About: Paragraph is a research topic. Over the lifetime, 3424 publications have been published within this topic receiving 48476 citations. The topic is also known as: subsection.
TL;DR: Paragraph Vector is an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents, and its construction gives the algorithm the potential to overcome the weaknesses of bag-of-words models.
Abstract: Many machine learning algorithms require the input to be represented as a fixed-length feature vector. When it comes to texts, one of the most common fixed-length features is bag-of-words. Despite their popularity, bag-of-words features have two major weaknesses: they lose the ordering of the words and they also ignore semantics of the words. For example, "powerful," "strong" and "Paris" are equally distant. In this paper, we propose Paragraph Vector, an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents. Our algorithm represents each document by a dense vector which is trained to predict words in the document. Its construction gives our algorithm the potential to overcome the weaknesses of bag-of-words models. Empirical results show that Paragraph Vectors outperforms bag-of-words models as well as other techniques for text representations. Finally, we achieve new state-of-the-art results on several text classification and sentiment analysis tasks.
TL;DR: The authors proposed paragraph vector, an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents, and achieved new state-of-the-art results on several text classification and sentiment analysis tasks.
Abstract: Many machine learning algorithms require the input to be represented as a fixed-length feature vector. When it comes to texts, one of the most common fixed-length features is bag-of-words. Despite their popularity, bag-of-words features have two major weaknesses: they lose the ordering of the words and they also ignore semantics of the words. For example, "powerful," "strong" and "Paris" are equally distant. In this paper, we propose Paragraph Vector, an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents. Our algorithm represents each document by a dense vector which is trained to predict words in the document. Its construction gives our algorithm the potential to overcome the weaknesses of bag-of-words models. Empirical results show that Paragraph Vectors outperform bag-of-words models as well as other techniques for text representations. Finally, we achieve new state-of-the-art results on several text classification and sentiment analysis tasks.
TL;DR: In this paper, a hierarchical RNN is proposed to generate one or multiple sentences to describe a realistic video, where a sentence generator produces one simple short sentence that describes a specific short video interval and a paragraph generator captures the inter-sentence dependency.
Abstract: We present an approach that exploits hierarchical Recurrent Neural Networks (RNNs) to tackle the video captioning problem, i.e., generating one or multiple sentences to describe a realistic video. Our hierarchical framework contains a sentence generator and a paragraph generator. The sentence generator produces one simple short sentence that describes a specific short video interval. It exploits both temporal-and spatial-attention mechanisms to selectively focus on visual elements during generation. The paragraph generator captures the inter-sentence dependency by taking as input the sentential embedding produced by the sentence generator, combining it with the paragraph history, and outputting the new initial state for the sentence generator. We evaluate our approach on two large-scale benchmark datasets: YouTubeClips and TACoS-MultiLevel. The experiments demonstrate that our approach significantly outperforms the current state-of-the-art methods with BLEU@4 scores 0.499 and 0.305 respectively.
TL;DR: This paper introduces an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph and evaluates the reconstructed paragraph using standard metrics to show that neural models are able to encode texts in a way that preserve syntactic, semantic, and discourse coherence.
Abstract: Natural language generation of coherent long texts like paragraphs or longer documents is a challenging problem for recurrent networks models. In this paper, we explore an important step toward this generation task: training an LSTM (Longshort term memory) auto-encoder to preserve and reconstruct multi-sentence paragraphs. We introduce an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph. We evaluate the reconstructed paragraph using standard metrics like ROUGE and Entity Grid, showing that neural models are able to encode texts in a way that preserve syntactic, semantic, and discourse coherence. While only a first step toward generating coherent text units from neural models, our work has the potential to significantly impact natural language generation and summarization1.
TL;DR: Using Parallel Structures and Fixing Sentence Problems Parallelism parallelism with Coordinators: And, Or, But Parallelism with Correlative (Paired) Conjunctions Sentence problems Sentence Fragments.
Abstract: PART I:WRITING A PARAGRAPH Chapter 1: Paragraph Structure The Three Parts of a Paragraph The Topic Sentence Position of Topic Sentences The Two Parts of a Topic Sentence Supporting Sentences The Concluding Sentence Review Writing Practice Chapter 2: Unity and Coherence Unity Coherence Repetition of Key Nouns Key Noun Substitutes Consistent Pronouns Transition Signals Logical Order Review Writing Practice Chapter 3: Supporting Details: Facts, Quotations, and Statistics Facts versus Opinions Using Outside Sources Plagiarism Citing Sources Quotations Direct Quotations Reporting Verbs and Phrases Punctuating Direct Quotations Indirect Quotations Writing Practice Statistics Writing Practice Review PART II:WRITING AN ESSAY Chapter 4: From Paragraph to Essay The Three Parts of an Essay The Introductory Paragraph Funnel Introduction Attention-Getting Introduction Thesis Statement Body Paragraphs Logical Division of Ideas Thesis Statements for Logical Division of Ideas Thesis Statement Pitfalls Transition Signals between Paragraphs The Concluding Paragraph Essay Outlining Review Writing Practice Applying What You Have Learned Reading Questions Suggestions for Discussion or Writing Chapter 5: Chronological Order: Process Essays Thesis Statements for a Process Essay Transition Signals for Chronological Order Review Writing Practice Applying What You Have Learned Reading1 Questions Suggestions for Discussion or Writing Reading2 Questions Suggestions for Discussion or Writing Chapter 6: Cause/Effect Essays Organization for Cause/Effect Order Block Organization Chain Organization Cause/Effect Signal Words and Phrases Cause Signal Words Effect Signal Words Review Writing Practice Applying What You Have Learned Reading Questions Suggestions for Discussion or Writing Chapter 7: Comparison/Contrast Essays Organization of Comparison/Contrast Essays Point-by-Point Organization Block Organization Comparison and Contrast Signal Words Comparison Signal Words Contrast Signal Words Review Writing Practice Applying What You Have Learned Reading Questions Suggestions for Discussion or Writing Chapter 8 Paraphrase and Summary Paraphrasing Plagiarism Using Paraphrases as Support Summarizing Review Chapter 9: Argumentative Essays Organization of Argumentative Essays The Introductory Paragraph Thesis Statement Review Writing Practice Applying What You Have Learned Topic 1, Reading 1 Questions Topic 1, Reading 2 Questions Topic 2, Reading 1 Questions Topic 2, Reading 2 Questions PART III: SENTENCE STRUCTURE Chapter 10: Types of Sentences Clauses Independent Clauses Dependent Clauses Kinds of Sentences Simple Sentence Compound Sentences Complex Sentences Compound-Complex Sentences Sentence Types and Writing Style Review Chapter 11: Using Parallel Structures and Fixing Sentence Problems Parallelism Parallelism with Coordinators: And, Or, But Parallelism with Correlative (Paired) Conjunctions Sentence Problems Sentence Fragments Choppy Sentences Run-On Sentences and Comma Splices Stringy Sentences Review Editing Practice Chapter 12: Noun Clauses That Clauses Sentences Beginning with It Special Verb Tenses in That Clauses If /Whether Clauses Question Clauses Review Editing Practice Writing Practice Chapter 13: Adverb Clauses Kinds of Adverb Clauses Punctuation of Adverb Clauses Time Clauses Place Clauses Distance, Frequency, and Manner Clauses Reason Clauses Result Clauses Purpose Clauses Contrast Clauses Direct Opposition Clauses Concession (Unexpected Result) Clauses Conditional Clauses Review Editing Practice Writing Practice Chapter 14: Adjective Clauses Relative Pronouns and Adverbs Position of Adjective Clauses Verb Agreement in Adjective Clauses Kinds of Adjective Clauses Relative Pronouns as Subjects Relative Pronouns as Objects Possessive Adjective Clauses Relative Pronouns as Objects of Prepositions Relative Pronouns in Phrases of Quantity and Quality Adjective Clauses of Time and Place Review Editing Practice Writing Practice Chapter 15: Participial Phrases Participles Participial Phrases Reduced Adjective Clauses Position and Punctuation of Participial Phrases General Form -ing Participial Phrases General Form -ed Participial Phrases Perfect Form Participial Phrases Participial Phrases and Writing Style Reduced Adverb Clauses Review Editing Practice Writing Practice Appendix A: The Process of Academic Writing The Writing Process, Step 1: Creating (Prewriting) The Writing Process, Step 2: Planning (Outlining) The Writing Process, Step 3: Writing The Writing Process, Step 4: Polishing Editing Practice Appendix B: Punctuation Rules Commas Semicolons Colons Quotation Marks Editing Practice Appendix C: Charts of Connecting Words and Transition Signals Coordinating Words Subordinating Words Conjunctive Adverbs Transition Signals Appendix D: Editing Symbols Appendix E: Research and Documentation of Sources Types of Sources Evaluating Sources Documentation of Sources In-Text Citations Works-Cited Lists Appendix F: Self-Editing and Peer-Editing Worksheets Scoring Rubrics