemble for Click Prediction in Bing Search Ads Xiaoliang Ling Microsoft Bing xiaoling@microsoft.com Hucheng Zhou Microsoft Research huzho@microsoft.com Weiwei Deng Microsoft Bing dedeng@microsoft.com
More informationINPE São José dos Campos
INPE-5479 PRE/1778 MONLINEAR ASPECTS OF DATA INTEGRATION FOR LAND COVER CLASSIFICATION IN A NEDRAL NETWORK ENVIRONNENT Maria Suelena S. Barros Valter Rodrigues INPE São José dos Campos 1993 SECRETARIA
More informationPREDICTING SPEECH RECOGNITION CONFIDENCE USING DEEP LEARNING WITH WORD IDENTITY AND SCORE FEATURES
PREDICTING SPEECH RECOGNITION CONFIDENCE USING DEEP LEARNING WITH WORD IDENTITY AND SCORE FEATURES Po-Sen Huang, Kshitiz Kumar, Chaojun Liu, Yifan Gong, Li Deng Department of Electrical and Computer Engineering,
More informationSemi-supervised methods of text processing, and an application to medical concept extraction. Yacine Jernite Text-as-Data series September 17.
Semi-supervised methods of text processing, and an application to medical concept extraction Yacine Jernite Text-as-Data series September 17. 2015 What do we want from text? 1. Extract information 2. Link
More informationLecture 1: Machine Learning Basics
1/69 Lecture 1: Machine Learning Basics Ali Harakeh University of Waterloo WAVE Lab ali.harakeh@uwaterloo.ca May 1, 2017 2/69 Overview 1 Learning Algorithms 2 Capacity, Overfitting, and Underfitting 3
More informationAttributed Social Network Embedding
JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, MAY 2017 1 Attributed Social Network Embedding arxiv:1705.04969v1 [cs.si] 14 May 2017 Lizi Liao, Xiangnan He, Hanwang Zhang, and Tat-Seng Chua Abstract Embedding
More informationQuickStroke: An Incremental On-line Chinese Handwriting Recognition System
QuickStroke: An Incremental On-line Chinese Handwriting Recognition System Nada P. Matić John C. Platt Λ Tony Wang y Synaptics, Inc. 2381 Bering Drive San Jose, CA 95131, USA Abstract This paper presents
More informationA Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval
A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval Yelong Shen Microsoft Research Redmond, WA, USA yeshen@microsoft.com Xiaodong He Jianfeng Gao Li Deng Microsoft Research
More informationModeling function word errors in DNN-HMM based LVCSR systems
Modeling function word errors in DNN-HMM based LVCSR systems Melvin Jose Johnson Premkumar, Ankur Bapna and Sree Avinash Parchuri Department of Computer Science Department of Electrical Engineering Stanford
More informationAutoencoder and selectional preference Aki-Juhani Kyröläinen, Juhani Luotolahti, Filip Ginter
ESUKA JEFUL 2017, 8 2: 93 125 Autoencoder and selectional preference Aki-Juhani Kyröläinen, Juhani Luotolahti, Filip Ginter AN AUTOENCODER-BASED NEURAL NETWORK MODEL FOR SELECTIONAL PREFERENCE: EVIDENCE
More informationA study of speaker adaptation for DNN-based speech synthesis
A study of speaker adaptation for DNN-based speech synthesis Zhizheng Wu, Pawel Swietojanski, Christophe Veaux, Steve Renals, Simon King The Centre for Speech Technology Research (CSTR) University of Edinburgh,
More informationNatural Language Processing. George Konidaris
Natural Language Processing George Konidaris gdk@cs.brown.edu Fall 2017 Natural Language Processing Understanding spoken/written sentences in a natural language. Major area of research in AI. Why? Humans
More informationModule 12. Machine Learning. Version 2 CSE IIT, Kharagpur
Module 12 Machine Learning 12.1 Instructional Objective The students should understand the concept of learning systems Students should learn about different aspects of a learning system Students should
More informationKnowledge Transfer in Deep Convolutional Neural Nets
Knowledge Transfer in Deep Convolutional Neural Nets Steven Gutstein, Olac Fuentes and Eric Freudenthal Computer Science Department University of Texas at El Paso El Paso, Texas, 79968, U.S.A. Abstract
More informationThe Karlsruhe Institute of Technology Translation Systems for the WMT 2011
The Karlsruhe Institute of Technology Translation Systems for the WMT 2011 Teresa Herrmann, Mohammed Mediani, Jan Niehues and Alex Waibel Karlsruhe Institute of Technology Karlsruhe, Germany firstname.lastname@kit.edu
More informationCourse Outline. Course Grading. Where to go for help. Academic Integrity. EE-589 Introduction to Neural Networks NN 1 EE
EE-589 Introduction to Neural Assistant Prof. Dr. Turgay IBRIKCI Room # 305 (322) 338 6868 / 139 Wensdays 9:00-12:00 Course Outline The course is divided in two parts: theory and practice. 1. Theory covers
More informationLearning Methods for Fuzzy Systems
Learning Methods for Fuzzy Systems Rudolf Kruse and Andreas Nürnberger Department of Computer Science, University of Magdeburg Universitätsplatz, D-396 Magdeburg, Germany Phone : +49.39.67.876, Fax : +49.39.67.8
More informationAssignment 1: Predicting Amazon Review Ratings
Assignment 1: Predicting Amazon Review Ratings 1 Dataset Analysis Richard Park r2park@acsmail.ucsd.edu February 23, 2015 The dataset selected for this assignment comes from the set of Amazon reviews for
More informationarxiv: v2 [cs.ir] 22 Aug 2016
Exploring Deep Space: Learning Personalized Ranking in a Semantic Space arxiv:1608.00276v2 [cs.ir] 22 Aug 2016 ABSTRACT Jeroen B. P. Vuurens The Hague University of Applied Science Delft University of
More informationModeling function word errors in DNN-HMM based LVCSR systems
Modeling function word errors in DNN-HMM based LVCSR systems Melvin Jose Johnson Premkumar, Ankur Bapna and Sree Avinash Parchuri Department of Computer Science Department of Electrical Engineering Stanford
More informationarxiv: v1 [cs.lg] 7 Apr 2015
Transferring Knowledge from a RNN to a DNN William Chan 1, Nan Rosemary Ke 1, Ian Lane 1,2 Carnegie Mellon University 1 Electrical and Computer Engineering, 2 Language Technologies Institute Equal contribution
More informationHuman Emotion Recognition From Speech
RESEARCH ARTICLE OPEN ACCESS Human Emotion Recognition From Speech Miss. Aparna P. Wanare*, Prof. Shankar N. Dandare *(Department of Electronics & Telecommunication Engineering, Sant Gadge Baba Amravati
More informationCalibration of Confidence Measures in Speech Recognition
Submitted to IEEE Trans on Audio, Speech, and Language, July 2010 1 Calibration of Confidence Measures in Speech Recognition Dong Yu, Senior Member, IEEE, Jinyu Li, Member, IEEE, Li Deng, Fellow, IEEE
More informationA Case Study: News Classification Based on Term Frequency
A Case Study: News Classification Based on Term Frequency Petr Kroha Faculty of Computer Science University of Technology 09107 Chemnitz Germany kroha@informatik.tu-chemnitz.de Ricardo Baeza-Yates Center
More information(Sub)Gradient Descent
(Sub)Gradient Descent CMSC 422 MARINE CARPUAT marine@cs.umd.edu Figures credit: Piyush Rai Logistics Midterm is on Thursday 3/24 during class time closed book/internet/etc, one page of notes. will include
More informationSyntactic systematicity in sentence processing with a recurrent self-organizing network
Syntactic systematicity in sentence processing with a recurrent self-organizing network Igor Farkaš,1 Department of Applied Informatics, Comenius University Mlynská dolina, 842 48 Bratislava, Slovak Republic
More informationLecture 1: Basic Concepts of Machine Learning
Lecture 1: Basic Concepts of Machine Learning Cognitive Systems - Machine Learning Ute Schmid (lecture) Johannes Rabold (practice) Based on slides prepared March 2005 by Maximilian Röglinger, updated 2010
More informationOCR for Arabic using SIFT Descriptors With Online Failure Prediction
OCR for Arabic using SIFT Descriptors With Online Failure Prediction Andrey Stolyarenko, Nachum Dershowitz The Blavatnik School of Computer Science Tel Aviv University Tel Aviv, Israel Email: stloyare@tau.ac.il,
More informationDropout improves Recurrent Neural Networks for Handwriting Recognition
2014 14th International Conference on Frontiers in Handwriting Recognition Dropout improves Recurrent Neural Networks for Handwriting Recognition Vu Pham,Théodore Bluche, Christopher Kermorvant, and Jérôme
More informationOn the Formation of Phoneme Categories in DNN Acoustic Models
On the Formation of Phoneme Categories in DNN Acoustic Models Tasha Nagamine Department of Electrical Engineering, Columbia University T. Nagamine Motivation Large performance gap between humans and state-
More informationA deep architecture for non-projective dependency parsing
Universidade de São Paulo Biblioteca Digital da Produção Intelectual - BDPI Departamento de Ciências de Computação - ICMC/SCC Comunicações em Eventos - ICMC/SCC 2015-06 A deep architecture for non-projective
More informationCS224d Deep Learning for Natural Language Processing. Richard Socher, PhD
CS224d Deep Learning for Natural Language Processing, PhD Welcome 1. CS224d logis7cs 2. Introduc7on to NLP, deep learning and their intersec7on 2 Course Logis>cs Instructor: (Stanford PhD, 2014; now Founder/CEO
More informationCSL465/603 - Machine Learning
CSL465/603 - Machine Learning Fall 2016 Narayanan C Krishnan ckn@iitrpr.ac.in Introduction CSL465/603 - Machine Learning 1 Administrative Trivia Course Structure 3-0-2 Lecture Timings Monday 9.55-10.45am
More informationSpeech Recognition at ICSI: Broadcast News and beyond
Speech Recognition at ICSI: Broadcast News and beyond Dan Ellis International Computer Science Institute, Berkeley CA Outline 1 2 3 The DARPA Broadcast News task Aspects of ICSI
More informationCS 598 Natural Language Processing
CS 598 Natural Language Processing Natural language is everywhere Natural language is everywhere Natural language is everywhere Natural language is everywhere!"#$%&'&()*+,-./012 34*5665756638/9:;< =>?@ABCDEFGHIJ5KL@
More informationCS Machine Learning
CS 478 - Machine Learning Projects Data Representation Basic testing and evaluation schemes CS 478 Data and Testing 1 Programming Issues l Program in any platform you want l Realize that you will be doing
More informationPhonetic- and Speaker-Discriminant Features for Speaker Recognition. Research Project
Phonetic- and Speaker-Discriminant Features for Speaker Recognition by Lara Stoll Research Project Submitted to the Department of Electrical Engineering and Computer Sciences, University of California
More informationAnalysis of Speech Recognition Models for Real Time Captioning and Post Lecture Transcription
Analysis of Speech Recognition Models for Real Time Captioning and Post Lecture Transcription Wilny Wilson.P M.Tech Computer Science Student Thejus Engineering College Thrissur, India. Sindhu.S Computer
More informationTest Effort Estimation Using Neural Network
J. Software Engineering & Applications, 2010, 3: 331-340 doi:10.4236/jsea.2010.34038 Published Online April 2010 (http://www.scirp.org/journal/jsea) 331 Chintala Abhishek*, Veginati Pavan Kumar, Harish
More informationTHE world surrounding us involves multiple modalities
1 Multimodal Machine Learning: A Survey and Taxonomy Tadas Baltrušaitis, Chaitanya Ahuja, and Louis-Philippe Morency arxiv:1705.09406v2 [cs.lg] 1 Aug 2017 Abstract Our experience of the world is multimodal
More informationTwitter Sentiment Classification on Sanders Data using Hybrid Approach
IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 17, Issue 4, Ver. I (July Aug. 2015), PP 118-123 www.iosrjournals.org Twitter Sentiment Classification on Sanders
More informationWhat Can Neural Networks Teach us about Language? Graham Neubig a2-dlearn 11/18/2017
What Can Neural Networks Teach us about Language? Graham Neubig a2-dlearn 11/18/2017 Supervised Training of Neural Networks for Language Training Data Training Model this is an example the cat went to
More informationKnowledge-Based - Systems
Knowledge-Based - Systems ; Rajendra Arvind Akerkar Chairman, Technomathematics Research Foundation and Senior Researcher, Western Norway Research institute Priti Srinivas Sajja Sardar Patel University
More informationDeep search. Enhancing a search bar using machine learning. Ilgün Ilgün & Cedric Reichenbach
#BaselOne7 Deep search Enhancing a search bar using machine learning Ilgün Ilgün & Cedric Reichenbach We are not researchers Outline I. Periscope: A search tool II. Goals III. Deep learning IV. Applying
More informationГлубокие рекуррентные нейронные сети для аспектно-ориентированного анализа тональности отзывов пользователей на различных языках
Глубокие рекуррентные нейронные сети для аспектно-ориентированного анализа тональности отзывов пользователей на различных языках Тарасов Д. С. (dtarasov3@gmail.com) Интернет-портал reviewdot.ru, Казань,
More informationCross Language Information Retrieval
Cross Language Information Retrieval RAFFAELLA BERNARDI UNIVERSITÀ DEGLI STUDI DI TRENTO P.ZZA VENEZIA, ROOM: 2.05, E-MAIL: BERNARDI@DISI.UNITN.IT Contents 1 Acknowledgment.............................................
More informationarxiv: v1 [cs.cl] 27 Apr 2016
The IBM 2016 English Conversational Telephone Speech Recognition System George Saon, Tom Sercu, Steven Rennie and Hong-Kwang J. Kuo IBM T. J. Watson Research Center, Yorktown Heights, NY, 10598 gsaon@us.ibm.com
More informationhave to be modeled) or isolated words. Output of the system is a grapheme-tophoneme conversion system which takes as its input the spelling of words,
A Language-Independent, Data-Oriented Architecture for Grapheme-to-Phoneme Conversion Walter Daelemans and Antal van den Bosch Proceedings ESCA-IEEE speech synthesis conference, New York, September 1994
More informationNoisy SMS Machine Translation in Low-Density Languages
Noisy SMS Machine Translation in Low-Density Languages Vladimir Eidelman, Kristy Hollingshead, and Philip Resnik UMIACS Laboratory for Computational Linguistics and Information Processing Department of
More informationLinking Task: Identifying authors and book titles in verbose queries
Linking Task: Identifying authors and book titles in verbose queries Anaïs Ollagnier, Sébastien Fournier, and Patrice Bellot Aix-Marseille University, CNRS, ENSAM, University of Toulon, LSIS UMR 7296,
More informationVisual CP Representation of Knowledge
Visual CP Representation of Knowledge Heather D. Pfeiffer and Roger T. Hartley Department of Computer Science New Mexico State University Las Cruces, NM 88003-8001, USA email: hdp@cs.nmsu.edu and rth@cs.nmsu.edu
More informationLanguage Model and Grammar Extraction Variation in Machine Translation
Language Model and Grammar Extraction Variation in Machine Translation Vladimir Eidelman, Chris Dyer, and Philip Resnik UMIACS Laboratory for Computational Linguistics and Information Processing Department
More informationRobust Speech Recognition using DNN-HMM Acoustic Model Combining Noise-aware training with Spectral Subtraction
INTERSPEECH 2015 Robust Speech Recognition using DNN-HMM Acoustic Model Combining Noise-aware training with Spectral Subtraction Akihiro Abe, Kazumasa Yamamoto, Seiichi Nakagawa Department of Computer
More informationThe MSR-NRC-SRI MT System for NIST Open Machine Translation 2008 Evaluation
The MSR-NRC-SRI MT System for NIST Open Machine Translation 2008 Evaluation AUTHORS AND AFFILIATIONS MSR: Xiaodong He, Jianfeng Gao, Chris Quirk, Patrick Nguyen, Arul Menezes, Robert Moore, Kristina Toutanova,
More informationJ j W w. Write. Name. Max Takes the Train. Handwriting Letters Jj, Ww: Words with j, w 321
Write J j W w Jen Will Directions Have children write a row of each letter and then write the words. Home Activity Ask your child to write each letter and tell you how to make the letter. Handwriting Letters
More informationWord Segmentation of Off-line Handwritten Documents
Word Segmentation of Off-line Handwritten Documents Chen Huang and Sargur N. Srihari {chuang5, srihari}@cedar.buffalo.edu Center of Excellence for Document Analysis and Recognition (CEDAR), Department
More informationA Vector Space Approach for Aspect-Based Sentiment Analysis
A Vector Space Approach for Aspect-Based Sentiment Analysis by Abdulaziz Alghunaim B.S., Massachusetts Institute of Technology (2015) Submitted to the Department of Electrical Engineering and Computer
More informationSyntax Parsing 1. Grammars and parsing 2. Top-down and bottom-up parsing 3. Chart parsers 4. Bottom-up chart parsing 5. The Earley Algorithm
Syntax Parsing 1. Grammars and parsing 2. Top-down and bottom-up parsing 3. Chart parsers 4. Bottom-up chart parsing 5. The Earley Algorithm syntax: from the Greek syntaxis, meaning setting out together
More informationSegmental Conditional Random Fields with Deep Neural Networks as Acoustic Models for First-Pass Word Recognition
Segmental Conditional Random Fields with Deep Neural Networks as Acoustic Models for First-Pass Word Recognition Yanzhang He, Eric Fosler-Lussier Department of Computer Science and Engineering The hio
More informationarxiv: v1 [cs.lg] 15 Jun 2015
Dual Memory Architectures for Fast Deep Learning of Stream Data via an Online-Incremental-Transfer Strategy arxiv:1506.04477v1 [cs.lg] 15 Jun 2015 Sang-Woo Lee Min-Oh Heo School of Computer Science and
More informationGeorgetown University at TREC 2017 Dynamic Domain Track
Georgetown University at TREC 2017 Dynamic Domain Track Zhiwen Tang Georgetown University zt79@georgetown.edu Grace Hui Yang Georgetown University huiyang@cs.georgetown.edu Abstract TREC Dynamic Domain
More informationClickthrough-Based Translation Models for Web Search: from Word Models to Phrase Models
Clickthrough-Based Translation Models for Web Search: from Word Models to Phrase Models Jianfeng Gao Microsoft Research One Microsoft Way Redmond, WA 98052 USA jfgao@microsoft.com Xiaodong He Microsoft
More information12- A whirlwind tour of statistics
CyLab HT 05-436 / 05-836 / 08-534 / 08-734 / 19-534 / 19-734 Usable Privacy and Security TP :// C DU February 22, 2016 y & Secu rivac rity P le ratory bo La Lujo Bauer, Nicolas Christin, and Abby Marsh
More informationDetecting English-French Cognates Using Orthographic Edit Distance
Detecting English-French Cognates Using Orthographic Edit Distance Qiongkai Xu 1,2, Albert Chen 1, Chang i 1 1 The Australian National University, College of Engineering and Computer Science 2 National
More informationTraining and evaluation of POS taggers on the French MULTITAG corpus
Training and evaluation of POS taggers on the French MULTITAG corpus A. Allauzen, H. Bonneau-Maynard LIMSI/CNRS; Univ Paris-Sud, Orsay, F-91405 {allauzen,maynard}@limsi.fr Abstract The explicit introduction
More informationarxiv: v2 [cs.cl] 26 Mar 2015
Effective Use of Word Order for Text Categorization with Convolutional Neural Networks Rie Johnson RJ Research Consulting Tarrytown, NY, USA riejohnson@gmail.com Tong Zhang Baidu Inc., Beijing, China Rutgers
More informationSpecification and Evaluation of Machine Translation Toy Systems - Criteria for laboratory assignments
Specification and Evaluation of Machine Translation Toy Systems - Criteria for laboratory assignments Cristina Vertan, Walther v. Hahn University of Hamburg, Natural Language Systems Division Hamburg,
More informationSpeaker Identification by Comparison of Smart Methods. Abstract
Journal of mathematics and computer science 10 (2014), 61-71 Speaker Identification by Comparison of Smart Methods Ali Mahdavi Meimand Amin Asadi Majid Mohamadi Department of Electrical Department of Computer
More informationIndian Institute of Technology, Kanpur
Indian Institute of Technology, Kanpur Course Project - CS671A POS Tagging of Code Mixed Text Ayushman Sisodiya (12188) {ayushmn@iitk.ac.in} Donthu Vamsi Krishna (15111016) {vamsi@iitk.ac.in} Sandeep Kumar
More information2/15/13. POS Tagging Problem. Part-of-Speech Tagging. Example English Part-of-Speech Tagsets. More Details of the Problem. Typical Problem Cases
POS Tagging Problem Part-of-Speech Tagging L545 Spring 203 Given a sentence W Wn and a tagset of lexical categories, find the most likely tag T..Tn for each word in the sentence Example Secretariat/P is/vbz
More informationMachine Learning and Data Mining. Ensembles of Learners. Prof. Alexander Ihler
Machine Learning and Data Mining Ensembles of Learners Prof. Alexander Ihler Ensemble methods Why learn one classifier when you can learn many? Ensemble: combine many predictors (Weighted) combina
More informationUsing dialogue context to improve parsing performance in dialogue systems
Using dialogue context to improve parsing performance in dialogue systems Ivan Meza-Ruiz and Oliver Lemon School of Informatics, Edinburgh University 2 Buccleuch Place, Edinburgh I.V.Meza-Ruiz@sms.ed.ac.uk,
More informationarxiv: v1 [cs.cl] 20 Jul 2015
How to Generate a Good Word Embedding? Siwei Lai, Kang Liu, Liheng Xu, Jun Zhao National Laboratory of Pattern Recognition (NLPR) Institute of Automation, Chinese Academy of Sciences, China {swlai, kliu,
More informationWord Embedding Based Correlation Model for Question/Answer Matching
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) Word Embedding Based Correlation Model for Question/Answer Matching Yikang Shen, 1 Wenge Rong, 2 Nan Jiang, 2 Baolin
More informationSwitchboard Language Model Improvement with Conversational Data from Gigaword
Katholieke Universiteit Leuven Faculty of Engineering Master in Artificial Intelligence (MAI) Speech and Language Technology (SLT) Switchboard Language Model Improvement with Conversational Data from Gigaword
More informationSpeech Emotion Recognition Using Support Vector Machine
Speech Emotion Recognition Using Support Vector Machine Yixiong Pan, Peipei Shen and Liping Shen Department of Computer Technology Shanghai JiaoTong University, Shanghai, China panyixiong@sjtu.edu.cn,
More informationEvolutive Neural Net Fuzzy Filtering: Basic Description
Journal of Intelligent Learning Systems and Applications, 2010, 2: 12-18 doi:10.4236/jilsa.2010.21002 Published Online February 2010 (http://www.scirp.org/journal/jilsa) Evolutive Neural Net Fuzzy Filtering:
More informationSARDNET: A Self-Organizing Feature Map for Sequences
SARDNET: A Self-Organizing Feature Map for Sequences Daniel L. James and Risto Miikkulainen Department of Computer Sciences The University of Texas at Austin Austin, TX 78712 dljames,risto~cs.utexas.edu
More informationDevice Independence and Extensibility in Gesture Recognition
Device Independence and Extensibility in Gesture Recognition Jacob Eisenstein, Shahram Ghandeharizadeh, Leana Golubchik, Cyrus Shahabi, Donghui Yan, Roger Zimmermann Department of Computer Science University
More informationPredicting Student Attrition in MOOCs using Sentiment Analysis and Neural Networks
Predicting Student Attrition in MOOCs using Sentiment Analysis and Neural Networks Devendra Singh Chaplot, Eunhee Rhim, and Jihie Kim Samsung Electronics Co., Ltd. Seoul, South Korea {dev.chaplot,eunhee.rhim,jihie.kim}@samsung.com
More informationAdaptive learning based on cognitive load using artificial intelligence and electroencephalography
Adaptive learning based on cognitive load using artificial intelligence and electroencephalography Håkon Jarle Hassel Master of Science in Computer Science Submission date: June 2017 Supervisor: Asbjørn
More information