Google SyntaxNet “Parsey McParseface and other SyntaxNet models are some of the most complex networks that we have trained with the TensorFlow framework.

Slides:



Advertisements
Similar presentations
School of something FACULTY OF OTHER School of Computing FACULTY OF ENGINEERING Chunking: Shallow Parsing Eric Atwell, Language Research Group.
Advertisements

Statistical NLP: Lecture 3
Deep Learning in NLP Word representation and how to use it for Parsing
For Monday Read Chapter 23, sections 3-4 Homework –Chapter 23, exercises 1, 6, 14, 19 –Do them in order. Do NOT read ahead.
Read Like a Writer. 1. Ideas Ideas are the heart of the piece — what the writer is writing about and the information her or she chooses to reveal about.
11 CS 388: Natural Language Processing: Syntactic Parsing Raymond J. Mooney University of Texas at Austin.
ELN – Natural Language Processing Giuseppe Attardi
Richard Socher Cliff Chiung-Yu Lin Andrew Y. Ng Christopher D. Manning
For Friday Finish chapter 23 Homework: –Chapter 22, exercise 9.
GLOSSARY COMPILATION Alex Kotov (akotov2) Hanna Zhong (hzhong) Hoa Nguyen (hnguyen4) Zhenyu Yang (zyang2)
Introduction to Text and Web Mining. I. Text Mining is part of our lives.
10/12/2015CPSC503 Winter CPSC 503 Computational Linguistics Lecture 10 Giuseppe Carenini.
Ngoc Minh Le - ePi Technology Bich Ngoc Do – ePi Technology
CS774. Markov Random Field : Theory and Application Lecture 19 Kyomin Jung KAIST Nov
11 Chapter 14 Part 1 Statistical Parsing Based on slides by Ray Mooney.
Natural language processing tools Lê Đức Trọng 1.
Using a Named Entity Tagger to Generalise Surface Matching Text Patterns for Question Answering Mark A. Greenwood and Robert Gaizauskas Natural Language.
For Friday Finish chapter 23 Homework –Chapter 23, exercise 15.
Tools for Linguistic Analysis. Overview of Linguistic Tools  Dictionaries  Linguistic Inquiry and Word Count (LIWC) Linguistic Inquiry and Word Count.
Correcting Comma Errors in Learner Essays, and Restoring Commas in Newswire Text Ross Israel Indiana University Joel Tetreault Educational Testing Service.
Overview of Statistical NLP IR Group Meeting March 7, 2006.
LING/C SC 581: Advanced Computational Linguistics Lecture Notes Feb 3 rd.
Writing an Essay. The Academic Essay The academic essay is composed of 3 parts: introduction, body, and conclusion. Why? To communicate your position.
 What’s going on here?  There’s no way to know for sure what goes on in a reader’s head. And every reader probably reads a little differently. This.
Language Identification and Part-of-Speech Tagging
If: expressing different scenarios through language
Natural Language Processing [05 hours/week, 09 Credits] [Theory]
Writing Inspirations, 2017 Aalto University
English-Korean Machine Translation System
PRESENTED BY: PEAR A BHUIYAN
Lecture – VIII Monojit Choudhury RS, CSE, IIT Kharagpur
Statistical NLP: Lecture 3
Basic Parsing with Context Free Grammars Chapter 13
Natural Language Processing (NLP)
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 27
GCSE English Week 5.
Improving a Pipeline Architecture for Shallow Discourse Parsing
University of Computer Studies, Mandalay
LING/C SC/PSYC 438/538 Lecture 21 Sandiway Fong.
LING/C SC/PSYC 438/538 Lecture 20 Sandiway Fong.
LING 388: Computers and Language
Text Analytics Giuseppe Attardi Università di Pisa
Machine Learning in Natural Language Processing
CS 388: Natural Language Processing: Syntactic Parsing
Writing Analytics Clayton Clemens Vive Kumar.
LING/C SC 581: Advanced Computational Linguistics
Quanzeng You, Jiebo Luo, Hailin Jin and Jianchao Yang
Stanford CoreNLP
Core Concepts Lecture 1 Lexical Frequency.
Watch the following clip from the film “Independence Day”, as you watch jot down notes on the following questions… Speaker- Who is the speaker? Subject-What.
FIRST SEMESTER GRAMMAR
WAT: GENERAL.
LING/C SC/PSYC 438/538 Lecture 23 Sandiway Fong.
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 26
Text Mining & Natural Language Processing
Natural Language Processing
Linguistic Essentials
Text Mining & Natural Language Processing
Natural Language Processing
Identrics – Team Vistula
PURE Learning Plan Richard Lee, James Chen,.
Natural Language Processing (NLP)
CS224N Section 3: Corpora, etc.
Print the Past Worksheets
Preposition error correction using Graph Convolutional Networks
CS224N Section 3: Project,Corpora
Neural Joint Model for Transition-based Chinese Syntactic Analysis
The Winograd Schema Challenge Hector J. Levesque AAAI, 2011
Artificial Intelligence 2004 Speech & Natural Language Processing
Natural Language Processing (NLP)
Presentation transcript:

Google SyntaxNet “Parsey McParseface and other SyntaxNet models are some of the most complex networks that we have trained with the TensorFlow framework at Google.” Quote from: https://www.tensorflow.org/versions/r0.9/tutorials/syntaxnet/index.html And https://research.googleblog.com/2016/05/announcing-syntaxnet-worlds-most.html Globally Normalized Transition-Based Neural Networks https://arxiv.org/pdf/1603.06042v2.pdf

Highlights Neural Net NLP framework for TensorFlow Pretrained Parsey McParseface parser Trained using old English newswire stories 20 year old Penn Treebank Wall Street Journal Speak Over 94% accuracy & > 600 words/second spaCy: 92.4% at 15k words per second linguists trained for the task agree 96-97% of the cases Parsey has cousins now! Thanks to open source, 40+ languages Drill Bit: POS + Dependency Parsing Parsey’s cousins: https://github.com/tensorflow/models/blob/master/syntaxnet/universal.md

Picture and caption from: http://www. dailymail. co

What SyntaxNet does not do Coreference Resolution Named-entity recognition (NER) Sentiment Analysis Many other things 

Coreference Resolution From: http://nlp.stanford.edu/projects/coref.shtml

Named-entity recognition From: https://en.wikipedia.org/wiki/Named-entity_recognition

Sentiment Analysis https://en.wikipedia.org/wiki/Sentiment_analysis Generally speaking, sentiment analysis aims to determine the attitude of a speaker or a writer with respect to some topic or the overall contextual polarity of a document. The attitude may be his or her judgment or evaluation (see appraisal theory), affective state (that is to say, the emotional state of the author when writing), or the intended emotional communication (that is to say, the emotional effect the author wishes to have on the reader). Could consider demoing: https://foxtype.com/politeness (Chocolate is the very best and amazing)

What SyntaxNet does Syntactic Parser Part-of-speech (POS) tagging Dependency Parsing

Why gramm[ae]r stinks as "Those buffalo(es) from Buffalo that are intimidated by buffalo(es) from Buffalo intimidate buffalo(es) from Buffalo."[1] From: https://en.wikipedia.org/wiki/Buffalo_buffalo_Buffalo_buffalo_buffalo_buffalo_Buffalo_buffalo and https://upload.wikimedia.org/wikipedia/commons/2/2c/Buffalo_buffalo_WikiWorld.png The sentence uses three distinct meanings of the word buffalo: the city of Buffalo, New York; the uncommon verb to buffalo, meaning "to bully, harass,or intimidate" or "to baffle"; and the animal, bison (often called buffalo in North America). The sentence can be phrased differently as "Those buffalo(es) from Buffalo that are intimidated by buffalo(es) from Buffalo intimidate buffalo(es) from Buffalo."[1]

Part-of-speech (POS) tagging From: https://github.com/tensorflow/models/tree/master/syntaxnet#installation This sentence is composed of words: strings of characters that are segmented into groups (e.g. "I", "saw", etc.) Each word in the sentence has a grammatical function that can be useful for understanding the meaning of language. For example, "saw" in this example is a past tense of the verb "to see". But any given word might have different meanings in different contexts: "saw" could just as well be a noun (e.g., a saw used for cutting) or a present tense verb (using a saw to cut something).

