text to text generation
play

Text-to-Text Generation Katja Filippova katjaf@google.com Friday, - PowerPoint PPT Presentation

Sep 04, 2022 •736 likes •1.95k views

Text-to-Text Generation Katja Filippova katjaf@google.com Friday, August 19, 2011 1 This course A quick overview of a number of topics under the umbrella term text-to-text generation. Research problems - what is being done and

  1. i. Paraphrasing: How? ● Monolingual parallel corpus. ● Machine learning-based approach (Barzilay & McKeown, 2001): ● Data - multiple fiction translations: Emma burst into tears and he tried to comfort her. Emma cried and he tried to console her. (“ Madame Bovary” ) ● Extract pairs which are positive+ ( <he, he>, <tried, tried> ) and negative- ( <he, tried>, <Emma, console> ) examples. ● For every pair, extract contextual features. ● Feature strength is the MLE - |f|+ / (|f|+ + |f|-). ● Find more paraphrases, update weights, repeat. RUSSIR - August 2011 Friday, August 19, 2011 23

  2. i. Paraphrasing: How? ● Pang, Knight & Marcu 2003: ● Align constituency trees of parallel sentences. S S NP VP NP VP PRP V PRP V PP Emma cried Emma burst PREP NP into NN tears RUSSIR - August 2011 Friday, August 19, 2011 24

  3. i. Paraphrasing: How? ● Quirk, Brockett & Dolan 2004: ● Use the standard SMT formula, E* = arg max p(E* | E) = arg max p(E*) p(E | E*) ● 140K “parallel” sentences obtained from online news (articles about the same event, edit distance to discard sentences which cannot be paraphrases). ● Paraphrasal pairs are extracted with associated probabilities. ● Given a sentence, a lattice of possible paraphrases is constructed and dynamic programming is used to find the best scoring paraphrase. RUSSIR - August 2011 Friday, August 19, 2011 25

  4. i. Paraphrasing: How? ● Parallel corpora are rare, comparable corpora are abundant. ● Shinyama et al. 2002: ● News articles from two sources which appeared on the same day. ● Similar articles are paired. ● Preprocessing: dependency parse trees, NE recognition. ● NEs are replaced with generic slots. ● Patterns pointing to the same NEs are taken as paraphrases. RUSSIR - August 2011 Friday, August 19, 2011 26

  5. i. Paraphrasing: How? ● Barzilay & Lee 2003: ● Two news agencies, the same period of time. ● Similar sentences (sharing many ngrams) are clustered. ● Multiple sequence alignment which results into a slotted word lattice. ● Backbone nodes are identified (shared by >50% of sentences) as points of commonality. ● Variability signals argument slots. ● Given a new sentence, a suitable cluster needs to be found before a paraphrase can be generated (there might be no such cluster). RUSSIR - August 2011 Friday, August 19, 2011 27

  6. i. Paraphrasing: How? ● Use of Synchronous and Quasi-synchronous Grammars. (these pictures are stolen from the presentation of Noah Smith at T2T workshop, ACL’11) RUSSIR - August 2011 Friday, August 19, 2011 28

  7. i. Paraphrasing: How? ● Synchronous grammars: ● define pairs of rules, e.g., for German and English: (VP; VP) -> (V NP; NP V) ● can be probabilistic (compare with PCFGs). ● does not have to be constituency syntax, e.g., TAG and logical forms (Shieber & Shabes, 1990). ● have been used for MT and also for getting paraphrase grammars. RUSSIR - August 2011 Friday, August 19, 2011 29

  8. i. Paraphrasing: How? ● Quasi-synchronous grammars (Smith & Eisner, 2006): ● were introduced for MT. ● the output sentence is “inspired” by the source sentence, not determined. ● again, does not have to be constituency syntax, e.g., dependency representation. ● have been used for other text-to-text generation tasks, like text simplification (Woodsend & Lapata, 2011) or question generation (Wang et al. 2007). RUSSIR - August 2011 Friday, August 19, 2011 30

