ACL 2009 - PDF Preprint Papers

ACL 2009 Meeting of the Association for Computational Linguistics

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ACL-2009 Paper

click to vote

ACL
2009

281views Computational Linguistics» more ACL 2009»

Unsupervised Relation Extraction by Mining Wikipedia Texts Using Information from the Web

13 years 2 months ago

Download www.aclweb.org

This paper presents an unsupervised relation extraction method for discovering and enhancing relations in which a specified concept in Wikipedia participates. Using respective cha...

Yulan Yan, Naoaki Okazaki, Yutaka Matsuo, Zhenglu ...

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	281	Unsupervised Relation Extraction by Mining Wikipedia Texts Using Information from the Web	claim
2	204	MARS: Multilingual Access and Retrieval System with Enhanced Query Translation and Document Retrieval	claim
3	199	A Syntax-Driven Bracketing Model for Phrase-Based Translation	claim
4	195	Distant supervision for relation extraction without labeled data	claim
5	185	An Error-Driven Word-Character Hybrid Model for Joint Chinese Word Segmentation and POS Tagging	claim
6	184	Query Segmentation Based on Eigenspace Similarity	claim
7	182	Automatic sense prediction for implicit discourse relations in text	claim
8	181	A Framework of Feature Selection Methods for Text Categorization	claim
9	180	A Graph-based Semi-Supervised Learning for Question-Answering	claim
10	177	Finding Hedges by Chasing Weasels: Hedge Detection Using Wikipedia Tags and Shallow Linguistic Features	claim
11	175	Who, What, When, Where, Why? Comparing Multiple Approaches to the Cross-Lingual 5W Task	claim
12	170	Concise Integer Linear Programming Formulations for Dependency Parsing	claim
13	169	A Comparative Study on Generalization of Semantic Roles in FrameNet	claim
14	167	Robust Approach to Abbreviating Terms: A Discriminative Latent Variable Model with Global Information	claim
15	167	Mining Bilingual Data from the Web with Adaptively Learnt Patterns	claim
16	166	Automatic Set Instance Extraction using the Web	claim
17	166	A Novel Discourse Parser Based on Support Vector Machine Classification	claim
18	166	Semi-Supervised Active Learning for Sequence Labeling	claim
19	165	Automatically Generating Wikipedia Articles: A Structure-Aware Approach	claim
20	165	Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty	claim
21	164	Unsupervised Multilingual Grammar Induction	claim
22	162	A Comparative Study of Hypothesis Alignment and its Improvement for Machine Translation System Combination	claim
23	161	CATiB: The Columbia Arabic Treebank	claim
24	160	Active Learning for Multilingual Statistical Machine Translation	claim
25	160	Introduction of a new paraphrase generation tool based on Monte-Carlo sampling	claim
26	160	Learning Semantic Categories from Clickthrough Logs	claim
27	159	Word to Sentence Level Emotion Tagging for Bengali Blogs	claim
28	157	A Non-negative Matrix Tri-factorization Approach to Sentiment Classification with Lexical Prior Knowledge	claim
29	156	Annotating and Recognising Named Entities in Clinical Notes	claim
30	154	Forest-based Tree Sequence to String Translation Model	claim
31	153	Incorporating Information Status into Generation Ranking	claim
32	153	Answering Opinion Questions with Random Walks on Graphs	claim
33	153	Bayesian Learning of a Tree Substitution Grammar	claim
34	151	Creating a Gold Standard for Sentence Clustering in Multi-Document Summarization	claim
35	151	Sentence diagram generation using dependency parsing	claim
36	151	Demonstration of Joshua: An Open Source Toolkit for Parsing-based Machine Translation	claim
37	150	Learning foci for Question Answering over Topic Maps	claim
38	149	Genre distinctions for discourse in the Penn TreeBank	claim
39	149	The Contribution of Linguistic Features to Automatic Machine Translation Evaluation	claim
40	149	Cross Language Dependency Parsing using a Bilingual Lexicon	claim
41	148	A Succinct N-gram Language Model	claim
42	147	Learning a Compositional Semantic Parser using an Existing Syntactic Parser	claim
43	147	Automatic Adaptation of Annotation Standards: Chinese Word Segmentation and POS Tagging - A Case Study	claim
44	147	Co-Training for Cross-Lingual Sentiment Classification	claim
45	147	Asynchronous Binarization for Synchronous Grammars	claim
46	146	Do Automatic Annotation Techniques Have Any Impact on Supervised Complex Question Answering?	claim
47	146	Automatic Generation of Information-seeking Questions Using Concept Clusters	claim
48	146	Mining User Reviews: from Specification to Summarization	claim
49	145	Composite Kernels For Relation Extraction	claim
50	145	A NLG-based Application for Walking Directions	claim
