ACL 2008 - PDF Preprint Papers

ACL 2008 Meeting of the Association for Computational Linguistics

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ACL-2008 Paper

click to vote

ACL
2008

263views Computational Linguistics» more ACL 2008»

Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data

14 years 1 months ago

Download aclweb.org

This paper provides evidence that the use of more unlabeled data in semi-supervised learning can improve the performance of Natural Language Processing (NLP) tasks, such as part-o...

Jun Suzuki, Hideki Isozaki

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	263	Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data	claim
2	213	Generalized Expectation Criteria for Semi-Supervised Learning of Conditional Random Fields	claim
3	204	Interactive Visualization for Computational Linguistics	claim
4	195	Enriching Morphologically Poor Languages for Statistical Machine Translation	claim
5	183	Exploiting Feature Hierarchy for Transfer Learning in Named Entity Recognition	claim
6	177	BART: A Modular Toolkit for Coreference Resolution	claim
7	175	Applying Morphology Generation Models to Machine Translation	claim
8	174	Automatic Editing in a Back-End Speech-to-Text System	claim
9	174	A Critical Reassessment of Evaluation Baselines for Speech Summarization	claim
10	173	Combining Multiple Resources to Improve SMT-based Paraphrasing Model	claim
11	173	Inducing Gazetteers for Named Entity Recognition by Large-Scale Clustering of Dependency Relations	claim
12	172	Integrating Graph-Based and Transition-Based Dependency Parsers	claim
13	171	Unsupervised Translation Induction for Chinese Abbreviations using Monolingual Corpora	claim
14	171	Cohesive Phrase-Based Decoding for Statistical Machine Translation	claim
15	170	Bayesian Learning of Non-Compositional Phrases with Synchronous Parsing	claim
16	169	Recent Improvements in the CMU Large Scale Chinese-English SMT System	claim
17	168	A Probabilistic Model for Fine-Grained Expert Search	claim
18	168	Distributed Word Clustering for Large Scale Class-Based Language Modeling in Machine Translation	claim
19	168	Unsupervised Learning of Acoustic Sub-word Units	claim
20	162	When Specialists and Generalists Work Together: Overcoming Domain Dependence in Sentiment Tagging	claim
21	161	Blog Categorization Exploiting Domain Dictionary and Dynamically Estimated Domains of Unknown Words	claim
22	160	Mining Parenthetical Translations from the Web by Word Alignment	claim
23	159	Decompounding query keywords from compounding languages	claim
24	158	Automatic Image Annotation Using Auxiliary Text Information	claim
25	158	Combining Source and Target Language Information for Name Tagging of Machine Translation Output	claim
26	158	Multi-domain Sentiment Classification	claim
27	156	Joint Word Segmentation and POS Tagging Using a Single Perceptron	claim
28	154	Soft Syntactic Constraints for Hierarchical Phrased-Based Translation	claim
29	154	Using Conditional Random Fields to Extract Contexts and Answers of Questions from Online Forums	claim
30	153	Pairwise Document Similarity in Large Collections with MapReduce	claim
31	152	Unsupervised Discovery of Generic Relationships Using Pattern Clusters and its Evaluation by Automatically Generated SAT Analogy Questions	claim
32	152	Learning Semantic Links from a Corpus of Parallel Temporal and Causal Relations	claim
33	151	Semantic Role Labeling Systems for Arabic using Kernel Methods	claim
34	151	A Supervised Learning Approach to Automatic Synonym Identification Based on Distributional Features	claim
35	150	A Discriminative Latent Variable Model for Statistical Machine Translation	claim
36	150	Improving Search Results Quality by Customizing Summary Lengths	claim
37	150	The QuALiM Question Answering Demo: Supplementing Answers with Paragraphs drawn from Wikipedia	claim
38	149	Extraction of Entailed Semantic Relations Through Syntax-Based Comma Resolution	claim
39	149	Arabic Language Modeling with Finite State Transducers	claim
40	148	Event Matching Using the Transitive Closure of Dependency Relations	claim
41	147	Automatic Syllabification with Structured SVMs for Letter-to-Phoneme Conversion	claim
42	146	Enhancing Performance of Lexicalised Grammars	claim
43	145	Better Alignments = Better Translations?	claim
44	145	Name Translation in Statistical Machine Translation - Learning When to Transliterate	claim
45	144	An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming	claim
46	144	Ad Hoc Treebank Structures	claim
47	144	Active Sample Selection for Named Entity Transliteration	claim
48	143	A Linguistically Annotated Reordering Model for BTG-based Statistical Machine Translation	claim
49	142	Classification of Semantic Relationships between Nominals Using Pattern Clusters	claim
50	140	Credibility Improves Topical Blog Post Retrieval	claim
51	140	The Tradeoffs Between Open and Traditional Relation Extraction	claim
52	140	MAXSIM: A Maximum Similarity Metric for Machine Translation Evaluation	claim
53	140	Contextual Preferences	claim
54	140	Arabic Morphological Tagging, Diacritization, and Lemmatization Using Lexeme Models and Feature Ranking	claim
55	140	Dimensions of Subjectivity in Natural Language	claim
56	139	Improving Parsing and PP Attachment Performance with Sense Information	claim
57	139	Parsing Noun Phrase Structure with CCG	claim
58	139	Introduction to Computational Advertising	claim
59	138	Phrase Table Training for Precision and Recall: What Makes a Good Phrase and a Good Phrase Pair?	claim
60	138	A Generic Sentence Trimmer with CRFs	claim
61	138	Assessing the Costs of Sampling Methods in Active Learning for Annotation	claim
62	138	Beyond Log-Linear Models: Boosted Minimum Error Rate Training for N-best Re-ranking	claim
63	138	FastSum: Fast and Accurate Query-based Multi-document Summarization	claim
64	137	Semantic Class Learning from the Web with Hyponym Pattern Linkage Graphs	claim
65	137	Active Learning with Confidence	claim
66	136	A Joint Model of Text and Aspect Ratings for Sentiment Summarization	claim
67	136	A Subcategorization Acquisition System for French Verbs	claim
68	136	Mixture Model POMDPs for Efficient Handling of Uncertainty in Dialogue Management	claim
69	135	A Single Generative Model for Joint Morphological Segmentation and Syntactic Parsing	claim
70	135	Efficient, Feature-based, Conditional Random Field Parsing	claim
71	135	Applying a Grammar-Based Language Model to a Simplified Broadcast-News Transcription Task	claim
72	135	Choosing Sense Distinctions for WSD: Psycholinguistic Evidence	claim
73	134	Sentence Simplification for Semantic Role Labeling	claim
74	134	A Hierarchical Approach to Encoding Medical Concepts for Clinical Notes	claim
75	134	Enforcing Transitivity in Coreference Resolution	claim
76	133	Assessing Dialog System User Simulation Evaluation Measures Using Human Judges	claim
77	133	Improving the Performance of the Random Walk Model for Answering Complex Questions	claim
78	132	Generating Impact-Based Summaries for Scientific Literature	claim
79	132	EM Can Find Pretty Good HMM POS-Taggers (When Given a Good Start)	claim
80	131	Selecting Query Term Alternations for Web Search by Exploiting Query Contexts	claim
81	131	Vector-based Models of Semantic Composition	claim
82	131	Demonstration of the UAM CorpusTool for Text and Image Annotation	claim
83	131	Adaptive Language Modeling for Word Prediction	claim
84	131	Computing Confidence Scores for All Sub Parse Trees	claim
85	131	Kernels on Linguistic Structures for Answer Extraction	claim
86	130	Gestural Cohesion for Topic Segmentation	claim
87	129	Phrase Chunking Using Entropy Guided Transformation Learning	claim
88	129	Interactive ASR Error Correction for Touchscreen Devices	claim
89	129	Evolving New Lexical Association Measures Using Genetic Programming	claim
90	128	Unsupervised Learning of Narrative Event Chains	claim
91	128	A Deductive Approach to Dependency Parsing	claim
92	128	A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model	claim
93	128	Mining Wikipedia Revision Histories for Improving Sentence Compression	claim
94	128	Distributed Listening: A Parallel Processing Approach to Automatic Speech Recognition	claim
95	127	Learning to Rank Answers on Large Online QA Collections	claim
96	127	Collecting a Why-Question Corpus for Development and Evaluation of an Automatic QA-System	claim
97	127	Learning Effective Multimodal Dialogue Strategies from Wizard-of-Oz Data: Bootstrapping and Evaluation	claim
98	127	Linguistically Motivated Features for Enhanced Back-of-the-Book Indexing	claim
99	126	Mining Wiki Resources for Multilingual Named Entity Recognition	claim
100	126	Chinese-English Backward Transliteration Assisted with Mining Monolingual Web Pages	claim
101	125	Correlation between ROUGE and Human Evaluation of Extractive Meeting Summaries	claim
102	124	Demonstration of a POMDP Voice Dialer	claim
103	124	Inferring Activity Time in News through Event Modeling	claim
104	124	splitSVM: Fast, Space-Efficient, non-Heuristic, Polynomial Kernel Computation for NLP Applications	claim
105	124	Text Segmentation with LDA-Based Fisher Kernel	claim
106	123	Semi-Supervised Convex Training for Dependency Parsing	claim
107	123	Learning Document-Level Semantic Properties from Free-Text Annotations	claim
108	122	Learning Bilingual Lexicons from Monolingual Corpora	claim
109	122	Enriching Spoken Language Translation with Dialog Acts	claim
110	120	Task-oriented Evaluation of Syntactic Parsers and Their Representations	claim
111	120	Grounded Language Modeling for Automatic Speech Recognition of Sports Video	claim
112	119	Forest Reranking: Discriminative Parsing with Non-Local Features	claim
113	119	Combining Speech Retrieval Results with Generalized Additive Models	claim
114	119	Finding Contradictions in Text	claim
115	119	Using Adaptor Grammars to Identify Synergies in the Unsupervised Acquisition of Linguistic Structure	claim
116	119	A Re-examination of Query Expansion Using Lexical Resources	claim
117	118	You Talking to Me? A Corpus and Algorithm for Conversation Disentanglement	claim
118	118	An Unsupervised Approach to Biography Production Using Wikipedia	claim
119	118	A Tree Sequence Alignment-based Tree-to-Tree Translation Model	claim
120	118	Summarizing Emails with Conversational Cohesion and Subjectivity	claim
121	118	An Integraged Architecture for Generating Parenthetical Constructions	claim
122	118	High Frequency Word Entrainment in Spoken Dialogue	claim
123	118	The Complexity of Phrase Alignment Problems	claim
124	117	Which Are the Best Features for Automatic Verb Classification	claim
125	117	Distributional Identification of Non-Referential Pronouns	claim
126	117	Randomized Language Models via Perfect Hash Functions	claim
127	116	Contradictions and Justifications: Extensions to the Textual Entailment Task	claim
128	116	The Role of Positive Feedback in Intelligent Tutoring Systems	claim
129	115	A Logical Basis for the D Combinator and Normal Form in CCG	claim
130	115	Can You Summarize This? Identifying Correlates of Input Difficulty for Multi-Document Summarization	claim
131	115	A Novel Feature-based Approach to Chinese Entity Relation Extraction	claim
132	114	Yawat: Yet Another Word Alignment Tool	claim
133	114	Construct State Modification in the Arabic Treebank	claim
134	114	Icelandic Data Driven Part of Speech Tagging	claim
135	113	Simple Semi-supervised Dependency Parsing	claim
136	113	Correcting Misuse of Verb Forms	claim
137	113	SIDE: The Summarization Integrated Development Environment	claim
138	113	Impact of Initiative on Collaborative Problem Solving	claim
139	112	Robustness and Generalization of Role Sets: PropBank vs. VerbNet	claim
140	112	Trainable Generation of Big-Five Personality Styles through Data-Driven Parameter Estimation	claim
141	112	Solving Relational Similarity Problems Using the Web as a Corpus	claim
142	112	Efficient Multi-Pass Decoding for Synchronous Context Free Grammars	claim
143	112	Lexicalized Phonotactic Word Segmentation	claim
144	112	Hypertagging: Supertagging for Surface Realization with CCG	claim
145	112	Coreference-inspired Coherence Modeling	claim
146	112	Extracting a Representation from Text for Semantic Analysis	claim
147	112	Segmentation for English-to-Arabic Statistical Machine Translation	claim
148	111	Generalizing Word Lattice Translation	claim
149	111	Evaluating Word Prediction: Framing Keystroke Savings	claim
150	110	Evaluating a Crosslinguistic Grammar Resource: A Case Study of Wambaya	claim
151	110	Unsupervised Lexicon-Based Resolution of Unknown Words for Full Morphological Analysis	claim
152	110	Query-based Sentence Fusion is Better Defined and Leads to More Preferred Results than Generic Sentence Fusion	claim
153	110	Using Structural Information for Identifying Similar Chinese Characters	claim
154	109	Dictionary Definitions based Homograph Identification using a Generative Hierarchical Model	claim
155	108	Hedge Classification in Biomedical Texts with a Weakly Supervised Selection of Keywords	claim
156	108	Pivot Approach for Extracting Paraphrase Patterns from Bilingual Corpora	claim
157	108	Machine Translation System Combination using ITG-based Alignments	claim
158	107	Measure Word Generation for English-Chinese SMT Systems	claim
159	107	Lyric-based Song Sentiment Classification with Sentiment Vector Space Model	claim
160	107	Adapting a WSJ-Trained Parser to Grammatically Noisy Text	claim
161	106	Searching Questions by Identifying Question Topic and Question Focus	claim
162	106	Learning Bigrams from Unigrams	claim
163	106	PDT 2.0 Requirements on a Query Language	claim
164	106	Analyzing the Errors of Unsupervised Learning	claim
165	106	Intrinsic vs. Extrinsic Evaluation Measures for Referring Expression Generation	claim
166	106	Extractive Summaries for Educational Science Content	claim
167	106	You've Got Answers: Towards Personalized Models for Predicting Success in Community Question Answering	claim
168	106	Combined One Sense Disambiguation of Abbreviations	claim
169	105	Refining Event Extraction through Cross-Document Inference	claim
170	105	Generating Research Websites Using Summarisation Techniques	claim
171	105	Language Dynamics and Capitalization using Maximum Entropy	claim
172	104	Joint Processing and Discriminative Training for Letter-to-Phoneme Conversion	claim
173	103	A Cascaded Linear Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging	claim
174	103	Large Scale Acquisition of Paraphrases for Learning Surface Patterns	claim
175	103	An Unsupervised Vector Approach to Biomedical Term Disambiguation: Integrating UMLS and Medline	claim
176	102	The Good, the Bad, and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words	claim
177	102	Surprising Parser Actions and Reading Difficulty	claim
178	101	Unsupervised Multilingual Learning for Morphological Segmentation	claim
179	101	Multi-Task Active Learning for Linguistic Annotations	claim
180	101	Smoothing a Tera-word Language Model	claim
181	101	Unlexicalised Hidden Variable Models of Split Dependency Grammars	claim
182	100	Evaluating Roget's Thesauri	claim
183	100	Intensional Summaries as Cooperative Responses in Dialogue: Automation and Evaluation	claim
184	99	Forest-Based Translation	claim
185	99	In-Browser Summarisation: Generating Elaborative Summaries Biased Towards the Reading Context	claim
186	98	Regular Tree Grammars as a Formalism for Scope Underspecification	claim
187	98	Multilingual Harvesting of Cross-Cultural Stereotypes	claim
188	98	Robust Dialog Management with N-Best Hypotheses Using Dialog Examples and Agenda	claim
189	97	Efficient Processing of Underspecified Discourse Representations	claim
190	96	Word Clustering and Word Selection Based Feature Reduction for MaxEnt Based Hindi NER	claim
191	96	Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System	claim
192	95	A Unified Syntactic Model for Parsing Fluent and Disfluent Speech	claim
193	95	Exploiting N-best Hypotheses for SMT Self-Enhancement	claim
194	95	Robust Extraction of Named Entity Including Unfamiliar Word	claim
195	94	Resolving Personal Names in Email Using Context Expansion	claim
196	93	Weakly-Supervised Acquisition of Open-Domain Classes and Class Attributes from Web Documents and Query Logs	claim
197	93	Novel Semantic Features for Verb Sense Disambiguation	claim
198	93	Self-Training for Biomedical Parsing	claim
199	92	Simulating the Behaviour of Older versus Younger Users when Interacting with Spoken Dialogue Systems	claim
200	91	Optimal $k$-arization of Synchronous Tree-Adjoining Grammar	claim
201	90	Partial Matching Strategy for Phrase-based Statistical Machine Translation	claim
202	82	Semantic Types of Some Generic Relation Arguments: Detection and Evaluation	claim
203	80	A Re-examination on Features in Regression Based Approach to Automatic MT Evaluation	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers