ACL 2010 - PDF Preprint Papers

ACL 2010 Meeting of the Association for Computational Linguistics

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ACL-2010 Paper

click to vote

ACL
2010

295views Computational Linguistics» more ACL 2010»

Open Information Extraction Using Wikipedia

13 years 2 months ago

Download aclweb.org

Information-extraction (IE) systems seek to distill semantic relations from naturallanguage text, but most systems use supervised learning of relation-specific examples and are th...

Fei Wu 0003, Daniel S. Weld

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	295	Open Information Extraction Using Wikipedia	claim
2	270	Wikipedia as Sense Inventory to Improve Diversity in Web Search Results	claim
3	239	How Many Words Is a Picture Worth? Automatic Caption Generation for News Images	claim
4	235	Bilingual Lexicon Generation Using Non-Aligned Signatures	claim
5	230	Cross-Lingual Latent Topic Extraction	claim
6	227	PCFGs, Topic Models, Adaptor Grammars and Learning Topical Collocations and the Structure of Proper Names	claim
7	224	Experiments in Graph-Based Semi-Supervised Learning Methods for Class-Instance Acquisition	claim
8	223	It Makes Sense: A Wide-Coverage Word Sense Disambiguation System for Free Text	claim
9	222	Hunting for the Black Swan: Risk Mining from Text	claim
10	220	The S-Space Package: An Open Source Package for Word Space Models	claim
11	217	Unsupervised Ontology Induction from Text	claim
12	214	Topic Models for Word Sense Disambiguation and Token-Based Idiom Detection	claim
13	211	Efficient Inference through Cascades of Weighted Tree Transducers	claim
14	209	Recommendation in Internet Forums and Blogs	claim
15	203	Active Learning-Based Elicitation for Semi-Supervised Word Alignment	claim
16	198	All Words Domain Adapted WSD: Finding a Middle Ground between Supervision and Unsupervision	claim
17	197	Automatic Generation of Story Highlights	claim
18	197	Convolution Kernel over Packed Parse Forest	claim
19	196	Speech-Driven Access to the Deep Web on Mobile Devices	claim
20	195	An Open-Source Package for Recognizing Textual Entailment	claim
21	193	Incorporating Extra-Linguistic Information into Reference Resolution in Collaborative Task Dialogue	claim
22	192	Automatically Generating Term Frequency Induced Taxonomies	claim
23	191	A Latent Dirichlet Allocation Method for Selectional Preferences	claim
24	191	Efficient Staggered Decoding for Sequence Labeling	claim
25	191	Balancing User Effort and Translation Error in Interactive Machine Translation via Confidence Measures	claim
26	190	Collocation Extraction beyond the Independence Assumption	claim
27	189	cdec: A Decoder, Alignment, and Learning Framework for Finite-State and Context-Free Translation Models	claim
28	187	Compositional Matrix-Space Models of Language	claim
29	185	Beetle II: A System for Tutoring and Computational Linguistics Experimentation	claim
30	184	Towards Open-Domain Semantic Role Labeling	claim
31	184	Word Representations: A Simple and General Method for Semi-Supervised Learning	claim
32	183	A Framework for Figurative Language Detection Based on Sense Differentiation	claim
33	182	Joint Syntactic and Semantic Parsing of Chinese	claim
34	182	Coreference Resolution with Reconcile	claim
35	181	Demonstration of a Prototype for a Conversational Companion for Reminiscing about Images	claim
36	180	Bucking the Trend: Large-Scale Cost-Focused Active Learning for Statistical Machine Translation	claim
37	180	Authorship Attribution Using Probabilistic Context-Free Grammars	claim
38	178	Combining Orthogonal Monolingual and Multilingual Sources of Evidence for All Words WSD	claim
39	178	Fully Unsupervised Core-Adjunct Argument Classification	claim
40	178	Improving Statistical Machine Translation with Monolingual Collocation	claim
41	178	Pseudo-Word for Phrase-Based Machine Translation	claim
42	178	Constituency to Dependency Translation with Forests	claim
43	178	Arabic Named Entity Recognition: Using Features Extracted from Noisy Data	claim
44	176	Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems	claim
45	176	An Active Learning Approach to Finding Related Terms	claim
46	176	Diversify and Combine: Improving Word Alignment for Machine Translation on Low-Resource Languages	claim
47	175	Towards Relational POMDPs for Adaptive Dialogue Management	claim
48	173	Using Parse Features for Preposition Selection and Error Detection	claim
49	171	A Joint Rule Selection Model for Hierarchical Phrase-Based Translation	claim
50	171	Talking NPCs in a Virtual Game World	claim
51	171	Detecting Experiences from Weblogs	claim
52	169	Modeling Norms of Turn-Taking in Multi-Party Conversation	claim
53	168	Boosting-Based System Combination for Machine Translation	claim
54	168	Learning 5000 Relational Extractors	claim
55	168	Learning Arguments and Supertypes of Semantic Relations Using Recursive Patterns	claim
56	168	Automatic Evaluation Method for Machine Translation Using Noun-Phrase Chunking	claim
57	167	A Hybrid Hierarchical Model for Multi-Document Summarization	claim
58	167	Hindi-to-Urdu Machine Translation through Transliteration	claim
59	167	The Manually Annotated Sub-Corpus: A Community Resource for and by the People	claim
60	167	Unsupervised Search for the Optimal Segmentation for Statistical Machine Translation	claim
61	167	Edit Tree Distance Alignments for Semantic Role Labelling	claim
62	166	Structural Semantic Relatedness: A Knowledge-Based Method to Named Entity Disambiguation	claim
63	166	Bootstrapping Semantic Analyzers from Non-Contradictory Texts	claim
64	166	"Was It Good? It Was Provocative." Learning the Meaning of Scalar Adjectives	claim
65	166	Practical Very Large Scale CRFs	claim
66	166	Word Alignment with Synonym Regularization	claim
67	166	Event-Based Hyperspace Analogue to Language for Query Expansion	claim
68	165	Efficient Third-Order Dependency Parsers	claim
69	165	Bilingual Sense Similarity for Statistical Machine Translation	claim
70	165	Tools for Multilingual Grammar-Based Translation on the Web	claim
71	164	The Importance of Rule Restrictions in CCG	claim
72	164	"Ask Not What Textual Entailment Can Do for You..."	claim
73	164	Unsupervised Discourse Segmentation of Documents with Inherently Parallel Structure	claim
74	164	Tackling Sparse Data Issue in Machine Translation Evaluation	claim
75	163	Automatic Evaluation of Linguistic Quality in Multi-Document Summarization	claim
76	161	Detecting Errors in Automatically-Parsed Dependency Relations	claim
77	161	Importance-Driven Turn-Bidding for Spoken Dialogue Systems	claim
78	160	Training Phrase Translation Models with Leaving-One-Out	claim
79	160	A Unified Graph Model for Sentence-Based Opinion Retrieval	claim
80	160	A Bayesian Method for Robust Estimation of Distributional Similarities	claim
81	160	Improving Chinese Semantic Role Labeling with Rich Syntactic Features	claim
82	158	BabelNet: Building a Very Large Multilingual Semantic Network	claim
83	158	Unsupervised Event Coreference Resolution with Rich Linguistic Features	claim
84	157	A Game-Theoretic Model of Metaphorical Bargaining	claim
85	157	Learning Script Knowledge with Web Experiments	claim
86	157	Fixed Length Word Suffix for Factored Statistical Machine Translation	claim
87	156	Supervised Noun Phrase Coreference Research: The First Fifteen Years	claim
88	156	Temporal Information Processing of a New Language: Fast Porting with Minimal Resources	claim
89	156	Accurate Context-Free Parsing with Combinatory Categorial Grammar	claim
90	155	Employing Personal/Impersonal Views in Supervised and Semi-Supervised Sentiment Classification	claim
91	155	Cross-Language Document Summarization Based on Machine Translation Quality Prediction	claim
92	155	Better Filtration and Augmentation for Hierarchical Phrase-Based Translation Rules	claim
93	154	Fine-Grained Tree-to-String Translation Rule Extraction	claim
94	153	Generating Templates of Entity Summaries with an Entity-Aspect Model and Pattern Mining	claim
95	153	A Rational Model of Eye Movement Control in Reading	claim
96	153	Distributional Similarity vs. PU Learning for Entity Set Expansion	claim
97	152	A Taxonomy, Dataset, and Classifier for Automatic Noun Compound Interpretation	claim
98	152	Optimal Rank Reduction for Linear Context-Free Rewriting Systems with Fan-Out Two	claim
99	152	Using Document Level Cross-Event Inference to Improve Event Extraction	claim
100	151	Comparable Entity Mining from Comparative Questions	claim
101	151	Exploring Syntactic Structural Features for Sub-Tree Alignment Using Bilingual Tree Kernels	claim
102	151	Domain Adaptation of Maximum Entropy Language Models	claim
103	151	Jointly Optimizing a Two-Step Conditional Random Field Model for Machine Transliteration and Its Fast Decoding Algorithm	claim
104	150	Extraction and Approximation of Numerical Attributes from the Web	claim
105	150	Improved Unsupervised POS Induction through Prototype Discovery	claim
106	149	Sentence and Expression Level Annotation of Opinions in User-Generated Discourse	claim
107	149	Hierarchical Joint Learning: Improving Joint Parsing and Named Entity Recognition with Non-Jointly Labeled Data	claim
108	149	Adapting Self-Training for Semantic Role Labeling	claim
109	148	Contextualizing Semantic Representations Using Syntactically Enriched Vector Models	claim
110	148	Hard Constraints for Grammatical Function Labelling	claim
111	148	Faster Parsing by Supertagger Adaptation	claim
112	148	Last but Definitely Not Least: On the Role of the Last Sentence in Automatic Polarity-Classification	claim
113	148	Automatically Generating Annotator Rationales to Improve Sentiment Classification	claim
114	147	Improving the Use of Pseudo-Words for Evaluating Selectional Preferences	claim
115	147	A Cognitive Cost Model of Annotations Based on Eye-Tracking Data	claim
116	147	Starting from Scratch in Semantic Role Labeling	claim
117	147	Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities	claim
118	146	Dependency Parsing and Projection Based on Word-Pair Classification	claim
119	146	Multilingual Pseudo-Relevance Feedback: Performance Study of Assisting Languages	claim
120	146	Automated Planning for Situated Natural Language Generation	claim
121	146	Dynamic Programming for Linear-Time Incremental Parsing	claim
122	146	Models of Metaphor in NLP	claim
123	146	Entity-Based Local Coherence Modelling Using Topological Fields	claim
124	146	Evaluating Machine Translations Using mNCD	claim
125	146	Complexity Assumptions in Ontology Verbalisation	claim
126	146	Sentiment Translation through Lexicon Induction	claim
127	146	Automatic Selectional Preference Acquisition for Latin Verbs	claim
128	145	Bayesian Synchronous Tree-Substitution Grammar Induction and Its Application to Sentence Compression	claim
129	145	Metadata-Aware Measures for Answer Summarization in Community Question Answering	claim
130	145	A New Approach to Improving Multilingual Summarization Using a Genetic Algorithm	claim
131	145	Open-Domain Semantic Role Labeling by Modeling Word Spans	claim
132	145	The Prevalence of Descriptive Referring Expressions in News and Narrative	claim
133	145	Paraphrase Lattice for Statistical Machine Translation	claim
134	145	An Entity-Level Approach to Information Extraction	claim
135	144	Understanding the Semantic Structure of Noun Phrase Queries	claim
136	144	Evaluating Multilanguage-Comparability of Subjectivity Analysis Systems	claim
137	144	Phylogenetic Grammar Induction	claim
138	144	Learning Phrase-Based Spelling Error Models from Clickthrough Data	claim
139	144	Cognitively Plausible Models of Human Language Processing	claim
140	144	The Impact of Interpretation Problems on Tutorial Dialogue	claim
141	144	Correcting Errors in a Treebank Based on Synchronous Tree Substitution Grammar	claim
142	144	How Spoken Language Corpora Can Refine Current Speech Motor Training Methodologies	claim
143	143	Generating Focused Topic-Specific Sentiment Lexicons	claim
144	142	A Study of Information Retrieval Weighting Schemes for Sentiment Analysis	claim
145	142	Optimising Information Presentation for Spoken Dialogue Systems	claim
146	142	Generating Image Descriptions Using Dependency Relational Patterns	claim
147	142	Finding Cognate Groups Using Phylogenies	claim
148	142	Blocked Inference in Bayesian Tree Substitution Grammars	claim
149	141	Global Learning of Focused Entailment Graphs	claim
150	141	Phrase-Based Statistical Language Generation Using Graphical Models and Active Learning	claim
151	141	Creating Robust Supervised Classifiers via Web-Scale N-Gram Data	claim
152	140	The Human Language Project: Building a Universal Corpus of the World's Languages	claim
153	140	A Transition-Based Parser for 2-Planar Dependency Structures	claim
154	140	Discriminative Modeling of Extraction Sets for Machine Translation	claim
155	140	Error Detection for Statistical Machine Translation Using Linguistic Features	claim
156	140	Inducing Domain-Specific Semantic Class Taggers from (Almost) Nothing	claim
157	140	Generating Fine-Grained Reviews of Songs from Album Reviews	claim
158	140	Identifying Text Polarity Using Random Walks	claim
159	140	Letter-Phoneme Alignment: An Exploration	claim
160	139	Viterbi Training for PCFGs: Hardness Results and Competitiveness of Uniform Initialization	claim
161	139	Learning to Translate with Source and Target Syntax	claim
162	139	The Influence of Discourse on Syntax: A Psycholinguistic Model of Sentence Processing	claim
163	139	Coreference Resolution across Corpora: Languages, Coding Schemes, and Preprocessing Information	claim
164	139	Learning Lexicalized Reordering Models from Reordering Graphs	claim
165	138	Latent Variable Models of Selectional Preference	claim
166	138	On Learning Subtypes of the Part-Whole Relation: Do Not Mix Your Seeds	claim
167	138	Computing Weakest Readings	claim
168	138	Optimizing Informativeness and Readability for Sentiment Summarization	claim
169	138	SVD and Clustering for Unsupervised POS Tagging	claim
170	137	A Tree Transducer Model for Synchronous Tree-Adjoining Grammars	claim
171	137	SystemT: An Algebraic Approach to Declarative Information Extraction	claim
172	137	Bitext Dependency Parsing with Bilingual Subtree Constraints	claim
173	137	Cross Lingual Adaptation: An Experiment on Sentiment Classifications	claim
174	137	Expanding Verb Coverage in Cyc with VerbNet	claim
175	137	Automatic Sanskrit Segmentizer Using Finite State Transducers	claim
176	137	The Use of Formal Language Models in the Typology of the Morphology of Amerindian Languages	claim
177	136	Using Smaller Constituents Rather Than Sentences in Active Learning for Japanese Dependency Parsing	claim
178	136	Untangling the Cross-Lingual Link Structure of Wikipedia	claim
179	136	Decision Detection Using Hierarchical Graphical Models	claim
180	135	Bridging SMT and TM with Translation Recommendation	claim
181	135	Minimized Models and Grammar-Informed Initialization for Supertagging with Highly Ambiguous Lexicons	claim
182	135	Assessing the Role of Discourse References in Entailment Inference	claim
183	135	Discriminative Pruning for Discriminative ITG Alignment	claim
184	135	Reading between the Lines: Learning to Map High-Level Instructions to Commands	claim
185	135	Preferences versus Adaptation during Referring Expression Generation	claim
186	135	Using Speech to Reply to SMS Messages While Driving: An In-Car Simulator User Study	claim
187	135	Importance of Linguistic Constraints in Statistical Dependency Parsing	claim
188	135	Mood Patterns and Affective Lexicon Access in Weblogs	claim
189	135	Personalising Speech-To-Speech Translation in the EMIME Project	claim
190	134	Simple Semi-Supervised Training of Part-Of-Speech Taggers	claim
191	134	Hierarchical Sequential Learning for Extracting Opinions and Their Attributes	claim
192	134	Weakly Supervised Learning of Presupposition Relations between Verbs	claim
193	133	A Statistical Model for Lost Language Decipherment	claim
194	133	Estimating Strictly Piecewise Distributions	claim
195	133	Simultaneous Tokenization and Part-Of-Speech Tagging for Arabic without a Morphological Analyzer	claim
196	133	Wrapping up a Summary: From Representation to Generation	claim
197	133	A Probabilistic Generative Model for an Intermediate Constituency-Dependency Representation	claim
198	132	Identifying Non-Explicit Citing Sentences for Citation-Based Summarization	claim
199	132	Fine-Grained Genre Classification Using Structural Learning Algorithms	claim
200	131	Knowledge-Rich Word Sense Disambiguation Rivaling Supervised Systems	claim
201	131	Learning Common Grammar from Multilingual Corpus	claim
202	131	Exemplar-Based Models for Word Meaning in Context	claim
203	131	WSD as a Distributed Constraint Optimization Problem	claim
204	131	Grammar Prototyping and Testing with the LinGO Grammar Matrix Customization System	claim
205	130	Conditional Random Fields for Word Hyphenation	claim
206	130	Complexity Metrics in an Incremental Right-Corner Parser	claim
207	130	Automatic Collocation Suggestion in Academic Writing	claim
208	130	Non-Cooperation in Dialogue	claim
209	129	Extracting Social Networks from Literary Fiction	claim
210	129	Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates	claim
211	129	On the Computational Complexity of Dominance Links in Grammatical Formalisms	claim
212	129	Learning Better Data Representation Using Inference-Driven Metric Learning	claim
213	128	Profiting from Mark-Up: Hyper-Text Annotations for Guided Parsing	claim
214	128	Correcting Errors in Speech Recognition with Articulatory Dynamics	claim
215	128	Hierarchical Search for Word Alignment	claim
216	128	Transition-Based Parsing with Confidence-Weighted Classification	claim
217	127	Plot Induction and Evolutionary Search for Story Generation	claim
218	127	Simple, Accurate Parsing with an All-Fragments Grammar	claim
219	127	Optimizing Question Answering Accuracy by Maximizing Log-Likelihood	claim
220	127	Intelligent Selection of Language Model Training Data	claim
221	126	On Jointly Recognizing and Aligning Bilingual Named Entities	claim
222	126	Towards Robust Multi-Tool Tagging. An OWL/DL-Based Approach	claim
223	126	Sentiment Learning on Product Reviews via Sentiment Ontology Tree	claim
224	126	Predicate Argument Structure Analysis Using Transformation Based Learning	claim
225	126	Growing Related Words from Seed via User Behaviors: A Re-Ranking Based Approach	claim
226	125	Sparsity in Dependency Grammar Induction	claim
227	125	Generating Entailment Rules from FrameNet	claim
228	125	Semantics-Driven Shallow Parsing for Chinese Semantic Role Labeling	claim
229	124	A Structured Model for Joint Learning of Argument Roles and Predicate Senses	claim
230	121	Learning to Follow Navigational Directions	claim
231	121	Tree-Based Deterministic Dependency Parsing - An Application to Nivre's Method -	claim
232	121	The Same-Head Heuristic for Coreference	claim
233	119	TrustRank: Inducing Trust in Automatic Translations via Ranking	claim
234	117	Classification of Feedback Expressions in Multimodal Data	claim
235	117	WebLicht: Web-Based LRT Services for German	claim
236	116	Vocabulary Choice as an Indicator of Perspective	claim
237	116	Hierarchical A* Parsing with Bridge Outside Scores	claim
238	115	A Generalized-Zero-Preserving Method for Compact Encoding of Concept Lattices	claim
239	115	Extracting Sequences from the Web	claim
240	114	A Hybrid Rule/Model-Based Finite-State Framework for Normalizing SMS Messages	claim
241	113	An Exact A* Method for Deciphering Letter-Substitution Ciphers	claim
242	113	Top-Down K-Best A* Parsing	claim
243	113	Using Anaphora Resolution to Improve Opinion Target Identification in Movie Reviews	claim
244	113	Online Generation of Locality Sensitive Hash Signatures	claim
245	112	Combining Data and Mathematical Models of Language Change	claim
246	109	Rebanking CCGbank for Improved NP Interpretation	claim
247	109	Now, Where Was I? Resumption Strategies for an In-Vehicle Dialogue System	claim
248	108	Identifying Generic Noun Phrases	claim
249	106	String Extension Learning	claim
250	105	Learning Word-Class Lattices for Definition and Hypernym Extraction	claim
251	99	Syntactic and Semantic Factors in Processing Difficulty: An Integrated Measure	claim
252	97	A Risk Minimization Framework for Extractive Speech Summarization	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers