ACL 2006 - PDF Preprint Papers

ACL 2006 Meeting of the Association for Computational Linguistics

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ACL-2006 Paper

click to vote

ACL
2006

226views Computational Linguistics» more ACL 2006»

Semi-Supervised Conditional Random Fields for Improved Sequence Segmentation and Labeling

13 years 6 months ago

Download www.metabolomics.ca

We present a new semi-supervised training procedure for conditional random fields (CRFs) that can be used to train sequence segmentors and labelers from a combination of labeled a...

Feng Jiao, Shaojun Wang, Chi-Hoon Lee, Russell Gre...

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	226	Semi-Supervised Conditional Random Fields for Improved Sequence Segmentation and Labeling	claim
2	223	Relation Extraction Using Label Propagation Based Semi-Supervised Learning	claim
3	217	Bootstrapping Path-Based Pronoun Resolution	claim
4	204	Boosting Statistical Word Alignment Using Labeled and Unlabeled Data	claim
5	200	Weakly Supervised Named Entity Transliteration and Discovery from Multilingual Comparable Corpora	claim
6	199	NLTK: The Natural Language Toolkit	claim
7	195	Conceptual Coherence in the Generation of Referring Expressions	claim
8	193	A Phrase-Based Statistical Model for SMS Text Normalization	claim
9	193	Prototype-Driven Grammar Induction	claim
10	184	Semantic Role Labeling via FrameNet, VerbNet and PropBank	claim
11	184	Modeling Commonality among Related Classes in Relation Extraction	claim
12	182	Automatically Extracting Nominal Mentions of Events with a Bootstrapped Probabilistic Classifier	claim
13	182	Morphological Richness Offsets Resource Demand - Experiences in Constructing a POS Tagger for Hindi	claim
14	180	Automatic Learning of Textual Entailments with Cross-Pair Similarities	claim
15	179	Combining Statistical and Knowledge-Based Spoken Language Understanding in Conditional Models	claim
16	177	Answer Extraction, Semantic Clustering, and Extractive Summarization for Clinical Question Answering	claim
17	174	URES : an Unsupervised Web Relation Extraction System	claim
18	173	Factorizing Complex Models: A Case Study in Mention Detection	claim
19	171	Discriminative Word Alignment with Conditional Random Fields	claim
20	164	Novel Association Measures Using Web Search with Double Checking	claim
21	163	A Clustered Global Phrase Reordering Model for Statistical Machine Translation	claim
22	162	MAGEAD: A Morphological Analyzer and Generator for the Arabic Dialects	claim
23	161	Minimum Risk Annealing for Training Log-Linear Models	claim
24	160	Learning to Predict Case Markers in Japanese	claim
25	157	Outilex, a Linguistic Platform for Text Processing	claim
26	157	Multi-Tagging for Lexicalized-Grammar Parsing	claim
27	156	Accurate Collocation Extraction Using a Multilingual Parser	claim
28	154	Discriminating Image Senses by Clustering with Multimodal Features	claim
29	153	Correcting ESL Errors Using Phrasal SMT Techniques	claim
30	153	Chinese-English Term Translation Mining Based on Semantic Prediction	claim
31	153	Analysis and Repair of Name Tagger Errors	claim
32	153	A Composite Kernel to Extract Relations between Entities with Both Flat and Structured Features	claim
33	150	Improved Discriminative Bilingual Word Alignment	claim
34	149	Subword-Based Tagging for Confidence-Dependent Chinese Word Segmentation	claim
35	148	A Hybrid Convolution Tree Kernel for Semantic Role Labeling	claim
36	148	Efficient Sentence Retrieval Based on Syntactic Structure	claim
37	148	A Hierarchical Bayesian Language Model Based On Pitman-Yor Processes	claim
38	148	Analysis of Selective Strategies to Build a Dependency-Analyzed Corpus	claim
39	147	Approximation Lasso Methods for Language Modeling	claim
40	147	Automated Japanese Essay Scoring System based on Articles Written by Experts	claim
41	146	An Effective Two-Stage Model for Exploiting Non-Local Dependencies in Named Entity Recognition	claim
42	146	A Logic-Based Semantic Approach to Recognizing Textual Entailment	claim
43	146	Left-to-Right Target Generation for Hierarchical Phrase-Based Translation	claim