From: https://www. google. com/url

POS + Dependency Parsing From: https://github.com/tensorflow/models/tree/master/syntaxnet#installation This sentence is composed of words: strings of characters that are segmented into groups (e.g. "I", "saw", etc.) Each word in the sentence has a grammatical function that can be useful for understanding the meaning of language. For example, "saw" in this example is a past tense of the verb "to see". But any given word might have different meanings in different contexts: "saw" could just as well be a noun (e.g., a saw used for cutting) or a present tense verb (using a saw to cut something).

Stanford typed dependencies (http://nlp. stanford From: http://nlp.stanford.edu/software/dependencies_manual.pdf

Grammars Slide directly taken from Berkeley slides: https://bcourses.berkeley.edu/courses/1267848/files/50935030/download?verifier=qPVn1u6pa0LKopYB6n7daB9KX9stNJxCWnwM7oBh&wrap=1 Quote: ‘The reconstruction of a sequence of grammar productions from a sentence is called “parsing” the sentence…… It is most conveniently represented as a tree….. The parser then tries to find the most likely sequence of productions that generate the given sentence’

One of the main problems that makes parsing so challenging is that human languages show remarkable levels of ambiguity. It is not uncommon for moderate length sentences - say 20 or 30 words in length - to have hundreds, thousands, or even tens of thousands of possible syntactic structures. A natural language parser must somehow search through all of these alternatives, and find the most plausible structure given the context. From: https://research.googleblog.com/2016/05/announcing-syntaxnet-worlds-most.html e.g. Alice drove down the street in her car has at least two possible dependency parses:

From: http://brnrd.me/google-syntaxnet-sentiment-analysis/

From: https://explosion.ai/blog/syntaxnet-in-context

Installation Runs on top of TensorFlow Python 2.7 Package manager: pip/brew Build tool: Bazel, Mock (unit testing) Other: Swig (script bindings), protobuf (serializing data), asciitree (for drawing parse trees)

POS + Dependency Parsing Default From: https://github.com/tensorflow/models/tree/master/syntaxnet#installation This sentence is composed of words: strings of characters that are segmented into groups (e.g. "I", "saw", etc.) Each word in the sentence has a grammatical function that can be useful for understanding the meaning of language. For example, "saw" in this example is a past tense of the verb "to see". But any given word might have different meanings in different contexts: "saw" could just as well be a noun (e.g., a saw used for cutting) or a present tense verb (using a saw to cut something). ConLL

Training the SyntaxNet POS Tagger From: https://github.com/tensorflow/models/tree/master/syntaxnet#installation

Transition-Based Parsing + Beam Search Paper: https://arxiv.org/pdf/1603.06042v2.pdf Garden path sentence: "The old man the boat".

Backup

it is critical to tightly integrate learning and search in order to achieve the highest prediction accuracy https://www.quora.com/Whats-the-difference-between-Machine-Learning-AI-and-NLP

Phrase structure grammar From: https://en.wikipedia.org/wiki/Phrase_structure_grammar

Other links Other: https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=2&ved=0ahUKEwiN8J7knuXPAhXGHD4KHWMuDGwQFggjMAE&url=https%3A%2F%2Fcourses.cs.washington.edu%2Fcourses%2Fcse454%2F09sp%2Fslides%2F07-posparsing.pptx&usg=AFQjCNGTy5Nr7tiEZ5HIKC3o-uSrRbSkIA&sig2=17Ok_q1lhrnjQP-HPg5HWw&bvm=bv.135974163,d.cWw