  9. i. Paraphrasing Questions? RUSSIR - August 2011 Friday, August 19, 2011 31

  10. ii. Sentence compression ● Simple and intuitive idea which is to shorten a long sentence preserving the main points and removing less relevant information. RUSSIR - August 2011 Friday, August 19, 2011 32

  11. ii. Sentence compression ● Simple and intuitive idea which is to shorten a long sentence preserving the main points and removing less relevant information. Simple and intuitive idea which is to shorten a long sentence preserving the main points and removing less relevant information. RUSSIR - August 2011 Friday, August 19, 2011 32

  12. ii. Sentence compression ● Simple and intuitive idea which is to shorten a long sentence preserving the main points and removing less relevant information. Simple and intuitive idea which is to shorten a long sentence preserving the main points and removing less relevant information. RUSSIR - August 2011 Friday, August 19, 2011 32

  13. ii. Sentence compression ● Simple and intuitive idea which is to shorten a long sentence preserving the main points and removing less relevant information. Simple and intuitive idea which is to shorten a long sentence preserving the main points and removing less relevant information. deletion (substitution reordering) RUSSIR - August 2011 Friday, August 19, 2011 32

  14. ii. Sentence compression ● Rule-based approaches rely on PoS annotations and syntactic structures and remove constituents/ dependencies likely to be less important (Grefenstette 1998, Corston-Oliver&Dolan 1999): ● relative clauses, prepositional phrases ● proper nouns > common nouns > adjectives ● Further sources of information can be used, e.g., a subcategorization lexicon (Jing 2000): give(Subj, AccObj, DatObj) On Friday, Ann gave Bill a book. RUSSIR - August 2011 Friday, August 19, 2011 33

  15. ii. Sentence compression ● Rules can be induced from a corpus of compressions (Dorr et al. 2003, Gagnon & DaSilva 2005): ● what kind of PPs are removed, ● what are the PoS, syntactic features of the removed constituents, ● look at a manually crafted corpus or at a corpus of news headlines (compare the length of headlines with the average sentence length). ● Supervised approaches learn what is “removable” without direct human intervention. RUSSIR - August 2011 Friday, August 19, 2011 34

  16. ii. Sentence compression ● Knight & Marcu 2002 use the noisy-channel model : p(y|x) = p(x,y)/p(x) = p(x|y)p(y)/p(x) ● Bayes rule: p(y|x) ~ p(x|y)p(y) ● Look for y maximizing y = arg max p(x|y) p(y) RUSSIR - August 2011 Friday, August 19, 2011 35

  17. ii. Sentence compression ● Knight & Marcu 2002 use the noisy-channel model : p(y|x) = p(x,y)/p(x) = p(x|y)p(y)/p(x) ● Bayes rule: p(y|x) ~ p(x|y)p(y) ● Look for y maximizing y = arg max p(x|y) p(y) MT: f = arg max p(e|f) p(f) RUSSIR - August 2011 Friday, August 19, 2011 35

  18. ii. Sentence compression ● Knight & Marcu 2002 use the noisy-channel model : p(y|x) = p(x,y)/p(x) = p(x|y)p(y)/p(x) ● Bayes rule: p(y|x) ~ p(x|y)p(y) ● Look for y maximizing y = arg max p(x|y) p(y) MT: f = arg max p(e|f) p(f) Q3: Why “split” into two things? RUSSIR - August 2011 Friday, August 19, 2011 35

  19. ii. Sentence compression ● Knight & Marcu 2002 use the noisy-channel model : p(y|x) = p(x,y)/p(x) = p(x|y)p(y)/p(x) ● Bayes rule: p(y|x) ~ p(x|y)p(y) ● Look for y maximizing y = arg max p(x|y) p(y) MT: f = arg max p(e|f) p(f) Q3: Why “split” into two things? SC: s = arg max p(s|l) p(s) RUSSIR - August 2011 Friday, August 19, 2011 35

  20. ii. Sentence compression ● What is p(s) supposed to do? ● assign low probability to ungrammatical, “strange” sentences. ● How to estimate p(s)? E.g., with a n-gram model from a corpus of (compressed) sentences. ● What is p(l|s) supposed to do? ● assign low probability to compressions which have little to do with the input, ● assign very low probability to compressions which flip the meaning (e.g., delete not ). ● How to estimate p(l|s)? RUSSIR - August 2011 Friday, August 19, 2011 36

  21. ii. Sentence compression ● Knight & Marcu 2002 look at constituency trees (CFG): s = S ( NP (John) VP (VB (saw) NP (Mary))) ~p(s) = p(S-NP VP|S) p(NP-John|NP) p(VP-VB NP|VP) p(VB-saw|VB) p(NP-Mary|NP) p(John|eos) p(saw|John) p(Mary|saw) p(eos|Mary) Q4: How can these probabilities be acquired? RUSSIR - August 2011 Friday, August 19, 2011 37

  22. ii. Sentence compression ● Given a corpus (Ziff-Davis) K&M want to learn probabilities of the expansion rules. ● parse the long and the short sentence, ● align the parse trees (not always possible, the model cannot deal with that problem), ● do maximum likelihood estimation of rules like the following: p(VP-VB NP PP | VP-VB NP) Q5: What does this rule express? ● Only 1.8% of the data can be used because the model assumes that the compressions are subsequences of the original sentences. RUSSIR - August 2011 Friday, August 19, 2011 38

  23. ii. Sentence compression ● (K&M contd.) Recall: s = arg max p(s|l) p(s) ● for every s we know how to estimate ● p(s) ● p(s|l) ● the search for the best s is called decoding, not covered here. RUSSIR - August 2011 Friday, August 19, 2011 39

  24. ii. Sentence compression ● A corpus of parsed sentence pairs (long sentence / compression) can be used in other ways. ● Nguyen et al. 2004 use Support Vector Machines (SVM) and syntactic, semantic (e.g., NE type) and other features to determine the sequence of rewriting actions (shift, reduce, drop, assign type, restore). [Similar to the shift-reduce parsing approach of Nivre, 2003+.] RUSSIR - August 2011 Friday, August 19, 2011 40

  25. ii. Sentence compression ● Galley & McKeown 2007 also use pairs of parsed trees but do not break down the probability into two terms. ● They look for s = arg max p(s, l) Q6: Can you explain where this formula comes from? ● Consider all possible tree pairs for s and l , then ● G&McK also use the synchronous grammar approach. RUSSIR - August 2011 Friday, August 19, 2011 41

  26. ii. Sentence compression ● Clarke&Lapata (2006, 2007) do not rely on labeled data at all (good news). A word deletion model. ● Constraints to ensure grammaticality: ● “if main verb, then subject” ● “if preposition, then its object” ● Discourse constraints (lexical chains) to promote words related to the main topic. ● They also introduced corpora (written and broadcast news) which can be used to test any system. RUSSIR - August 2011 Friday, August 19, 2011 42

  27. ii. Sentence compression ● The objective function to maximize is, essentially, a linear combination of the trigram score of the compression and the informativeness of single words. ● x_ijk represents a trigram, y_i represents a single word. ● This objective function is subject to a variety of grammar and discourse constraint on the variables. ● The (approximate) solution is found with Integer Linear Programming (ILP). RUSSIR - August 2011 Friday, August 19, 2011 43

  28. ii. Sentence compression ● What is linear programming? maximizing/minimizing a linear combination of a finite number of variables which are subject to constraints. ● Binary integer programming - all variables are 0 or 1. You can think of it as a way to select from a given set given constraints on how elements in the set can be combined. RUSSIR - August 2011 Friday, August 19, 2011 44

  29. ii. Sentence compression ● An example of a grammar constraint: y_i - y_j >= 0 if w_j modifies w_ i. ● An example of a discourse constraint: y_i = 1, if w_i belongs to a lexical chain . ● Other discourse constraints are based on the Centering theory. RUSSIR - August 2011 Friday, August 19, 2011 45

  30. ii. Sentence compression ● An example of a grammar constraint: y_i - y_j >= 0 if w_j modifies w_ i. ● An example of a discourse constraint: y_i = 1, if w_i belongs to a lexical chain . ● Other discourse constraints are based on the Centering theory. RUSSIR - August 2011 Friday, August 19, 2011 45

  31. ii. Sentence compression ● An example of a grammar constraint: y_i - y_j >= 0 if w_j modifies w_ i. ● An example of a discourse constraint: y_i = 1, if w_i belongs to a lexical chain . ● Other discourse constraints are based on the Centering theory. RUSSIR - August 2011 Friday, August 19, 2011 45

  32. ii. Sentence compression ● Evaluation: ● intrinsic - dependency parse score (Riezler et al. 2003): How similar are the dependency trees of the two compressions (“gold” = created by a human, and the one the system produced). The larger the overlap in dependencies, the better. ● extrinsic - in the context of a QA task: Given a compressed document and a number of questions about the document, can human readers answer those questions? (The questions were generated by other humans who were given uncompressed documents.) RUSSIR - August 2011 Friday, August 19, 2011 46

  33. ii. Sentence compression Questions? RUSSIR - August 2011 Friday, August 19, 2011 47

  34. iii. Sentence fusion ● How about cases where we have several sentences as input - the multi-document summarization scenario? What can we do with them if they are somewhat similar? ● Compression is helpful if we are doing single-document summarization - we can compress every sentence we want to add to the summary, one by one. ● In case of MDS, one usually first clusters all the sentences, then ranks those clusters, then selects a sentence from each of the top N clusters. RUSSIR - August 2011 Friday, August 19, 2011 48

  35. iii. Sentence fusion ● Extractive approach: ● Similar sentences are clustered. ● Clusters are ranked. ● A sentence is selected from each of the top clusters. RUSSIR - August 2011 Friday, August 19, 2011 49

  36. iii. Sentence fusion ● “Fuse” several related sentences into one (Barzilay & McKeown, 2005) ● Setting: multi-document, generic news summarization. Idea: recurrent information is important. RUSSIR - August 2011 Friday, August 19, 2011 50

  37. iii. Sentence fusion ● “Fuse” several related sentences into one (Barzilay & McKeown, 2005) ● Setting: multi-document, generic news summarization. Idea: recurrent information is important. RUSSIR - August 2011 Friday, August 19, 2011 50

  38. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 51

  39. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 52

  40. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 52

  41. iii. Sentence fusion ● pairwise recursive bottom-up tree alignment ● each alignment has a score - the more similar two trees are, the higher the score ● from the alignment score the basis tree is determined ● it is the basis tree around which the fusion is performed RUSSIR - August 2011 Friday, August 19, 2011 53

  42. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 54

  43. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 54

  44. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 54

  45. iii. Sentence fusion ● Now we have a dependency graph expressing the recurrent content from the input. “Overgenerate-and-rank” approach: consider up to 20K possible strings and rank them with a language model. RUSSIR - August 2011 Friday, August 19, 2011 55

  46. iii. Sentence fusion ● Now we have a dependency graph expressing the recurrent content from the input. Q6: How can we get a sentence? “Overgenerate-and-rank” approach: consider up to 20K possible strings and rank them with a language model. RUSSIR - August 2011 Friday, August 19, 2011 55

  47. iii. Sentence fusion ● The fusion model of Barzilay & McKeown does intersection fusion - it relies on the idea that recurrent = important, the fused sentences express the content shared among many sentences. ● We can think of it as multi-sentence compression . ● Can we do without dependency representations? Let’s consider a word graph where edges represent adjacency relation (Filippova 2010). RUSSIR - August 2011 Friday, August 19, 2011 56

  48. iii. Sentence fusion ● Hillary Clinton paid a visit to the People’s Republic of China on Monday. ● Hilary Clinton wanted to visit China last month but postponed her plans till Monday last week. ● The wife of a former U.S. president Bill Clinton Hillary Clinton visited China last Monday. ● Last week the Secretary of State Ms. Clinton visited Chinese officials. RUSSIR - August 2011 Friday, August 19, 2011 57

  49. iii. Sentence fusion (1) but postponed her plans RUSSIR - August 2011 Friday, August 19, 2011 58

  50. iii. Sentence fusion ● Words from a new sentence are added in three steps: ● unambiguous non-stopwords - either merged with a word- node in the graph, or a new word-node is created; ● ambiguous non-stopwords - select the word-node with some overlap in neighbors (i.e., previous-following words in the sentence and neighbors in the graph); ● stopwords - only merged with an existing word-node if the following word in the sentence matches an out-neighbor in the graph, otherwise a new word-node is created. ● Words from the same sentence are never merged in one node. RUSSIR - August 2011 Friday, August 19, 2011 59

  51. iii. Sentence fusion (1) but postponed her plans RUSSIR - August 2011 Friday, August 19, 2011 60

  52. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 61

  53. iii. Sentence fusion ● Idea: good compressions - salient and short paths from Start to End. ● Edge weight can be defined as: RUSSIR - August 2011 Friday, August 19, 2011 62

  54. iii. Sentence fusion ● How about we are not going for the recurrent information but want to combine complementary content? That is, we are interested not intersection but union fusion (Krahmer & Marsi, 2008). ● Can we abstract to a non-redundant representation of all the content expressed in the input? (which is a set of related sentences). ● First, can we make the dependency representation a bit more semantic? RUSSIR - August 2011 Friday, August 19, 2011 63

  55. iii. Sentence fusion visited subj advmod obj student Oxford recently det pp conj of a of and prep cj John Cambridge app Smith RUSSIR - August 2011 Friday, August 19, 2011 64

  56. iii. Sentence fusion visited subj advmod obj student Oxford recently det pp conj of a of and prep cj John Cambridge app Smith RUSSIR - August 2011 Friday, August 19, 2011 64

  57. iii. Sentence fusion visited subj advmod obj student Oxford recently det conj a and cj John Cambridge app Smith RUSSIR - August 2011 Friday, August 19, 2011 64

  58. iii. Sentence fusion visited subj advmod obj student Oxford recently det conj of a and cj John Cambridge app Smith RUSSIR - August 2011 Friday, August 19, 2011 64

  59. iii. Sentence fusion visited subj advmod obj student Oxford recently det of a John app Smith RUSSIR - August 2011 Friday, August 19, 2011 64

  60. iii. Sentence fusion Cambridge obj visited subj advmod obj student Oxford recently det of a John app Smith RUSSIR - August 2011 Friday, August 19, 2011 64

  61. iii. Sentence fusion Cambridge obj visited subj advmod obj student Oxford recently of John app Smith RUSSIR - August 2011 Friday, August 19, 2011 64

  62. iii. Sentence fusion root Cambridge obj visited subj advmod obj student Oxford recently of John app Smith RUSSIR - August 2011 Friday, August 19, 2011 64

  63. iii. Sentence fusion ● Given such modified dependency representations of related sentences, join them in a single DAG by merging identical words, synonyms (e.g., WordNet) and entities (you can use Freebase, NE, coreference resolution). ● The resulting DAG covers all the input trees. ● Multiple dependency trees can be extracted from it, very few make sense. ● How can we find the best dependency tree? ● How can we find a valid / grammatical dependency tree? RUSSIR - August 2011 Friday, August 19, 2011 65

  64. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 66

  65. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 66

  66. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 66

  67. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 66

  68. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 66

  69. iii. Sentence fusion RUSSIR - August 2011 Friday, August 19, 2011 66

  70. iii. Sentence fusion ● We can use ILP to obtain grammatical and informative trees: ● for every edge, introduce a binary variable; ● structural constraints to get a tree and not a random set of edges; ● we can add syntactic, semantic, discourse constraints. ● But what are edge weights? Which edges are more important? p(label | lex-head) as a measure of syntactic importance, MLEstimated. ● no need to use lexicons or rules like in previous work; ● all is needed is a parsed corpus. RUSSIR - August 2011 Friday, August 19, 2011 67

  71. iii. Sentence fusion ● Examples of semantic constraints: ● do not retain take more than one edge from the same parent with the same label if the dependents are in ISA relation. visited obja Cambridge obja obja Oxford England ● do not retain two edges from the same head and with the same label if the lexical similarity between dependents is low: “ studies with pleasure and Niels Bohr” , sim(pleasure, N.B) = 0.01. RUSSIR - August 2011 Friday, August 19, 2011 68

  72. iii. Sentence fusion ● Examples of semantic constraints: ● do not retain take more than one edge from the same parent with the same label if the dependents are in ISA relation. visited obja Cambridge obja obja Oxford England ● do not retain two edges from the same head and with the same label if the lexical similarity between dependents is low: “ studies with pleasure and Niels Bohr” , sim(pleasure, N.B) = 0.01. RUSSIR - August 2011 Friday, August 19, 2011 68

  73. iii. Sentence fusion ● What we have at this point is a dependency tree which still needs to be linearized - converted into a sentence, a string of words in a correct order. ● we can overgenerate and rank again, ● we can use a more efficient method ... [not presented here]. ● A bonus: we can use the exact same method for sentence compression! [results comparable with state- of-the-art models on the mentioned datasets from C&L.] RUSSIR - August 2011 Friday, August 19, 2011 69

Recommend

GANocracy Outline Background: Text Generation Latent-Variable Generation Learning

GANocracy Outline Background: Text Generation Latent-Variable Generation Learning

Controlling Text Generation Alexander Rush (and Sam Wiseman) Harvard / Cornell Tech GANocracy Outline Background: Text Generation Latent-Variable Generation Learning Neural Templates Machine Learning for Text Generation y 1: T =

710 views • 55 slides
Text-to-Image Generation Yu Cheng Text-to-Image Synthesis Text-to-Image Synthesis

Text-to-Image Generation Yu Cheng Text-to-Image Synthesis Text-to-Image Synthesis

Text-to-Image Generation Yu Cheng Text-to-Image Synthesis Text-to-Image Synthesis StackGAN, AttnGAN, TAGAN, ObjGAN Text-to-Video Synthesis GAN-based methods, VAE-based methods, StoryGAN Dialogue-based Image Synthesis

827 views • 45 slides
Unsupervised Machine Translation Sachin Kumar Conditional Text Generation Generate text

Unsupervised Machine Translation Sachin Kumar Conditional Text Generation Generate text

CMU CS11-737: Multilingual NLP (Fall 2020) Unsupervised Machine Translation Sachin Kumar Conditional Text Generation Generate text according to a specification: P(Y|X) Input X Output Y (Text) Task English Hindi Machine Translation

743 views • 35 slides
Title of an article [16 pt] Introduction [14 pt] Text. Text. Text. Text. Text. Text. Text. Text.

Title of an article [16 pt] Introduction [14 pt] Text. Text. Text. Text. Text. Text. Text. Text.

REQUIREMENTS FOR POSTER PRESENTATION 1. Volume of poster presentation (or Article) from 4 to 10 pages (A4 format). Please submit an electronic version by email. Along with the article must be submitted a review of a scientist . A review

71 views • 3 slides
From Text Message to Research Paper: Teaching the Text Message Generation Heidi Wright Ohio

From Text Message to Research Paper: Teaching the Text Message Generation Heidi Wright Ohio

From Text Message to Research Paper: Teaching the Text Message Generation Heidi Wright Ohio State University Introduction and Organization Origins- SIUC 2006 Increased number of tasks and shorter time frame Insufficient background

241 views • 22 slides
Parsing Eric McCreath Overview In this lecture we will look at: structured text, generation,

Parsing Eric McCreath Overview In this lecture we will look at: structured text, generation,

Parsing Eric McCreath Overview In this lecture we will look at: structured text, generation, parsing, tokens, grammars, and writing a simple parser. 2 Structured Text Information is often stored in text files. Also we often provide

522 views • 13 slides
Statistical Perspectives on Text-to-Text Generation Noah Smith Language Technologies Institute

Statistical Perspectives on Text-to-Text Generation Noah Smith Language Technologies Institute

Statistical Perspectives on Text-to-Text Generation Noah Smith Language Technologies Institute Machine Learning Department School of Computer Science Carnegie Mellon University nasmith@cs.cmu.edu Im A Learning Guy I use statistics for

1.2k views • 82 slides
11-830 Computational Ethics for NLP Ethical Concerns on OpenAI Text Generation System Discussion

11-830 Computational Ethics for NLP Ethical Concerns on OpenAI Text Generation System Discussion

11-830 Computational Ethics for NLP Ethical Concerns on OpenAI Text Generation System Discussion OpenAI Text Generation System CNN: This AI is so good at writing that its creators wont let you use it Takes in a text prompt and

336 views • 8 slides
Text Text #ICANN51 Contractual Compliance Text Text Contractual Compliance Update

Text Text #ICANN51 Contractual Compliance Text Text Contractual Compliance Update

Text Text #ICANN51 Contractual Compliance Text Text Contractual Compliance Update Wednesday, 15 October 2014 #ICANN51 Agenda Text Text Learn More about Compliance Metrics Audit Program Update Registrar Related Update

847 views • 57 slides
Here is some test text Here is some test text Here is some test text By Mou Mount nt_Everes

Here is some test text Here is some test text Here is some test text By Mou Mount nt_Everes

Here is some test text Here is some test text Here is some test text By Mou Mount nt_Everes erest_as_see een_ n_fro rom_ m_Dru rukai air2. r2.jp jpg: g: shri rimpo mpo196 1967de 7deri rivat ative e wor work: : Papa pa Li

370 views • 32 slides
Text layout with Core Text Jjgod Jiang &lt;gzjjgod@gmail.com&gt; What is text layout? Convert a

Text layout with Core Text Jjgod Jiang &lt;gzjjgod@gmail.com&gt; What is text layout? Convert a

Text layout with Core Text Jjgod Jiang &lt;gzjjgod@gmail.com&gt; What is text layout? Convert a large piece of text into glyphs, and position them into correct place. Simple explanation: Width in, heights out. Input: text (in Unicode),

403 views • 38 slides
Non-Monotonic Sequential Text Generation Sean Welleck, Kiant Brantley, Hal Daum III,

Non-Monotonic Sequential Text Generation Sean Welleck, Kiant Brantley, Hal Daum III,

Non-Monotonic Sequential Text Generation Sean Welleck, Kiant Brantley, Hal Daum III, Kyunghyun Cho Sequential Text Generation Y = ( y 1 , y 2 , , y N ) ( hi , how , are , you , ? ) Sequential Text Generation Unconditional Y ( hi ,

459 views • 24 slides
Speech Generation From Concept and from Text Martin Jansche CS 6998 2004-02-11 Components of

Speech Generation From Concept and from Text Martin Jansche CS 6998 2004-02-11 Components of

Speech Generation From Concept and from Text Martin Jansche CS 6998 2004-02-11 Components of spoken output systems Front end: From input to control parameters. From naturally occurring text; or From constrained mark-up language; or

420 views • 27 slides
What is text alignment? Text alignment is the comparison of two or more parallel texts It

What is text alignment? Text alignment is the comparison of two or more parallel texts It

A tool for syntax-based intra-language text alignment Tariq Yousef, Chiara Palladino University of Leipzig Berlin Digital Classicist Seminars, November 29, 2016 What is text alignment? Text alignment is the comparison of two or more

688 views • 53 slides
Post-Conference Presentation Sunday Oladayo Oladejo Table of Content A Introduction B

Post-Conference Presentation Sunday Oladayo Oladejo Table of Content A Introduction B

Post-Conference Presentation Sunday Oladayo Oladejo Table of Content A Introduction B Benefits C Take-Aways D Research Areas Add text add text add text add text add text add text add text add text add text add text add text E Research

513 views • 12 slides
Enhanced Through the Gate &amp; Community Integration Service Text here Text here Text here

Enhanced Through the Gate &amp; Community Integration Service Text here Text here Text here

Enhanced Through the Gate &amp; Community Integration Service Text here Text here Text here Text here Text here Shelter Offender Services What we do In Offender Services we work with people who have been convicted of an offence and given a

301 views • 12 slides
Text Text #ICANN50 Contractual Compliance Text Text GNSO Council Meeting Wednesday, Jun 25

Text Text #ICANN50 Contractual Compliance Text Text GNSO Council Meeting Wednesday, Jun 25

Text Text #ICANN50 Contractual Compliance Text Text GNSO Council Meeting Wednesday, Jun 25 2014 #ICANN50 Objective Text Text To provide an update to the GNSO council on the Contractual Compliance efforts regarding 20130516-1 Address

675 views • 56 slides
Text Generation with Exemplar-based Adaptive Decoding Hao Peng, Ankur Parikh, Manaal Faruqui,

Text Generation with Exemplar-based Adaptive Decoding Hao Peng, Ankur Parikh, Manaal Faruqui,

Text Generation with Exemplar-based Adaptive Decoding Hao Peng, Ankur Parikh, Manaal Faruqui, Bhuwan Dhingra, Dipanjan Das @NAACL June 4, 2019 Outline Background and Overview Adaptive Decoding Experiments Conditioned Text Generation

652 views • 49 slides
5. Text CHAPTER HIGHLIGHTS Text tradition. Codes for computer text. C d f t t t

5. Text CHAPTER HIGHLIGHTS Text tradition. Codes for computer text. C d f t t t

10/12/2016 CHAPTER 5. Text CHAPTER HIGHLIGHTS Text tradition. Codes for computer text. C d f t t t Font technologies. Multimedia text. Guidelines for use of text in multimedia. 2 1 10/12/2016 POWERS OF TEXT

597 views • 13 slides
The Son of God is Tempted Matthew 4:1-11 Here is some test text Here is some test text Here is

The Son of God is Tempted Matthew 4:1-11 Here is some test text Here is some test text Here is

Here is some test text Here is some test text Here is some test text The Son of God is Tempted Matthew 4:1-11 Here is some test text Here is some test text Here is some test text 1. Jesus is temped to gratify His desires apart from Gods

418 views • 15 slides
Text Text #ICANN51 15 October 2014 Text Text IDN Root Zone LGR Sarmad Hussain IDN Program

Text Text #ICANN51 15 October 2014 Text Text IDN Root Zone LGR Sarmad Hussain IDN Program

Text Text #ICANN51 15 October 2014 Text Text IDN Root Zone LGR Sarmad Hussain IDN Program Senior Manager #ICANN51 Agenda Text Text Introduction Sarmad Hussain Need, Limitations and Mechanisms for the Root Zone LGR Marc

817 views • 65 slides
Learning to generate: Concept-to-text generation using machine learning Ioannis Konstas

Learning to generate: Concept-to-text generation using machine learning Ioannis Konstas

Learning to generate: Concept-to-text generation using machine learning Ioannis Konstas Institute for Language, Cognition and Computation University of Edinburgh Aberdeen, NLG Summer School 21 July 2015 Konstas (ILCC) Concept-to-Text

1.83k views • 143 slides
The Handwriting of God Daniel 5 Here is some test text Here is some test text Here is some test

The Handwriting of God Daniel 5 Here is some test text Here is some test text Here is some test

Here is some test text Here is some test text Here is some test text The Handwriting of God Daniel 5 Here is some test text Here is some test text Here is some test text 1. God warns us not to trust the security of earthly kingdoms Here is

707 views • 39 slides
God Pursues Us with NEW LIFE Ezekiel 37:1-14 Here is some test text Here is some test text Here

God Pursues Us with NEW LIFE Ezekiel 37:1-14 Here is some test text Here is some test text Here

Here is some test text Here is some test text Here is some test text God Pursues Us with NEW LIFE Ezekiel 37:1-14 Here is some test text Here is some test text Here is some test text 1. Gods people are spiritually dead and scattered in

364 views • 25 slides

More recommend