44	146	Maximum Entropy Based Restoration of Arabic Diacritics	claim
45	145	Robust Word Sense Translation by EM Learning of Frame Semantics	claim
46	145	Multilingual Legal Terminology on the Jibiki Platform: The LexALP Project	claim
47	145	Discursive Usage of Six Chinese Punctuation Marks	claim
48	144	Argumentative Feedback: A Linguistically-Motivated Term Expansion for Information Retrieval	claim
49	144	A Best-First Probabilistic Shift-Reduce Parser	claim
50	143	An Empirical Study of Chinese Chunking	claim
51	142	Partially Specified Signatures: A Vehicle for Grammar Modularity	claim
52	142	Automatic Identification of Pro and Con Reasons in Online Reviews	claim
53	142	Improving the Scalability of Semi-Markov Conditional Random Fields for Named Entity Recognition	claim
54	141	Automatic Construction of Polarity-Tagged Corpus from HTML Documents	claim
55	141	A DOM Tree Alignment Model for Mining Parallel Data from the Web	claim
56	140	Discriminative Reranking for Semantic Parsing	claim
57	140	Guiding a Constraint Dependency Parser with Supertags	claim
58	140	Using String-Kernels for Learning Semantic Parsers	claim
59	140	A Comparison of Alternative Parse Tree Paths for Labeling Semantic Roles	claim
60	140	Word Sense Disambiguation Using Lexical Cohesion in the Context	claim
61	139	Statistical Phrase-Based Models for Interactive Computer-Assisted Translation	claim
62	138	Learning the Structure of Task-Driven Human-Human Dialogs	claim
63	138	Sub-Sentential Alignment Using Substring Co-Occurrence Counts	claim
64	138	Annotation Schemes and their Influence on Parsing Results	claim
65	137	Constraint-Based Sentence Compression: An Integer Programming Approach	claim
66	137	Stochastic Iterative Alignment for Machine Translation Evaluation	claim
67	137	Machine Learning of Temporal Relations	claim
68	137	Extraction of Tree Adjoining Grammars from a Treebank for Korean	claim
69	137	Modelling Lexical Redundancy for Machine Translation	claim
70	136	Japanese Dependency Parsing Using Co-Occurrence Information and a Combination of Case Elements	claim
71	136	A Pipeline Framework for Dependency Parsing	claim
72	136	Time Period Identification of Events in Text	claim
73	136	Unsupervised Topic Modelling for Multi-Party Spoken Discourse	claim
74	135	Direct Word Sense Matching for Lexical Substitution	claim
75	135	The Benefit of Stochastic PP Attachment to a Rule-Based Parser	claim
76	135	Tree-to-String Alignment Template for Statistical Machine Translation	claim
77	135	Word Alignment for Languages with Scarce Resources Using Bilingual Corpora of Other Language Pairs	claim
78	134	Distortion Models for Statistical Machine Translation	claim
79	134	Semi-Supervised Training for Statistical Word Alignment	claim
80	134	An Iterative Implicit Feedback Approach to Personalized Search	claim
81	134	Unsupervised Induction of Modern Standard Arabic Verb Classes Using Syntactic Frames and LSA	claim
82	134	The Effect of Translation Quality in MT-Based Cross-Language Information Retrieval	claim
83	133	Learning to Generate Naturalistic Utterances Using Reviews in Spoken Dialogue Systems	claim
84	132	Exploiting Comparable Corpora and Bilingual Dictionaries for Cross-Language Text Categorization	claim
85	132	Learning Transliteration Lexicons from the Web	claim
86	132	Optimal Constituent Alignment with Edge Covers for Semantic Projection	claim
87	131	Coreference Handling in XMG	claim
88	131	Event Extraction in a Plot Advice Agent	claim
89	131	Question Answering with Lexical Chains Propagating Verb Arguments	claim
90	131	Semantic Taxonomy Induction from Heterogenous Evidence	claim
91	130	N Semantic Classes are Harder than Two	claim
92	130	On-Demand Information Extraction	claim
93	129	Using Machine Learning Techniques to Build a Comma Checker for Basque	claim
94	129	Acceptability Prediction by Means of Grammaticality Quantification	claim
95	128	An Unsupervised Morpheme-Based HMM for Hebrew Morphological Disambiguation	claim
96	128	Archivus: A Multimodal System for Multimedia Meeting Browsing and Retrieval	claim
97	128	Creating a CCGbank and a Wide-Coverage CCG Lexicon for German	claim
98	128	Aligning Features with Sense Distinction Dimensions	claim
99	127	Detection of Quotations and Inserted Clauses and Its Application to Dependency Structure Analysis in Spontaneous Japanese	claim
100	127	Trace Prediction and Recovery with Unlexicalized PCFGs and Slash Features	claim
101	127	Inducing Word Alignments with Bilexical Synchronous Trees	claim
102	126	FAST - An Automatic Generation System for Grammar Tests	claim
103	126	Bayesian Query-Focused Summarization	claim
104	126	Hybrid Parsing: Using Probabilistic Models as Predictors for a Symbolic Parser	claim
105	126	Concept Unification of Terms in Different Languages for IR	claim
106	126	Training Conditional Random Fields with Multivariate Evaluation Measures	claim
107	125	A Bio-Inspired Approach for Multi-Word Expression Extraction	claim
108	125	Segment-Based Hidden Markov Models for Information Extraction	claim
109	125	Contextual Dependencies in Unsupervised Word Segmentation	claim
110	125	Unsupervised Segmentation of Chinese Text by Use of Branching Entropy	claim
111	125	Investigations on Event-Based Summarization	claim
112	125	A Grammatical Approach to Understanding Textual Tables Using Two-Dimensional SCFGs	claim
113	124	An Account for Compound Prepositions in Farsi	claim
114	124	Mildly Non-Projective Dependency Structures	claim
115	124	The Role of Information Retrieval in Answering Complex Questions	claim
116	124	Re-Usable Tools for Precision Machine Translation	claim
117	123	A Flexible Approach to Natural Language Generation for Disabled Children	claim
118	123	Topic-Focused Multi-Document Summarization Using an Approximate Oracle Score	claim
119	123	Discriminative Classifiers for Deterministic Dependency Parsing	claim
120	123	QuestionBank: Creating a Corpus of Parse-Annotated Questions	claim
121	123	Punjabi Machine Transliteration	claim
122	123	Simultaneous English-Japanese Spoken Language Translation Based on Incremental Dependency Parsing and Transfer	claim
123	122	Using WordNet to Automatically Deduce Relations between Words in Noun-Noun Compounds	claim
124	122	On2L - A Framework for Incremental Ontology Learning in Spoken Dialog Systems	claim
125	121	A Bootstrapping Approach to Unsupervised Detection of Cue Phrase Variants	claim
126	121	Models for Sentence Compression: A Comparison across Domains, Training Requirements and Evaluation Measures	claim
127	121	Parsing and Subcategorization Data	claim
128	121	Extractive Summarization using Inter- and Intra- Event Relevance	claim
129	121	Combination of Arabic Preprocessing Schemes for Statistical Machine Translation	claim
130	120	Unsupervised Part-of-Speech Tagging Employing Efficient Graph Clustering	claim
131	120	Unsupervised Analysis for Decipherment Problems	claim
132	120	Using Comparable Corpora to Solve Problems Difficult for Human Translators	claim
133	120	Maximum Entropy Based Phrase Reordering Model for Statistical Machine Translation	claim
134	119	Interpreting Semantic Relations in Noun Compounds via Verb Semantics	claim
135	119	An Equivalent Pseudoword Solution to Chinese Word Sense Disambiguation	claim
136	119	Annealing Structural Bias in Multilingual Weighted Grammar Induction	claim
137	118	Soft Syntactic Constraints for Word Alignment through Discriminative Training	claim
138	118	An End-to-End Discriminative Approach to Machine Translation	claim
139	117	A Collaborative Framework for Collecting Thai Unknown Words from the Web	claim
140	117	Automatic Classification of Verbs in Biomedical Texts	claim
141	117	Graph Transformations in Data-Driven Dependency Parsing	claim
142	117	Extracting Parallel Sub-Sentential Fragments from Non-Parallel Corpora	claim
143	117	From Prosodic Trees to Syntactic Trees	claim
144	117	Clavius: Bi-Directional Parsing for Generic Multimodal Interaction	claim
145	117	Translating HPSG-Style Outputs of a Robust Parser into Typed Dynamic Logic	claim
146	116	An All-Subtrees Approach to Unsupervised Parsing	claim
147	116	Minority Vote: At-Least-N Voting Improves Recall for Extracting Relations	claim
148	116	An Improved Redundancy Elimination Algorithm for Underspecified Representations	claim
149	116	Modeling Human Sentence Processing Data with a Statistical Parts-of-Speech Tagger	claim
150	116	Continuous Space Language Models for Statistical Machine Translation	claim
151	116	Integrated Morphological and Syntactic Disambiguation for Modern Hebrew	claim
152	116	Word Sense and Subjectivity	claim
153	115	A Modified Joint Source-Channel Model for Transliteration	claim
154	114	A Comparison of Document, Sentence, and Term Event Spaces	claim
155	114	Exploring Distributional Similarity Based Models for Query Spelling Correction	claim
156	114	Focus to Emphasize Tone Structures for Prosodic Analysis in Spoken Language Generation	claim
157	114	Valido: A Visual Tool for Validating Sense Annotations	claim
158	114	Infrastructure for Standardization of Asian Language Resources	claim
159	113	Evaluating the Accuracy of an Unlexicalized Statistical Parser on the PARC DepBank	claim
160	113	PCFGs with Syntactic and Prosodic Indicators of Speech Repairs	claim
161	113	Utilizing Co-Occurrence of Answers in Question Answering	claim
162	113	A Hybrid Relational Approach for WSD - First Results	claim
163	112	A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization	claim
164	112	Morphology-Syntax Interface for Turkish LFG	claim
165	112	Exploiting Syntactic Patterns as Clues in Zero-Anaphora Resolution	claim
166	112	Trimming CFG Parse Trees for Sentence Compression Using Machine Learning Approaches	claim
167	111	Using Machine-Learning to Assign Function Labels to Parser Output for Spanish	claim
168	111	Guessing Parts-of-Speech of Unknown Words Using Global Information	claim
169	111	Dependency Parsing of Japanese Spoken Monologue Based on Clause Boundaries	claim
170	110	Reduced n-gram Models for English and Chinese Corpora	claim
171	110	Speeding Up Full Syntactic Parsing by Leveraging Partial Parsing Decisions	claim
172	110	A Study on Automatically Extracted Keywords in Text Categorization	claim
173	110	A FrameNet-Based Semantic Role Labeler for Swedish	claim
174	110	Learning to Say It Well: Reranking Realizations by Predicted Synthesis Quality	claim
175	109	Estimating Class Priors in Domain Adaptation for Word Sense Disambiguation	claim
176	109	Exploiting Non-Local Features for Spoken Language Understanding	claim
177	109	Minimum Cut Model for Spoken Lecture Segmentation	claim
178	108	Local Constraints on Sentence Markers and Focus in Somali	claim
179	108	Polarized Unification Grammars	claim
180	108	Modeling Adjectives in Computational Relational Lexica	claim
181	107	MT Evaluation: Human-Like vs. Human Acceptable	claim
182	107	Ensemble Methods for Unsupervised WSD	claim
183	107	BiTAM: Bilingual Topic AdMixture Models for Word Alignment	claim
184	106	Enhancing Electronic Dictionaries with an Index Based on Associations	claim
185	106	Scalable Inference and Training of Context-Rich Syntactic Translation Models	claim
186	106	Leveraging Reusability: Cost-Effective Lexical Acquisition for Large-Scale Ontology Translation	claim
187	105	Automatic Creation of Domain Templates	claim
188	105	Exploring the Potential of Intractable Parsers	claim
189	105	Integrating Pattern-Based and Distributional Similarity Methods for Lexical Entailment Acquisition	claim
190	105	A Progressive Feature Selection Algorithm for Ultra Large Feature Spaces	claim
191	104	Unsupervised Relation Disambiguation Using Spectral Clustering	claim
192	104	Empirical Lower Bounds on the Complexity of Translational Equivalence	claim
193	103	Discriminative Pruning of Language Models for Chinese Word Segmentation	claim
194	103	Reranking and Self-Training for Parser Adaptation	claim
195	103	Error Mining in Parsing Results	claim
196	102	Semantic Retrieval for the Accurate Identification of Relational Concepts in Massive Textbases	claim
197	102	Whose Thumb Is It Anyway? Classifying Author Personality from Weblog Text	claim
198	102	Improving QA Accuracy by Question Inversion	claim
199	101	Highly Constrained Unification Grammars	claim
200	101	Examining the Content Load of Part of Speech Blocks for Information Retrieval	claim
201	101	Phoneme-to-Text Transcription System with an Infinite Vocabulary	claim
202	101	Learning Accurate, Compact, and Interpretable Tree Annotation	claim
203	100	The Second Release of the RASP System	claim
204	100	Factoring Synchronous Grammars by Sorting	claim
205	100	Semantic Parsing with Structured SVM Ensemble Classification Models	claim
206	100	A Discriminative Global Training Algorithm for Statistical MT	claim
207	99	Are These Documents Written from Different Perspectives? A Test of Different Perspectives Based on Statistical Distribution Divergence	claim
208	99	Learning Event Durations from Event Descriptions	claim
209	98	Reranking Answers for Definitional QA Using Language Modeling	claim
210	98	Exact Decoding for Jointly Labeling and Chunking Sequences	claim
211	98	Compiling a Lexicon of Cooking Actions for Animation Generation	claim
212	97	Semi-Supervised Learning of Partial Cognates Using Bilingual Bootstrapping	claim
213	97	Using Word Support Model to Improve Chinese Input System	claim
214	97	TwicPen: Hand-held Scanner and Translation Software for non-Native Readers	claim
215	96	GF Parallel Resource Grammars and Russian	claim
216	96	Meaningful Clustering of Senses Helps Boost Word Sense Disambiguation Performance	claim
217	95	Selection of Effective Contextual Information for Automatic Synonym Acquisition	claim
218	95	An Intermediate Representation for the Interpretation of Temporal Expressions	claim
219	94	Integrating Syntactic Priming into an Incremental Probabilistic Parser, with an Application to Psycholinguistic Modeling	claim
220	94	Noun Phrase Chunking in Hebrew: Influence of Lexical and Morphological Features	claim
221	94	K-QARD: A Practical Korean Question Answering Framework for Restricted Domain	claim
222	94	A Fast, Accurate Deterministic Parser for Chinese	claim
223	93	Combining Association Measures for Collocation Extraction	claim
224	93	Semantic Discourse Segmentation and Labeling for Route Instructions	claim
225	93	Advances in Discriminative Parsing	claim
226	92	A Finite-State Model of Human Sentence Processing	claim
227	92	A Phonetic-Based Approach to Chinese Chat Text Normalization	claim
228	91	Extracting Loanwords from Mongolian Corpora and Producing a Japanese-Mongolian Bilingual Dictionary	claim
229	91	Names and Similarities on the Web: Fact Extraction in the Fast Lane	claim
230	91	Using Machine Learning to Explore Human Multimodal Clarification Strategies	claim
231	91	Exploring Correlation of Dependency Relation Paths for Answer Extraction	claim
232	90	Obfuscating Document Stylometry to Preserve Author Anonymity	claim
233	90	Expressing Implicit Semantic Relations without Supervision	claim
234	89	Scaling Distributional Similarity to Large Corpora	claim
235	89	Dependencies between Student State and Speech Recognition Problems in Spoken Tutoring Dialogues	claim
236	88	A Rote Extractor with Edit Distance-Based Generalisation and Multi-Corpora Precision Calculation	claim
237	88	Towards Conversational QA: Automatic Identification of Problematic Situations and User Intent	claim
238	87	Measuring Language Divergence by Intra-Lexical Comparison	claim
239	87	Japanese Idiom Recognition: Drawing a Line between Literal and Idiomatic Meanings	claim
240	86	Towards A Modular Data Model For Multi-Layer Annotated Corpora	claim
241	86	Discourse Generation Using Utility-Trained Coherence Models	claim
242	86	Named Entity Transliteration with Comparable Corpora	claim
243	86	Sinhala Grapheme-to-Phoneme Conversion and Rules for Schwa Epenthesis	claim
244	86	Computational Analysis of Move Structures in Academic Abstracts	claim
245	85	Implementing a Characterization of Genre for Automatic Genre Identification of Web Pages	claim
246	84	Going Beyond AER: An Extensive Analysis of Word Alignments and Their Impact on MT	claim
247	84	Word Vectors and Two Kinds of Similarity	claim
248	83	Robust PCFG-Based Generation Using Automatically Acquired LFG Approximations	claim
249	82	Ontologizing Semantic Relations	claim
250	77	LexNet: A Graphical Environment for Graph-Based NLP	claim
251	75	A Term Recognition Approach to Acronym Recognition	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers