TAILIEUCHUNG - Báo cáo khoa học: "Supervised and Unsupervised Learning for Sentence Compression"

In Statistics-Based Summarization - Step One: Sentence Compression, Knight and Marcu (Knight and Marcu, 2000) (K&M) present a noisy-channel model for sentence compression. The main difficulty in using this method is the lack of data; Knight and Marcu use a corpus of 1035 training sentences. More data is not easily available, so in addition to improving the original K&M noisy-channel model, we create unsupervised and semi-supervised models of the task. | Supervised and Unsupervised Learning for Sentence Compression Jenine Turner and Eugene Charniak Department of Computer Science Brown Laboratory for Linguistic Information Processing BLLIP Brown University Providence RI 02912 j enine ec @ Abstract In Statistics-Based Summarization - Step One Sentence Compression Knight and Marcu Knight and Marcu 2000 K M present a noisy-channel model for sentence compression. The main difficulty in using this method is the lack of data Knight and Marcu use a corpus of 1035 training sentences. More data is not easily available so in addition to improving the original K M noisy-channel model we create unsupervised and semi-supervised models of the task. Finally we point out problems with modeling the task in this way. They suggest areas for future research. 1 Introduction Summarization in general and sentence compression in particular are popular topics. Knight and Marcu henceforth K M introduce the task of statistical sentence compression in Statistics-Based Summarization - Step One Sentence Compression Knight and Marcu 2000 . The appeal of this problem is that it produces summarizations on a small scale. It simplifies general compression problems such as text-to-abstract conversion by eliminating the need for coherency between sentences. The model is further simplified by being constrained to word deletion no rearranging of words takes place. Others have performed the sentence compression task using syntactic approaches to this problem Mani et al. 1999 Zajic et al. 2004 but we focus exclusively on the K M formulation. Though the problem is simpler it is still pertinent to current needs generation of captions for television and audio scanning services for the blind Grefenstette 1998 as well as compressing chosen sentences for headline generation Angheluta et al. 2004 are examples of uses for sentence compression. In addition to simplifying the task K M s noisy-channel formulation is also appealing. In the following .

• Báo cáo khoa học
• Supervised
• Unsupervised Learning
• Sentence Compression
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Employing Personal
• Impersonal Views in Supervised
• Semi supervised Sentiment Classification
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• End of Supervised
• Parsing in Sight
• Is the End of Supervised Parsing in Sight?
• The additional function
• Dynamic semi supervised fuzzy clustering
• Dental X ray image segmentation
• Additional function
• Fuzzy C Means
• Active learning
• Graph based method
• K means
• Semi supervised clustering
• Semi supervised graph based clustering
• Semi supervised Dependency Parsing
• Lexical Affinities
• Alexis Nasr
• A Graph based Cross lingual Projection Approach
• Weakly Supervised Relation Extraction
• Gary Geunbae Lee
• Unsupervised Morphology Rivals Supervised Morphology
• Arabic MT
• David Stallard
• Aspect Extraction
• Semi Supervised Modeling
• Arjun Mukherjee
• A Statistical Model for Unsupervised
• Semi supervised Transliteration Mining
• Hassan Sajjad Alexander
• Graph based Semi Supervised Learning Algorithms
• NLP
• Long Papers
• Word representations
• A simple and general method
• semi supervised learning
• Creating Robust Supervised Classifiers
• Web Scale N gram Data
• Shane Bergsma
• Supervised Noun Phrase
• Coreference Research
• The First Fifteen Years
• Experiments in Graph based
• Semi Supervised Learning Methods
• Class Instance Acquisition
• Knowledge rich Word Sense
• Disambiguation Rivaling Supervised Systems
• Simone Paolo Ponzetto
• Semi Supervised
• Frame Semantic Parsing
• Unknown Predicates
• Simple semi supervised training
• part of speech taggers
• A Semi Supervised Key Phrase Extraction Approach
• Learning from Title Phrases
• Document Semantic Network
• Supervised Word Alignment
• Jinxi Xu and Jinying Chen
• Active Learning Based Elicitation
• Semi Supervised Word Alignment
• Vamshi Ambati
• Prenominal Modifier Ordering
• Margaret Mitchell
• Document Selection Help Semi supervised Learning
• A Case Study On Event Extraction
• Ralph Grishman
• Typed Graph Models
• Name Ethnicity
• Semi supervised latent variable models
• sentence level sentiment analysis
• Learning Condensed Feature Representations
• Large Unsupervised Data Sets
• Supervised Learning