51	144	Multi-Task Transfer Learning for Weakly-Supervised Relation Extraction	claim
52	144	Brutus: A Semantic Role Labeling System Incorporating CCG, CFG, and Dependency Features	claim
53	142	Semantic Tagging of Web Search Queries	claim
54	141	SMS based Interface for FAQ Retrieval	claim
55	141	The Impact of Query Refinement in the Web People Search Task	claim
56	140	Unsupervised Argument Identification for Semantic Role Labeling	claim
57	139	Toward Smaller, Faster, and Better Hierarchical Phrase-based SMT	claim
58	139	Handling phrase reorderings for machine translation	claim
59	138	Confidence Measure for Word Alignment	claim
60	138	Semi-supervised Learning for Automatic Prosodic Event Detection Using Co-training Algorithm	claim
61	138	Generalizing over Lexical Features: Selectional Preferences for Semantic Role Classification	claim
62	137	Opinion and Generic Question Answering Systems: a Performance Analysis	claim
63	137	Syntax is from Mars while Semantics from Venus! Insights from Spectral Analysis of Distributional Similarity Networks	claim
64	137	Accurate Learning for Chinese Function Tags from Minimal Features	claim
65	136	Application-driven Statistical Paraphrase Generation	claim
66	134	Cross-Domain Dependency Parsing Using a Deep Linguistic Grammar	claim
67	134	Quadratic-Time Dependency Parsing for Machine Translation	claim
68	133	Summarizing multiple spoken documents: finding evidence from untranscribed audio	claim
69	133	A global model for joint lemmatization and part-of-speech prediction	claim
70	133	Better Word Alignments with Supervised ITG Models	claim
71	133	Reducing the Annotation Effort for Letter-to-Phoneme Conversion	claim
72	133	The Contribution of Stylistic Information to Content-based Mobile Spam Filtering	claim
73	133	Hidden Markov Tree Model in Dependency-based Machine Translation	claim
74	131	ProLiV - a Tool for Teaching by Viewing Computational Linguistics	claim
75	130	Unsupervised Learning of Narrative Schemas and their Participants	claim
76	130	Extracting Paraphrases of Technical Terms from Noisy Parallel Software Corpora	claim
77	129	Exploiting Bilingual Information to Improve Web Search	claim
78	129	Employing Topic Models for Pattern-based Semantic Class Discovery	claim
79	129	Case markers and Morphology: Addressing the crux of the fluency problem in English-Hindi SMT	claim
80	129	Bridging Morpho-Syntactic Gap between Source and Target Sentences for English-Korean Statistical Machine Translation	claim
81	129	English-Chinese Bi-Directional OOV Translation based on Web Mining and Supervised Learning	claim
82	129	Data Cleaning for Word Alignment	claim
83	128	Revisiting Pivot Language Approach for Machine Translation	claim
84	128	Learning to Tell Tales: A Data-driven Approach to Story Generation	claim
85	127	Collaborative Decoding: Partial Hypothesis Re-ranking Using Translation Consensus between Decoders	claim
86	126	Comparing the Accuracy of CCG and Penn Treebank Parsers	claim
87	126	An Integrated Multi-document Summarization Approach based on Word Hierarchical Representation	claim
88	126	Discriminative Approach to Predicate-Argument Structure Analysis with Zero-Anaphora Resolution	claim
89	126	A Web-Based Interactive Computer Aided Translation Tool	claim
90	125	Bayesian Unsupervised Word Segmentation with Nested Pitman-Yor Language Modeling	claim
91	125	Conundrums in Noun Phrase Coreference Resolution: Making Sense of the State-of-the-Art	claim
92	124	Markov Random Topic Fields	claim
93	124	System for Querying Syntactically Annotated Corpora	claim
94	123	Reinforcement Learning for Mapping Instructions to Actions	claim
95	123	Improving Automatic Speech Recognition for Lectures through Transformation-based Rules Learned from Minimal Data	claim
96	123	Profile Based Cross-Document Coreference Using Kernelized Fuzzy Relational Clustering	claim
97	123	Query-Focused Summaries or Query-Biased Summaries?	claim
98	123	Graph Ranking for Sentiment Transfer	claim
99	123	An Ontology-Based Approach for Key Phrase Extraction	claim
100	123	Reducing SMT Rule Table with Monolingual Key Phrase	claim
101	123	A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar	claim
102	122	Reducing Semantic Drift with Bagging and Distributional Similarity	claim
103	122	Part of Speech Tagger for Assamese Text	claim
104	122	Topological Ordering of Function Words in Hierarchical Phrase-based Translation	claim
105	121	Learning Semantic Correspondences with Less Supervision	claim
106	121	Efficient Minimum Error Rate Training and Minimum Bayes-Risk Decoding for Translation Hypergraphs and Lattices	claim
107	120	Learning Context-Dependent Mappings from Sentences to Logical Form	claim
108	120	Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition	claim
109	120	Using Generation for Grammar Analysis and Error Detection	claim
110	120	Arabic Cross-Document Coreference Resolution	claim
111	119	Latent Variable Models of Concept-Attribute Attachment	claim
112	119	Automatic Cost Estimation for Tree Edit Distance Using Particle Swarm Optimization	claim
113	117	Heterogeneous Transfer Learning for Image Clustering via the SocialWeb	claim
114	116	A Syntax-Free Approach to Japanese Sentence Compression	claim
115	116	Automatic Satire Detection: Are You Having a Laugh?	claim
116	116	WikiBABEL: A Wiki-style Platform for Creation of Parallel Data	claim
117	116	WISDOM: A Web Information Credibility Analysis Systematic	claim
118	115	Quantitative modeling of the neural representation of adjective-noun phrases to account for fMRI activation	claim
119	115	A System for Semantic Analysis of Chemical Compound Names	claim
120	114	Coordinate Structure Analysis with Global Structural Constraints and Alignment-Based Local Features	claim
121	114	A Stochastic Finite-State Morphological Parser for Turkish	claim
122	113	Abstraction and Generalisation in Semantic Role Labels: PropBank, VerbNet or both?	claim
123	113	Summarizing Definition from Wikipedia	claim
124	113	Compiling a Massive, Multilingual Dictionary via Probabilistic Inference	claim
125	113	Robust Machine Translation Evaluation with Entailment Features	claim
126	113	Detecting Compositionality in Multi-Word Expressions	claim
127	113	An Earley Parsing Algorithm for Range Concatenation Grammars	claim
128	113	Chinese Term Extraction Using Different Types of Relevance	claim
129	113	Co-Feedback Ranking for Query-Focused Summarization	claim
130	113	The Modulation of Cooperation and Emotion in Dialogue: The REC Corpus	claim
131	112	Dependency Grammar Induction via Bitext Projection Constraints	claim
132	112	Dialogue Segmentation with Large Numbers of Volunteer Internet Annotators	claim
133	112	K-Best A* Parsing	claim
134	112	Minimized Models for Unsupervised Part-of-Speech Tagging	claim
135	112	Sub-Sentence Division for Tree-Based Machine Translation	claim
136	111	Setting Up User Action Probabilities in User Simulations for Dialog System Development	claim
137	110	The Chinese Aspect Generation Based on Aspect Selection Functions	claim
138	110	Incremental HMM Alignment for MT System Combination	claim
139	110	Improving Tree-to-Tree Translation with Packed Forests	claim
140	109	DEPEVAL(summ): Dependency-based Evaluation for Automatic Summaries	claim
141	109	Using Syntax to Disambiguate Explicit Discourse Connectives in Text	claim
142	109	A Novel Word Segmentation Approach for Written Languages with Word Boundary Markers	claim
143	108	Joint Decoding with Multiple Translation Models	claim
144	108	Improving data-driven dependency parsing using large-scale LFG grammars	claim
145	108	Multi-Document Summarization using Sentence-based Topic Models	claim
146	108	Bypassed alignment graph for learning coordination in Japanese sentences	claim
147	107	A Polynomial-Time Parsing Algorithm for TT-MCTAG	claim
148	107	Variational Inference for Grammar Induction with Prior Knowledge	claim
149	107	Play the Language: Play Coreference	claim
150	106	What lies beneath: Semantic and syntactic analysis of manually reconstructed spontaneous speech	claim
151	106	Realistic Grammar Error Simulation using Markov Logic	claim
152	106	iChi: a bilingual dictionary generating tool	claim
153	105	Linefeed Insertion into Japanese Spoken Monologue for Captioning	claim
154	105	Source-Language Entailment Modeling for Translating Unknown Terms	claim
155	105	Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria	claim
156	104	Recognizing Stances in Online Debates	claim
157	104	Capturing Salience with a Trainable Cache Model for Zero-anaphora Resolution	claim
158	104	Investigations on Word Senses and Word Usages	claim
159	104	Where's the Verb? Correcting Machine Translation During Question Answering	claim
160	104	Investigating Pitch Accent Recognition in Non-native Speech	claim
161	104	Optimizing Language Model Information Retrieval System with Expectation Maximization Algorithm	claim
162	103	Phrase Clustering for Discriminative Learning	claim
163	103	Correlating Human and Automatic Evaluation of a German Surface Realiser	claim
164	103	Sense-based Interpretation of Logical Metonymy Using a Statistical Method	claim
165	102	A Metric-based Framework for Automatic Taxonomy Induction	claim
166	102	A Gibbs Sampler for Phrasal Synchronous Grammar Induction	claim
167	102	The Lie Detector: Explorations in the Automatic Recognition of Deceptive Language	claim
168	102	Generalizing Dependency Features for Opinion Mining	claim
169	102	Incremental Parsing with Monotonic Adjoining Operation	claim
170	102	Hybrid Approach to User Intention Modeling for Dialog Simulation	claim
171	102	Paraphrase Recognition Using Machine Learning to Combine Similarity Measures	claim
172	101	Language Identification of Search Engine Queries	claim
173	101	Comparing Objective and Subjective Measures of Usability in a Human-Robot Dialogue System	claim
174	101	Parsing Speech Repair without Specialized Grammar Symbols	claim
175	100	Extending a Surface Realizer to Generate Coherent Discourse	claim
176	99	Exploiting Heterogeneous Treebanks for Parsing	claim
177	99	Jointly Identifying Temporal Relations with Markov Logic	claim
178	99	A Framework for Entailed Relation Recognition	claim
179	99	A Beam-Search Extraction Algorithm for Comparable Data	claim
180	98	Discovering the Discriminative Views: Measuring Term Weights for Sentiment Analysis	claim
181	98	A Unified Single Scan Algorithm for Japanese Base Phrase Chunking and Dependency Parsing	claim
182	96	Word or Phrase? Learning Which Unit to Stress for Information Retrieval	claim
183	96	Homophones and Tonal Patterns in English-Chinese Transliteration	claim
184	96	Automatic Compilation of Travel Information from Automatically Identified Travel Blogs	claim
185	94	Dependency Based Chinese Sentence Realization	claim
186	94	A Ranking Approach to Stress Prediction for Letter-to-Phoneme Conversion	claim
187	94	Prediction of Thematic Rank for Structured Semantic Role Labeling	claim
188	93	Paraphrase Identification as Probabilistic Quasi-Synchronous Recognition	claim
189	93	Learning with Annotation Noise	claim
190	93	Knowing the Unseen: Estimating Vocabulary Size over Unseen Samples	claim
191	93	A Rose is a Roos is a Ruusu: Querying Translations for Web Image Search	claim
192	93	Hierarchical Multi-Label Text Categorization with Global Margin Maximization	claim
193	93	Transfer Learning, Feature Selection and Word Sense Disambiguation	claim
194	92	Non-Projective Dependency Parsing in Expected Linear Time	claim
195	92	Efficient Inference of CRFs for Large-Scale Natural Language Data	claim
196	91	A Generative Blog Post Retrieval Model that Uses Query Expansion based on External Collections	claim
197	91	A Syntactic and Lexical-Based Discourse Segmenter	claim
198	91	Predicting Barge-in Utterance Errors by using Implicitly-Supervised ASR Accuracy and Barge-in Rate per User	claim
199	91	LX-Center: a center of online linguistic services	claim
200	90	Topological Field Parsing of German	claim
201	90	Capturing Errors in Written Chinese Words	claim
202	89	Variational Decoding for Statistical Machine Translation	claim
203	89	Mining Association Language Patterns for Negative Life Event Classification	claim
204	89	Updating a Name Tagger Using Contemporary Unlabeled Data	claim
205	89	Modeling Morphologically Rich Languages Using Split Words and Unstructured Dependencies	claim
206	88	Modeling Latent Biographic Attributes in Conversational Genres	claim
207	88	A Note on the Implementation of Hierarchical Dirichlet Processes	claim
208	88	The Backtranslation Score: Automatic MT Evalution at the Sentence Level without Reference Translations	claim
209	87	Fast Consensus Decoding over Translation Forests	claim
210	86	Extracting Lexical Reference Rules from Wikipedia	claim
211	86	A non-contiguous Tree Sequence Alignment-based Model for Statistical Machine Translation	claim
212	85	Directional Distributional Similarity for Lexical Expansion	claim
213	84	Transliteration Alignment	claim
214	84	Validating the web-based evaluation of NLG systems	claim
215	83	Distributional Representations for Handling Sparsity in Supervised Sequence-Labeling	claim
216	83	Insights into Non-projectivity in Hindi	claim
217	83	A Tool for Deep Semantic Encoding of Narrative Texts	claim
218	81	Phrase-Based Statistical Machine Translation as a Traveling Salesman Problem	claim
219	81	Toward finer-grained sentiment identification in product reviews through linguistic and ontological analyses	claim
220	79	Optimizing Word Alignment Combination For Phrase Table Training	claim
221	78	Improved Smoothing for N-gram Language Models Based on Ordinary Counts	claim
222	78	Leveraging Structural Relations for Fluent Compressions at Multiple Compression Rates	claim
223	78	From Extractive to Abstractive Meeting Summaries: Can It Be Done by Sentence Compression?	claim
224	76	Semi-Supervised Cause Identification from Aviation Safety Reports	claim
225	74	Predicting Unknown Time Arguments based on Cross-Event Propagation	claim
226	73	Clustering Technique in Multi-Document Personal Name Disambiguation	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers