Chinese Poetry Generation with Planning based Neural Network

Slides:



Advertisements
Similar presentations
Processing XML Keyword Search by Constructing Effective Structured Queries Jianxin Li, Chengfei Liu, Rui Zhou and Bo Ning Swinburne University of Technology,
Advertisements

Multi-Document Person Name Resolution Michael Ben Fleischman (MIT), Eduard Hovy (USC) From Proceedings of ACL-42 Reference Resolution workshop 2004.
Statistical Machine Translation Part II: Word Alignments and EM Alexander Fraser ICL, U. Heidelberg CIS, LMU München Statistical Machine Translation.
Distributed Representations of Sentences and Documents
Statistical Natural Language Processing. What is NLP?  Natural Language Processing (NLP), or Computational Linguistics, is concerned with theoretical.
Machine translation Context-based approach Lucia Otoyo.
1 Formal Models for Expert Finding on DBLP Bibliography Data Presented by: Hongbo Deng Co-worked with: Irwin King and Michael R. Lyu Department of Computer.
Presenter: Shanshan Lu 03/04/2010
1 Learning Sub-structures of Document Semantic Graphs for Document Summarization 1 Jure Leskovec, 1 Marko Grobelnik, 2 Natasa Milic-Frayling 1 Jozef Stefan.
Survey of Computer Science Fields Related to the Titles of Master Thesis at Faculty of Mathematics in Belgrade Dušan Tošić University of Belgrade, Faculty.
1 A Web Search Engine-Based Approach to Measure Semantic Similarity between Words Presenter: Guan-Yu Chen IEEE Trans. on Knowledge & Data Engineering,
Effective Reranking for Extracting Protein-protein Interactions from Biomedical Literature Deyu Zhou, Yulan He and Chee Keong Kwoh School of Computer Engineering.
Multi-level Bootstrapping for Extracting Parallel Sentence from a Quasi-Comparable Corpus Pascale Fung and Percy Cheung Human Language Technology Center,
Context-Aware Query Classification Huanhuan Cao, Derek Hao Hu, Dou Shen, Daxin Jiang, Jian-Tao Sun, Enhong Chen, Qiang Yang Microsoft Research Asia SIGIR.
Finding document topics for improving topic segmentation Source: ACL2007 Authors: Olivier Ferret (18 route du Panorama, BP6) Reporter:Yong-Xiang Chen.
Single Document Key phrase Extraction Using Neighborhood Knowledge.
A Multilingual Hierarchy Mapping Method Based on GHSOM Hsin-Chang Yang Associate Professor Department of Information Management National University of.
1 ICASSP Paper Survey Presenter: Chen Yi-Ting. 2 Improved Spoken Document Retrieval With Dynamic Key Term Lexicon and Probabilistic Latent Semantic Analysis.
Maximum Entropy techniques for exploiting syntactic, semantic and collocational dependencies in Language Modeling Sanjeev Khudanpur, Jun Wu Center for.
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation EMNLP’14 paper by Kyunghyun Cho, et al.
DeepWalk: Online Learning of Social Representations
Bassem Makni SML 16 Click to add text 1 Deep Learning of RDF rules Semantic Machine Learning.
Fabien Cromieres Chenhui Chu Toshiaki Nakazawa Sadao Kurohashi
Neural Machine Translation
Statistical Machine Translation Part II: Word Alignments and EM
CNN-RNN: A Unified Framework for Multi-label Image Classification
Learning linguistic structure with simple and more complex recurrent neural networks Psychology February 2, 2017.
Korean version of GloVe Applying GloVe & word2vec model to Korean corpus speaker : 양희정 date :
End-To-End Memory Networks
Designing Cross-Language Information Retrieval System using various Techniques of Query Expansion and Indexing for Improved Performance  Hello everyone,
CS 388: Natural Language Processing: LSTM Recurrent Neural Networks
CS 4501: Introduction to Computer Vision Computer Vision + Natural Language Connelly Barnes Some slides from Fei-Fei Li / Andrej Karpathy / Justin Johnson.
An Image Database Retrieval Scheme Based Upon Multivariate Analysis and Data Mining Presented by C.C. Chang Dept. of Computer Science and Information.
System for Semi-automatic ontology construction
Using lexical chains for keyword extraction
Recurrent Neural Networks for Natural Language Processing
Adversarial Learning for Neural Dialogue Generation
Neural Machine Translation by Jointly Learning to Align and Translate
A Deep Learning Technical Paper Recommender System
张昊.
Intelligent Information System Lab
Intro to NLP and Deep Learning
Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning Shizhu He, Cao liu, Kang Liu and Jun Zhao.
Neural Machine Translation By Learning to Jointly Align and Translate
Presentation 王睿.
Paraphrase Generation Using Deep Learning
Recurrent Neural Networks
Presented by: Prof. Ali Jaoua
Final Presentation: Neural Network Doc Summarization
Learning linguistic structure with simple and more complex recurrent neural networks Psychology February 8, 2018.
Automatic Detection of Causal Relations for Question Answering
Introduction to RNNs for NLP
Other Classification Models: Recurrent Neural Network (RNN)
Memory-augmented Chinese-Uyghur Neural Machine Translation
Socialized Word Embeddings
Machine Translation(MT)
Natural Language to SQL(nl2sql)
Learning linguistic structure with simple recurrent neural networks
Attention.
Please enjoy.
EGR 2131 Unit 12 Synchronous Sequential Circuits
Attention for translation
Topic: Semantic Text Mining
Question Answering System
Presented By: Harshul Gupta
Baseline Model CSV Files Pandas DataFrame Sentence Lists
Week 3 Presentation Ngoc Ta Aidean Sharghi.
Week 7 Presentation Ngoc Ta Aidean Sharghi
Construcing Narrative Event Evolutionary Graph for Script Event Prediction 刘潇远.
Neural Machine Translation by Jointly Learning to Align and Translate
Presentation transcript:

Chinese Poetry Generation with Planning based Neural Network Yiding Wen, Jiefu Liang, Jiabao Zeng

Poetry Generation More than text generation: need to follow some specific structural, rhythmical and tonal patterns Some approaches: Based on semantic and grammar templates Statistical machine translation methods Consider it as a sequence to sequence generation problem …...

Approches: Planning-based poetry generation approach (PPG) Two stages: User’s writing intent N keywords N lines poem Poem Planning Poem Generation A word, sentence, document...

Approches: Planning-based poetry generation approach (PPG) PPG Framework

Approaches: Poem Planning User’s writing intent N keywords N lines poem Poem Generation A word, sentence, document... What if we don’t have enough keywords? Keyword Extraction (TextRank algorithm) Keyword Expansion

Keyword Extraction: TextRank Algorithm User’s writing intent Keywords Keyword Expansion derived from: Vertex: a word Edge: co-occurrence between two words TextRange score S(Vi): d is a damping factor (usually set to 0.85) Wij is the weight of the edge between Vi and Vj. E(Vij): the set of vertices connected with Vi

Keyword Expansion: Less than N Keywords Keyword Expansion User’s writing intent N Keywords Keyword Extraction RNNLM-based model Predict the subsequent keywords according to the preceding sequence of keywords: Only suitable for generating subtopics for those covering by the collected poem. Knowledge-based method Extra knowledge from encyclopedias, lexical databases (WordNet),... Generate candidate words Choose candidate words with the highest TextRank

Approaches: Poem Generation User’s writing intent N keywords N lines poem Poem Planning A word, sentence, document... Framework of an attention based RNN encoder-decoder(RNN enc-dec) Encoder Decoder

An illustration of poem generation model Another GRU Decoder Encoder Bi-directional Gated Recurrent Unit (GRU) An illustration of poem generation model

Approaches - Poem Generation Encoder All preceding text Corresponding Keyword X = {x1, x2...xTx} K = {a1, a2...aTk} First Backward State of rTk Last Forward State of r1 [h1, h2… hTx] [r1, r2… rTx] h0 h = [h0, h2….hTx] Context Vector c

Approaches - Poem Generation Encode keyword Decoder Internal Status Vector St Context Vector ct Previous Output yt-1 Encode all preceding text

Experiment Dataset 76,859 Chinese quatrains: 2,000 poems for validation, 2,000 poems for testing, and the rest for training The training corpus of poems: CRF based word segmentation-> keyword extraction and expansion-> four triples for every poem

Experiment Evaluation A human study to evaluate the poem generation models

Experiment Result Four baselines: SMT(Statistical Machine Translation), RNNLM(RNN Language Model), RNNPG(RNN-based Poem Generator) and ANMT(Attention-based Neural Machine Translation) PPG(Planning-based Poetry Generation) outperforms all baseline models in average scores. The results are consistent with both settings of 5-character and 7-character poem generations. From the results of the human evaluation, it can be seen that the proposed method obtained very close performances in Poeticness and Fluency compared with ANMT but much higher Coherence and Meaning scores, which verified the effectiveness of the sub-topic prediction model.

Experiment Automatic Generation vs. Human Poet 40 evaluators: Four of them were professional in Chinese literature and were assigned to the Expert Group. 36 were assigned to the Normal Group. Choose from three options: 1) poem A is written by the human; 2) poem B is written by the human; 3) cannot distinguish which one is written by the human We can draw two conclusions from the result: (1) under the standard of normal users, the quality of our machine-generated poems is very close to human poets; (2) but from the view of professional experts, the machine-generated poems still have some obvious shortages comparing to human-written poems.

Experiment Generation Examples The model can also generate poems based on any modern terms The title of the left poem in Table 7 is 啤酒(beer), the keywords given by our poem planning model are 啤酒(beer), 香醇(aroma), 清爽(cool) and 醉(drunk). The title of the right one is a named entity 冰心(Xin Bing), who was a famous writer. The poem planning system generates three keywords besides 冰心(Xin Bing): 春水(spring river), 繁星(stars) and 往事(the past), which are all related to the writer’s works.

Conclusion and Future Work PPG (Planning-based Poetry Generation): two stages Topic planning: pLSA, LDA or word2vec Other forms of literary genres: Song iambics, Yuan Qu etc., or poems in other languages

Thank you! Enjoy the spring break and good luck on homework :)