Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data: 16th China National Conference, CCL 2017, and 5th International Symposium, NLP-NABD 2017, Nanjing, China, October 13-15, 2017, ProceedingsMaosong Sun, Xiaojie Wang, Baobao Chang, Deyi Xiong This book constitutes the proceedings of the 16th China National Conference on Computational Linguistics, CCL 2017, and the 5th International Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2017, held in Nanjing, China, in October 2017. The 39 full papers presented in this volume were carefully reviewed and selected from 272 submissions. They were organized in topical sections named: Fundamental theory and methods of computational linguistics; Machine translation and multilingual information processing; Knowledge graph and information extraction; Language resource and evaluation; Information retrieval and question answering; Text classification and summarization; Social computing and sentiment analysis; NLP applications; Minority language information processing. |
Contents
| 3 | |
| 13 | |
| 24 | |
Improving Word Embeddings for Low Frequency Words by Pseudo Contexts | 37 |
A Pipelined Pretraining Algorithm for DBNs | 48 |
Enhancing LSTMbased Word Segmentation Using Unlabeled Data | 60 |
Machine Translation and Multilingual Information Processing | 71 |
Context Sensitive Word Deletion Model for Statistical Machine Translation | 73 |
Generating Textual Entailment Using Residual LSTMs | 263 |
Unsupervised Joint Entity Linking over Question Answering Pair with Global Knowledge | 273 |
Hierarchical Gated Recurrent Neural Tensor Network for Answer Triggering | 287 |
Question Answering with CharacterLevel LSTM Encoders and ModelBased Data Augmentation | 295 |
Exploiting Explicit Matching Knowledge with Long ShortTerm Memory | 306 |
Text Classification and Summarization | 318 |
TopicSpecific Image Caption Generation | 321 |
Deep Learning Based Document Theme Analysis for Composition Generation | 333 |
CostAware Learning Rate for Neural Machine Translation | 85 |
Knowledge Graph and Information Extraction | 94 |
Integrating Word Sequences and Dependency Structures for ChemicalDisease Relation Extraction | 97 |
Named Entity Recognition with Gated Convolutional Neural Networks | 110 |
Improving Event Detection via Information Sharing Among Related Event Types | 122 |
Joint Extraction of Multiple Relations and Entities by Using a Hybrid Neural Network | 135 |
A Fast and Effective Framework for Lifelong Topic Model with Selflearning Knowledge | 147 |
Collective Entity Linking on Relational Graph Model with Mentions | 159 |
An Unsupervised Bilingual Entity Linking System | 172 |
Using CostSensitive Ranking Loss to Improve Distant Supervised Relation Extraction | 184 |
Multichannel LSTMCRF for Named Entity Recognition in Chinese Social Media | 197 |
Language Resource and Evaluation | 209 |
Generating Chinese Classical Poems with RNN EncoderDecoder | 210 |
Collaborative Recognition and Recovery of the Chinese Intercept Abbreviation | 224 |
Semantic Dependency Labeling of Chinese Noun Phrases Based on Semantic Lexicon | 237 |
Information Retrieval and Question Answering | 249 |
Bidirectional Gated Memory Networks for Answer Selection | 251 |
A Multilingual Document Summarization Framework Based on Summary Diversity and Hierarchical Topics | 343 |
Conceptual Multilayer Neural Network Model for Headline Generation | 355 |
Social Computing and Sentiment Analysis | 368 |
Local Community Detection Using Social Relations and Topic Features in Social Networks | 371 |
NLP Applications | 384 |
Dual Interaction Model for Machine Comprehension | 387 |
Multiview LSTM Language Model with WordSynchronized Auxiliary Feature for LVCSR | 398 |
Memory Augmented Attention Model for Chinese Implicit Discourse Relation Recognition | 411 |
Natural Logic Inference for Emotion Detection | 424 |
Minority Language Information Processing | 437 |
Tibetan SyllableBased Functional Chunk Boundary Identification | 438 |
Harvest UyghurChinese AlignedSentences Bitexts from Multilingual Sites Based on Word Embedding | 449 |
Language Model for Mongolian Polyphone Proofreading | 461 |
EndtoEnd Neural Text Classification for Tibetan | 472 |
| 481 | |
Other editions - View all
Common terms and phrases
abbreviation achieve annotated answer entity approach arXiv preprint Association for Computational baseline Beijing bigram candidate entities caption character Chen China Chinese chunk classification collocation Computational Linguistics conditional random field Conference context convolutional neural networks corpus cosine similarity dataset decoder deep learning denotes distribution document domain EMNLP emotion encoder entity linking evaluation experiments F1 score frequency hidden layer improve inference input knowledge label language model learning rate lexical LSTM matching memory mentions method module n-gram named entity recognition Natural Language Processing node noun output pairs paper parameters performance pre-training algorithm prediction problem Proceedings proposed QA-pairs question answering recurrent neural networks relation extraction representation score semantic relations sentence sequence shown similarity softmax state-of-the-art statistical machine translation syntactic Table target task Tibetan topic models training data unigram vector verbs Wang Wikipedia word deletion word embeddings word segmentation Zhang