EMNLP 2008 - PDF Preprint Papers

EMNLP 2008

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed EMNLP-2008 Paper

click to vote

EMNLP
2008

234views Natural Language Processing» more EMNLP 2008»

Scalable Language Processing Algorithms for the Masses: A Case Study in Computing Word Co-occurrence Matrices with MapReduce

14 years 26 days ago

Download www.umiacs.umd.edu

This paper explores the challenge of scaling up language processing algorithms to increasingly large datasets. While cluster computing has been available in commercial environment...

Jimmy J. Lin

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status

1	234	Scalable Language Processing Algorithms for the Masses: A Case Study in Computing Word Co-occurrence Matrices with MapReduce	claim
2	201	Arabic Named Entity Recognition using Optimized Feature Sets	claim
3	199	Acquiring Domain-Specific Dialog Information from Task-Oriented Human-Human Interaction through an Unsupervised Learning	claim
4	195	A Dependency-based Word Subsequence Kernel	claim
5	182	HTM: A Topic Model for Hypertexts	claim
6	174	Learning to Predict Code-Switching Points	claim
7	174	Relative Rank Statistics for Dialog Analysis	claim
8	173	Mining and Modeling Relations between Formal and Informal Chinese Phrases from Web Corpora	claim
9	160	Lattice-based Minimum Error Rate Training for Statistical Machine Translation	claim
10	159	A Japanese Predicate Argument Structure Analysis using Decision Lists	claim
11	158	An Analysis of Active Learning Strategies for Sequence Labeling Tasks	claim
12	148	Predicting Success in Machine Translation	claim
13	147	Automatic Prediction of Parser Accuracy	claim
14	147	Word Sense Disambiguation Using OntoNotes: An Empirical Study	claim
15	144	Online Methods for Multi-Domain Learning and Adaptation	claim
16	144	Generalizing Local and Non-Local Word-Reordering Patterns for Syntax-Based Machine Translation	claim
17	143	Coarse-to-Fine Syntactic Machine Translation using Language Projections	claim
18	142	Modeling Annotators: A Generative Approach to Learning from Annotator Rationales	claim
19	140	Phrase Translation Probabilities with ITG Priors and Smoothing as Learning Objective	claim
20	139	Improved Sentence Alignment on Parallel Web Pages Using a Stochastic Tree Alignment Model	claim
21	139	Revealing the Structure of Medical Dictations with Conditional Random Fields	claim
22	138	Language and Translation Model Adaptation using Comparable Corpora	claim
23	133	Sparse Multi-Scale Grammars for Discriminative Latent Variable Parsing	claim
24	133	Cheap and Fast - But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks	claim
25	133	Selecting Sentences for Answering Complex Questions	claim
26	132	Adapting a Lexicalized-Grammar Parser to Contrasting Domains	claim
27	131	Integrating Multi-level Linguistic Knowledge with a Unified Framework for Mandarin Speech Recognition	claim
28	131	Maximum Entropy based Rule Selection Model for Syntax-based Statistical Machine Translation	claim
29	131	Mention Detection Crossing the Language Barrier	claim
30	130	Lattice Minimum Bayes-Risk Decoding for Statistical Machine Translation	claim
31	130	Seed and Grow: Augmenting Statistically Generated Summary Sentences using Schematic Word Patterns	claim
32	129	Ranking Reader Emotions Using Pairwise Loss Minimization and Emotional Distribution Regression	claim
33	128	Automatic Set Expansion for List Question Answering	claim
34	127	A Structured Vector Space Model for Word Meaning in Context	claim
35	127	Improving Chinese Semantic Role Classification with Hierarchical Feature Selection Strategy	claim
36	127	A Simple and Effective Hierarchical Phrase Reordering Model	claim
37	125	Better Binarization for the CKY Parsing	claim
38	125	Using Bilingual Knowledge and Ensemble Techniques for Unsupervised Chinese Sentiment Analysis	claim
39	123	Weakly-Supervised Acquisition of Labeled Class Instances using Graph Random Walks	claim
40	123	Adding Redundant Features for CRFs-based Sentence Sentiment Classification	claim
41	121	Regular Expression Learning for Information Extraction	claim
42	121	Indirect-HMM-based Hypothesis Alignment for Combining Outputs from Machine Translation Systems	claim
43	121	A Generative Model for Parsing Natural Language to Meaning Representations	claim
44	120	Who is Who and What is What: Experiments in Cross-Document Co-Reference	claim
45	119	Graph-based Analysis of Semantic Drift in Espresso-like Bootstrapping Algorithms	claim
46	119	A Phrase-Based Alignment Model for Natural Language Inference	claim
47	119	LTAG Dependency Parsing with Bidirectional Incremental Construction	claim
48	119	Incorporating Temporal and Semantic Information with Eye Gaze for Automatic Word Acquisition in Multimodal Conversational Systems	claim
49	118	Online Large-Margin Training of Syntactic and Structural Translation Features	claim
50	118	A Graph-theoretic Model of Lexical Syntactic Acquisition	claim
51	117	Learning with Compositional Semantics as Structural Inference for Subsentential Sentiment Analysis	claim
52	117	Sampling Alignment Structure under a Bayesian Translation Model	claim
53	117	CoCQA: Co-Training over Questions and Answers with an Application to Predicting Question Subjectivity Orientation	claim
54	117	Stacking Dependency Parsers	claim
55	115	Joint Unsupervised Coreference Resolution with Markov Logic	claim
56	114	Dependency-based Semantic Role Labeling of PropBank	claim
57	114	Studying the History of Ideas Using Topic Models	claim
58	113	Learning with Probabilistic Features for Improved Pipeline Models	claim
59	111	A Casual Conversation System Using Modality and Word Associations Retrieved from the Web	claim
60	111	A Discriminative Candidate Generator for String Transformations	claim
61	110	Automatic Inference of the Temporal Location of Situations in Chinese Text	claim
62	110	Specialized Models and Ranking for Coreference Resolution	claim
63	109	A comparison of Bayesian estimators for unsupervised Hidden Markov Model POS taggers	claim
64	109	Seeded Discovery of Base Relations in Large Corpora	claim
65	109	N-gram Weighting: Reducing Training Data Mismatch in Cross-Domain Language Model Estimation	claim
66	108	Multilingual Subjectivity Analysis Using Machine Translation	claim
67	108	Summarizing Spoken and Written Conversations	claim
68	108	Triplet Lexicon Models for Statistical Machine Translation	claim
69	107	Attacking Decipherment Problems Optimally with Low-Order N-gram Models	claim
70	107	Discriminative Learning of Selectional Preference from Unlabeled Text	claim
71	106	Online Word Games for Semantic Data Collection	claim
72	106	HotSpots: Visualizing Edits to a Text	claim
73	105	Learning Graph Walk Based Similarity Measures for Parsed Text	claim
74	105	One-Class Clustering in the Text Domain	claim
75	104	Latent-Variable Modeling of String Transductions with Finite-State Methods	claim
76	104	Automatic induction of FrameNet lexical units	claim
77	104	Soft-Supervised Learning for Text Classification	claim
78	104	Refining Generative Language Models using Discriminative Learning	claim
79	102	Improving Interactive Machine Translation via Mouse Actions	claim
80	101	Topic-Driven Multi-Document Summarization with Encyclopedic Knowledge and Spreading Activation	claim
81	100	Revisiting Readability: A Unified Framework for Predicting Text Quality	claim
82	98	An Exploration of Document Impact on Graph-Based Multi-Document Summarization	claim
83	97	Multimodal Subjectivity Analysis of Multiparty Conversation	claim
84	95	Bayesian Unsupervised Topic Segmentation	claim
85	94	Cross-Task Knowledge-Constrained Self Training	claim
86	94	Complexity of Finding the BLEU-optimal Hypothesis in a Confusion Network	claim
87	94	Two Languages are Better than One (for Syntactic Parsing)	claim
88	94	Question Classification using Head Words and their Hypernyms	claim
89	94	Probabilistic Inference for Machine Translation	claim
90	92	Part-of-Speech Tagging for English-Spanish Code-Switched Text	claim
91	92	Legal Docket Classification: Where Machine Learning Stumbles	claim
92	91	It's a Contradiction - no, it's not: A Case Study using Functional Relations	claim
93	91	Understanding the Value of Features for Coreference Resolution	claim
94	91	Transliteration as Constrained Optimization	claim
95	90	Online Acquisition of Japanese Unknown Morphemes using Morphological Constraints	claim
96	90	The Linguistic Structure of English Web-Search Queries	claim
97	90	Computing Word-Pair Antonymy	claim
98	89	Unsupervised Multilingual Learning for POS Tagging	claim
99	89	Decomposability of Translation Metrics for Improved Evaluation and Efficient Algorithms	claim
100	88	Syntactic Constraints on Paraphrases Extracted from Parallel Corpora	claim
101	85	Syntactic Models for Structural Word Insertion and Deletion during Translation	claim
102	83	Sentence Fusion via Dependency Graph Compression	claim
103	81	A Noisy-Channel Model of Human Sentence Comprehension under Uncertain Input	claim
104	75	Forest-based Translation Rule Extraction	claim
105	75	Unsupervised Models for Coreference Resolution	claim
106	74	Learning the Scope of Negation in Biomedical Texts	claim
107	73	Information Retrieval Oriented Word Segmentation based on Character Association Strength Ranking	claim
108	72	Scaling Textual Inference to the Web	claim
109	72	When Harry Met Harri: Cross-lingual Name Spelling Normalization	claim
110	67	Jointly Combining Implicit Constraints Improves Temporal Ordering	claim
111	62	A Tale of Two Parsers: Investigating and Combining Graph-based and Transition-based Dependency Parsing	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers