 |
Coling 2008Manchester, 18-22 August, 2008The 22nd International Conference on Computational Linguistics |
|
Coling 2008Manchester, 18-22 August, 2008The 22nd International Conference on Computational Linguistics |
| 09.00 | Opening session | |||
| 09.30 |  |
Keynote lecture: Dr Elizabeth Shriberg, Senior Research Psycholinguist Speech Technology & Research Laboratory, SRI International, Menlo Park CA and International Computer Science Institute, Berkeley CA Challenges to Using Prosody in Automatic Language Processing | ||
| 10.30 | B R E A K | |||
| Discourse | Parsing | Machine Translation | Resources | |
| 11.00 | A fully-lexicalized probabilistic model for Japanese zero anaphora resolution |
Training conditional random fields using incomplete annotations |
Domain adaptation for statistical machine translation with domain dictionary and monolingual corpora |
Automatic generation of parallel treebanks |
| 11.30 | Coreference systems based on kernels methods |
Classifying chart cells for quadratic complexity context-free inference |
Source language markers in EUROPARL translations |
Parsing the SynTagRus treebank of Russian |
| 12.00 | A classification of dialogue actions in tutorial dialogue | Comparative parser performance analysis across grammar frameworks through automatic tree conversion using synchronous grammars |
Linguistically-based sub-sentential alignment for terminology extraction from a bilingual automotive corpus |
Recent advances in a feature-rich framework for treebank annotation |
| 12.30 | L U N C H | |||
| Lexicon | Semantics | Information Extraction | Posters | |
| 14.00 | Semantic role assignment for event nominalisations by leveraging verbal data |
A hybrid generative/discriminative framework to train a semantic parser from an un-annotated corpus |
Automatic seed word selection for unsupervised sentiment classification of Chinese text |
Building a bilingual lexicon using phrase-based statistical machine translation via a pivot language Generation under space constraints Metaphor in textual entailment Multilingual alignments by monolingual string differences On "redundancy" in selecting attributes for generating referring expressions Phrasal segmentation models for statistical machine translation Range concatenation grammars for translation Scaling up analogical learning The impact of reference quality on automatic MT evaluation |
| 14.30 | A supervised algorithm for verb disambiguation into VerbNet classes |
A uniform approach to analogies, synonyms, antonyms, and associations |
Mining opinions in comparative sentences | |
| 15.00 | The choice of features for classification of verbs in biomedical texts |
Almost flat functional semantics for speech translation |
Reading the markets: forecasting public opinion of political candidates by news analysis | |
| 15.30 | B R E A K | |||
| Lexicon | Parsing | Machine Translation | Resources | |
| 16.00 | OntoNotes: corpus cleanup of mistaken agreement using word sense disambiguation |
When is self-training effective for parsing? |
Bayesian semi-supervised Chinese word segmentation for statistical machine translation |
Computer aided correction and extension of a syntactic wide-coverage lexicon |
| 16.30 | Measuring and predicting orthographic associations: modelling the similarity of Japanese kanji |
Weakly supervised supertagging with grammar-informed initialization |
Generating Chinese couplets using a statistical MT approach |
Extending a thesaurus with words from pan-Chinese sources |
| 17.00 | Modeling Chinese documents with topical word-character models |
Relational-Realizational Parsing |
Grammar comparison study for translational equivalence modeling and statistical machine translation |
|
| Information Retrieval | Entailment Paraphrasing | Information Extraction | Summarization Paraphrase Parsing | |
| 09.00 | Active learning with sampling by uncertainty and density for word sense disambiguation and text classification |
Learning entailment rules for unary templates |
An integrated probabilistic and logic approach to encyclopedia relation extraction with multiple features |
Scientific paper summarization using citation summary networks |
| 09.30 | An improved hierarchical bayesian model of language for document classification |
Metric learning for synonym acquisition |
Event frame extraction based on a gene regulation corpus |
A framework for identifying textual redundancy |
| 10.00 | Authorship attribution and verification with many authors and limited data |
A probabilistic model for measuring grammaticality and similarity of automatically generated paraphrases of predicate phrases |
Exploiting constituent dependencies for tree kernel-based semantic relation extraction |
Re-estimation of lexical parameters for treebank PCFGs |
| 10.30 | B R E A K | |||
| Discourse | Parsing | Machine Translation | Tagging and Learning | |
| 11.00 | Other-Anaphora resolution in biomedical texts with automatic mined patterns |
Coordination disambiguation without any similarities |
Tera-scale statistical translation models via pattern matching |
Evaluating unsupervised part-of-speech tagging for grammar induction |
| 11.30 | Statistical anaphora resolution in biomedical texts |
Unsupervised induction of labeled parse trees by clustering with syntactic features |
Improving statistical machine translation using lexicalized rule selection |
Homotopy-based semi-supervised Hidden Markov Models for sequence labeling |
| 12.00 | Switching to real-time tasks in multi-tasking dialogue |
Modeling latent-dynamics in shallow parsing: a latent conditional model with improved inference |
Random restarts in minimum error rate training for statistical machine translation |
Word lattice reranking for Chinese word segmentation and part-of-speech tagging |
| 12.30 | L U N C H | |||
| Lexicon | Semantics | Machine Translation | Posters | |
| 14.00 | Measuring topic homogeneity and its application to dictionary-based word sense disambiguation |
An algorithm for adverbial aspect shift |
Syntactic reordering integrated with phrase-based SMT |
A language-independent approach to keyphrase extraction and evaluation A scalable MMR approach to sentence scoring for multi-document update summarization distilling opinion in Discourse: A Preliminary Study Exact inference for multi-label classification using sparse graphical models Hindi compound verbs and their automatic extraction Sentence compression as a step in summarization or an alternative path in text shortening The power of negative thinking: exploiting label disagreement in the min-cut classification framework Using very simple statistics for review search: an exploration |
| 14.30 | A concept-centered approach to noun-compound interpretation |
Class-driven attribute extraction |
Choosing the right translation: a syntactically informed classification approach | |
| 15.00 | On robustness and domain adaptation using SVD for word sense disambiguation |
Are morpho-syntactic features more predictive for the resolution of noun phrase coordination ambiguity than lexico-semantic similarity scores? |
Sentence type based reordering model for statistical machine translation | |
| 15.30 | B R E A K | |||
| Lexicon | Parsing | Information Extraction | Demos | |
| 16.00 | Good neighbors make good senses: exploiting distributional similarity for unsupervised WSD |
Toward a psycholinguistically-motivated model of language processing |
What's the date? High accuracy interpretation of weekday names |
Online-monitoring of security-related events A grammar checking system for Punjabi A Punjabi to Hindi machine translation system Multilingual mobile-phone translation services for world travelers Entailment-based question answering for structured data A linguistic knowledge discovery tool: very large ngram database search with arbitrary wildcards |
| 16.30 | Semantic classification with distributional kernels |
Efficiently parsing with the product-free Lambek calculus |
Chinese term extraction using minimal resources | |
| 17.00 | A joint information model for n-best ranking |
Shift-reduce dependency DAG parsing |
Stopping criteria for active learning of named entity recognition | |
| 09.30 |  |
Keynote lecture: Prof John Shawe-Taylor Centre for Computational Statistics and Machine Learning, University College London Machine Learning for multilingual analysis | ||
| 10.30 | B R E A K | |||
| Discourse | Parsing | Machine Translation | Summarization | |
| 11.00 | Investigating the portability of corpus-derived cue phrases for dialogue act classification |
Chinese dependency parsing with large scale automatically constructed case structures |
Regenerating hypotheses for statistical machine translation |
Extractive summarization using supervised and semi-supervised learning |
| 11.30 | Verification and implementation of language-based deception indicators in civil and criminal narratives |
Learning reliable information for dependency parsing adaptation |
Linguistically annotated BTG for statistical machine translation |
Mind the gap: dangers of divorcing evaluations of summary content from linguistic quality |
| 12.00 | Applying discourse analysis and data mining methods to spoken OSCE assessments |
Japanese dependency parsing using a tournament model |
Improving alignments for better confusion networks for combining machine translation systems |
Pedagogically useful extractive summaries for science education |
| 12.30 | L U N C H | |||
| Lexicon | Generation | Information Extraction | Posters | |
| 14.00 | Acquiring sense tagged examples using relevance feedback |
Dependency-based n-gram models for general purpose sentence realisation |
A local alignment kernel in the context of NLP |
Comparative evaluation of Arabic language morphological analysers and stemmers ILP-based conceptual analysis for Chinese NPs Detecting erroneous uses of complex postpositions in an agglutinative language Experiments in base-NP chunking and its role in dependency parsing for Thai Explaining similarity of terms Integrating motion predicate classes with spatial and temporal annotations On the weak generative capacity of weighted context-free grammars Robust and efficient Chinese word dependency analysis with linear kernel support vector machines Word sense disambiguation for all words using tree-structured conditional random fields |
| 14.30 | Using hidden Markov random fields to combine distributional and pattern-based word clustering |
Generation of referring expressions: managing structural ambiguities |
Looking for trouble | |
| 15.00 | Using three way data for word sense discrimination |
PNR2: ranking sentences with positive and negative reinforcement for query-oriented update summarization |
Topic Identification for fine-grained opinion analysis | |
| 15.30 | B R E A K | |||
| Information Retrieval | Parsing | Machine Translation | Demos | |
| 16.00 | Multi-criteria-based strategy to stop active learning for data annotation |
Estimation of conditional probabilities with decision trees and an application to fine-grained POS tagging |
Tighter integration of rule-based and statistical MT in serial system combination |
Semantic visualization and meaning computation A toolchain for grammarians "Build your own" spoken dialogue systems: automatically generating ISU dialogue systems from business user resources Multilingual assistant for medical diagnosing and drug prescription based on category ranking Shahmukhi to Gurmukhi transliteration system Temporal processing with the TARSQI toolkit |
| 16.30 | Retrieving bilingual verb-noun collocations by integrating cross-language category hierarchies |
Representations for category disambiguation |
A systematic comparison of phrase-based, hierarchical and syntax-augmented statistical MT | |
| 17.00 | Robust similarity measures for named entities matching |
A method for automatic POS guessing of Chinese unknown words |
Diagnostic evaluation of machine translation systems using automatically constructed linguistic check-points | |
| Information Retrieval | Entailment Paraphrasing | Information Extraction | Language checking | |
| 09.00 | Classifying what-type questions by head noun tagging |
Sentence compression beyond word deletion |
Textual demand analysis: detection of users' wants and needs from opinions |
A classifier-based approach to preposition and determiner error correction in L2 English |
| 09.30 | Translating queries into snippets for improved query expansion |
Two-phased event relation acquisition: coupling the relation-oriented and argument-oriented approaches |
A fluid knowledge representation for understanding and generating creative metaphors |
Hybrid processing for grammar and style checking |
| 10.00 | Using syntactic information for improving why-question answering |
ParaMetric: an automatic evaluation metric for paraphrasing | Instance-based ontology population exploiting named-entity substitution |
The ups and downs of preposition error detection in ESL writing |
| 10.30 | B R E A K | |||
| Discourse and Information Extraction | Semantics | Information Extraction | Resources | |
| 11.00 | Emotion classification using massive examples extracted from the Web |
Modeling semantic containment and exclusion in natural language inference |
Understanding and summarizing answers in community-based question answering services |
Exploiting graph structure for accelerating the calculation of shortest paths in Wordnets |
| 11.30 | Discourse level opinion interpretation |
prediction of maximal projection for semantic role labeling |
Tracking the dynamic evolution of participants salience in a discussion |
Anomalies in the WordNet verb hierarchy |
| 12.00 | Exploring domain differences for the design of a pronoun resolution system for biomedical texts |
Integrating a unification-based semantics in a large scale lexicalised tree adjoining grammar for French |
A discriminative alignment model for abbreviation recognition |
KnowNet: building a large net of knowledge from the Web |
| 12.30 | L U N C H | |||
| Information Retrieval | Semantics | Information Extraction | Posters | |
| 14.00 | Using Web-search results to measure word-group similarity |
Contents modelling of Neo-Sumerian Ur III economic text corpus |
CollabRank: towards a collaborative approach to single-document keyphrase extraction |
A complete and modestly funny system for generating and performing Japanese stand-up comedy Construction of an infrastructure for providing users with suitable language resources Easily identifiable discourse relations Modeling multilinguality in ontologies Quantification and implication in semantic calendar expressions represented with finite-state transducers Rank distance as a stylistic similarity Towards incremental end-of-utterance detection in dialogue systems Underspecified Modelling of complex discourse constraints Bayes risk-based dialogue management for document retrieval system with speech interface |
| 14.30 | Enhancing multilingual latent semantic analysis with term alignment information |
Experiments with reasoning for temporal relations between events |
Detecting multiple facets of an event using graph-based unsupervised methods | |
| 15.00 | Hindi Urdu machine transliteration using finite-state transducers |
From words to senses: a case study of subjectivity recognition |
Investigating statistical techniques for sentence-level event classification | |
| 15.30 | B R E A K | |||
| Semantics | Parsing | Machine Translation | Miscellaneous | |
| 16.00 | The effect of syntactic representation on semantic role labeling |
A syntactic time-series model for parsing fluent and disfluent speech |
Non-compositional language model and pattern dictionary development for Japanese compound and complex sentences |
Modeling the structure and dynamics of the consonant inventories: a complex network approach |
| 16.30 | Using discourse commitments to recognize textual entailment |
Latent morpho-semantic analysis: multilingual information retrieval with character n-grams and mutual information |
Extracting synchronous grammar rules from word-level alignments in linear time |
Normalizing SMS: are two metaphors better than one? |
| 17.00 | Closing Session incl. Springer Best Paper Award | |||