MAXIMUM LIKELIHOOD: Related Papers in ACL Anthology

MAXIMUM LIKELIHOOD can be found in the following ACL ARC 1.0 documents (click to explore):

• (ACL ID: A00-2014) the effectiveness of corpus-induced dependency grammars for post-processing speech
• (ACL ID: A00-2017) a classification approach to word prediction
• (ACL ID: A00-2021) exploiting auxiliary distributions in stochastic unification-based grammars
• (ACL ID: A00-2030) a novel use of statistical parsing to extract information from text
• (ACL ID: A88-1028) computational techniques for improved name search
• (ACL ID: A92-1018) a practical part-of-speech tagger
• (ACL ID: A94-1010) improving language models by clustering training sentences
• (ACL ID: A94-1012) combination of symbolic and statistical approaches for grammatical knowledge acquisition
• (ACL ID: A97-1017) probabilistic and rule-based tagger of an inflective language- a comparison
• (ACL ID: A97-1056) sequential model selection for word sense disambiguation
• (ACL ID: C00-1010) an empirical evaluation of lfg-dop
• (ACL ID: C00-1011) parsing with the shortest derivation
• (ACL ID: C00-1029) a class-based probabilistic approach to structural disambiguation
• (ACL ID: C00-1044) effects of adjective orientation and gradability on sentence subjectivity
• (ACL ID: C00-1056) an english to korean transliteration model of extended markov window
• (ACL ID: C00-1068) flexible mixed-initiative dialogue management using concept-level confidence measures of speech recognizer output
• (ACL ID: C00-1070) lexicalized hidden markov models for part-of-speech tagging
• (ACL ID: C00-2108) clustering verbs semantically according to their alternation behaviour
• (ACL ID: C00-2114) a dynamic language model based on individual word domains
• (ACL ID: C00-2135) acquisition of phrase-level bilingual correspondence using dependency structure
• (ACL ID: C02-1004) combining unsupervised and supervised methods for pp attachment disambiguation
• (ACL ID: C02-1010) structure alignment using bilingual chunking
• (ACL ID: C02-1016) determining recurrent sound correspondences by inducing translation models
• (ACL ID: C02-1019) the grammatical function analysis between korean adnoun clause and noun phrase by using support vector machines
• (ACL ID: C02-1050) bidirectional decoding for statistical machine translation
• (ACL ID: C02-1090) taxonomy learning - factoring the structure of a taxonomy into a semantic classification decision
• (ACL ID: C02-1112) syntactic features for high precision word sense disambiguation
• (ACL ID: C02-1132) probabilistic models of verb-argument structure
• (ACL ID: C02-2025) the lingo redwoods treebank
• (ACL ID: C02-2026) creating a finite-state parser with application semantics
• (ACL ID: C04-1013) partially distribution-free learning of regular languages from positive samples
• (ACL ID: C04-1014) modeling of long distance context dependency
• (ACL ID: C04-1022) automatic learning of language model structure
• (ACL ID: C04-1045) improving word alignment quality using morpho-syntactic information
• (ACL ID: C04-1066) japanese unknown word identification by character-based chunking
• (ACL ID: C04-1081) chinese segmentation and new word detection using conditional random fields
• (ACL ID: C04-1094) using syntactic information to extract relevant terms for multi-document summarization
• (ACL ID: C04-1098) a trigger language model-based ir system
• (ACL ID: C04-1103) direct orthographical mapping for machine transliteration
• (ACL ID: C04-1146) characterising measures of lexical distributional similarity
• (ACL ID: C04-1147) fast computation of lexical affinity models
• (ACL ID: C04-1167) statistical language modeling with performance benchmarks using various levels of syntactic-semantic information
• (ACL ID: C69-4901) simulation of word-meaning stochastic processes
• (ACL ID: C90-3038) neural network approach to word category prediction for english texts
• (ACL ID: C92-1055) syntactic ambiguity resolution using a discrimination and robustness oriented adaptive learning algorithm
• (ACL ID: C94-2210) syllable-based phonetic transcription by maximum likelihood methods
• (ACL ID: C96-1003) clustering words with the mdl principle
• (ACL ID: C96-1056) grice incorporated cooperativity in spoken dialogue
• (ACL ID: E06-1014) improving probabilistic latent semantic analysis with principal component analysis
• (ACL ID: E06-1034) from detecting errors to automatically correcting them
• (ACL ID: E06-1035) automatic segmentation of multiparty dialogue
• (ACL ID: E06-1044) modelling semantic role pausibility in human sentence processing
• (ACL ID: E06-2017) computing term translation probabilities with generalized latent semantic analysis
• (ACL ID: E87-1014) an automatic speech recognition system for the italian language
• (ACL ID: E93-1054) text alignment in a tool for translating revised documents
• (ACL ID: E95-1016) on learning more appropriate selectional restrictions
• (ACL ID: E99-1026) japanese dependency structure analysis based on maximum entropy models
• (ACL ID: H01-1003) advances in meeting recognition
• (ACL ID: H01-1029) fine-grained hidden markov modeling for broadcast-news story segmentation
• (ACL ID: H01-1046) latat
• (ACL ID: H01-1064) scanmail
• (ACL ID: H05-1005) improving multilingual summarization
• (ACL ID: H05-1022) hmm word and phrase alignment for statistical machine translation
• (ACL ID: H05-1048) detection of entity mentions occuring in english and chinese text
• (ACL ID: H05-1087) maximum expected f-measure training of logistic regression models
• (ACL ID: H05-1092) multi-way relation classification
• (ACL ID: H05-1100) morphology and reranking for the statistical parsing of spanish
• (ACL ID: H05-1110) inducing a multilingual dictionary from a parallel multitext in related languages
• (ACL ID: H89-1005) speaker independent phonetic transcription of fluent speech for large vocabulary speech recognition
• (ACL ID: H89-1045) chart parsing of stochastic spoken language models
• (ACL ID: H89-2013) enhanced good-turing and cat.cal
• (ACL ID: H89-2037) towards speech recognition without vocabulary-specific training
• (ACL ID: H89-2038) large-vocabulary speaker-independent continuous speech recognition with semi.continuous hidden markov models
• (ACL ID: H89-2047) improvements in the stochastic segment model for phoneme recognition
• (ACL ID: H90-1006) the use of relative duration in syntactic disambiguation
• (ACL ID: H90-1034) towards environment-independent spoken language systems
• (ACL ID: H90-1037) fast search algorithms for connected phone recognition using the stochastic segment model
• (ACL ID: H90-1039) on the interaction between true source, training, and testing language models
• (ACL ID: H90-1040) continuous speech recognition from a phonetic transcription
• (ACL ID: H90-1050) session 9
• (ACL ID: H90-1057) representation quality in text classification
• (ACL ID: H90-1061) implementation aspects of large vocabulary recognition based on intraword and interword phonetic units
• (ACL ID: H90-1066) recognition of noisy speech
• (ACL ID: H91-1020) stochastic representation of conceptual structure in the atis task
• (ACL ID: H91-1026) identifying word correspondences in parallel texts
• (ACL ID: H91-1045) calculating the probability of a partial parse of a sentence
• (ACL ID: H91-1049) a dynamical system approach to continuous speech recognition
• (ACL ID: H91-1054) a study on speaker-adaptive speech recognition
• (ACL ID: H91-1065) studies in part of speech labelling
• (ACL ID: H92-1023) decision tree models applied to the labeling of text with parts-of-speech
• (ACL ID: H92-1028) parameter estimation for constrained context-free language models
• (ACL ID: H92-1033) vocabulary and environment adaptation in vocabulary-independent speech recognition
• (ACL ID: H92-1036) map estimation of continuous density hmm
• (ACL ID: H92-1045) one sense per discourse
• (ACL ID: H92-1079) large vocabulary recognition of wall street journal sentences at dragon systems
• (ACL ID: H93-1016) an overview of the sphinx-ii speech recognition system
• (ACL ID: H93-1019) identification of non-linguistic speech features
• (ACL ID: H93-1020) on the use of tied-mixture distributions
• (ACL ID: H93-1021) adaptive language modeling using the maximum entropy principle
• (ACL ID: H93-1023) topic and speaker identification via large vocabulary continuous speech recognition
• (ACL ID: H93-1051) corpus-based statistical sense resolution
• (ACL ID: H93-1087) lingstat
• (ACL ID: H94-1013) a hybrid approach to adaptive statistical language modeling
• (ACL ID: H94-1014) language modeling with sentence-level mixtures
• (ACL ID: H94-1015) speech recognition using a stochastic language model integrating local and global constraints
• (ACL ID: H94-1042) integrated techniques for phrase extraction from speech
• (ACL ID: H94-1047) a new approach to word sense disambiguation
• (ACL ID: H94-1054) japanese word segmentation by hidden markov model
• (ACL ID: H94-1074) speech-based retrieval using semantic co-occurrence filtering
• (ACL ID: H94-1080) a one pass decoder design for large vocabulary recognition
• (ACL ID: H94-1091) evaluating the use of prosodic information in speech recognition and understanding
• (ACL ID: I05-2002) a hierarchical parsing approach with punctuation processing for long chinese sentences
• (ACL ID: I05-2012) automatic extraction of english-korean translations for constituents of technical terms
• (ACL ID: I05-2034) probabilistic models for korean morphological analysis
• (ACL ID: J00-1004) learning dependency translation models as collections of finite-state head transducers
• (ACL ID: J00-2004) models of translational equivalence among words
• (ACL ID: J00-3003) dialogue act modeling for automatic tagging and recognition of conversational speech
• (ACL ID: J01-1001) using suffix arrays to compute term frequency and document frequency for all substrings in a corpus
• (ACL ID: J01-2004) probabilistic top-down parsing and language modeling
• (ACL ID: J01-3001) the interaction of knowledge sources in word sense disambiguation
• (ACL ID: J01-3002) a statistical model for word discovery in transcribed speech
• (ACL ID: J02-3004) the disambiguation of nominalizations
• (ACL ID: J03-2004) a probabilistic account of logical metonymy
• (ACL ID: J05-4004) induction of word and phrase alignments for automatic document summarization
• (ACL ID: J05-4005) chinese word segmentation and named entity recognition
• (ACL ID: J84-1002) a formal of natural basis for language performance evaluation understanding systems
• (ACL ID: J92-4003) class-based n-gram models of natural language
• (ACL ID: J93-1004) a program for aligning sentences in bilingual corpora
• (ACL ID: J93-1005) structural ambiguity and lexical relations
• (ACL ID: J93-1006) text-translation alignment
• (ACL ID: J93-2003) the mathematics of statistical machine translation
• (ACL ID: J93-2006) coping with ambiguity and unknown words through probabilistic models
• (ACL ID: J94-1002) a hierarchical stochastic model for automatic prediction of prosodic boundary location
• (ACL ID: J94-2001) tagging english text with a probabilistic model
• (ACL ID: J94-4003) word sense disambiguation using a second language monolingual corpus
• (ACL ID: J94-4005) training and scaling preference functions for disambiguation
• (ACL ID: J95-2001) automatic stochastic tagging of natural language texts
• (ACL ID: J95-3002) robust learning, smoothing, and parameter tying on syntactic ambiguity resolution
• (ACL ID: J96-1002) a maximum entropy approach to natural language processing
• (ACL ID: J96-2001) estimating lexical priors for low-frequency morphologically ambiguous forms
• (ACL ID: J96-2003) improving statistical language model performance with automatically generated word hierarchies
• (ACL ID: J96-3004) a stochastic finite-state word-segmentation algorithm for chinese
• (ACL ID: J98-2005) squibs and discussions
• (ACL ID: J98-4004) pcfg models of linguistic tree representations
• (ACL ID: J99-2002) decomposable modeling in natural language processing
• (ACL ID: J99-3003) vector-based natural language call routing
• (ACL ID: J99-4002) lexical rules in constraint-based grammars
• (ACL ID: M98-1009) bbn
• (ACL ID: M98-1016) description of the kent ridge digital labs system used for muc-7
• (ACL ID: N01-1010) tree-cut and a lexicon based on systematic polysemy
• (ACL ID: N03-1019) a weighted finite state transducer implementation of the alignment template model for statistical machine translation
• (ACL ID: N03-1025) language and task independent text categorization with simple language models
• (ACL ID: N03-1027) supervised and unsupervised pcfg adaptation to novel domains
• (ACL ID: N03-1029) comma restoration using constituency information
• (ACL ID: N03-1030) sentence level discourse parsing using syntactic and lexical information
• (ACL ID: N03-1032) frequency estimates for statistical word similarity measures
• (ACL ID: N03-1033) feature-rich part-of-speech tagging with a cyclic dependency network
• (ACL ID: N03-2002) factored language models and generalized parallel backoff
• (ACL ID: N03-2012) detection of agreement vs. disagreement in meetings
• (ACL ID: N03-3006) a low-complexity, broad-coverage probabilistic dependency parser for english
• (ACL ID: N04-1003) robust reading
• (ACL ID: N04-1022) minimum bayes-risk decoding for statistical machine translation
• (ACL ID: N04-1030) shallow semantic parsing using support vector machines
• (ACL ID: N04-1039) exponential priors for maximum entropy models
• (ACL ID: N04-1042) accurate information extraction from research papers using conditional random fields
• (ACL ID: N04-2001) multilingual speech recognition for information retrieval in indian context
• (ACL ID: N04-2010) speaker recognition with mixtures of gaussians with sparse regression matrices
• (ACL ID: N04-4006) language model adaptation with map estimation and the perceptron algorithm
• (ACL ID: N04-4007) advances in children's speech recognition within an interactive literacy tutor
• (ACL ID: N04-4022) context-based speech recognition error detection and correction
• (ACL ID: N04-4023) feature selection for trainable multilingual broadcast news segmentation
• (ACL ID: N06-1002) do we need phrases? challenging the conventional wisdom in statistical machine translation
• (ACL ID: N06-1003) improved statistical machine translation using paraphrases
• (ACL ID: N06-1008) acquiring inference rules with temporal constraints by using japanese coordinated sentences and noun-verb co-occurrences
• (ACL ID: N06-1010) exploiting domain structure for named entity recognition
• (ACL ID: N06-1022) multilevel coarse-to-fine pcfg parsing
• (ACL ID: N06-1023) a fully-lexicalized probabilistic model for japanese syntactic and case structure analysis
• (ACL ID: N06-1040) probabilistic context-free grammar induction based on structural zeros
• (ACL ID: N06-1043) cross-entropy and estimation of probabilistic context-free grammars
• (ACL ID: N06-1044) estimation of consistent probabilistic context-free grammars
• (ACL ID: N06-1052) language model information retrieval with document expansion
• (ACL ID: N06-1061) language model-based document clustering using random walks
• (ACL ID: N06-1062) unlimited vocabulary speech recognition for agglutinative languages
• (ACL ID: N06-2010) gesture improves coreference resolution
• (ACL ID: N06-2023) summarizing speech without text using hidden markov models
• (ACL ID: N06-2037) selecting relevant text subsets from web-data for building topic specific language models
• (ACL ID: N06-4010) factoid question answering with web, mobile and speech interfaces
• (ACL ID: N06-5002) beyond em
• (ACL ID: P00-1012) the order of prenominal adjectives in natural language generation
• (ACL ID: P00-1029) inducing probabilistic syllable classes using multivariate clustering
• (ACL ID: P00-1061) lexicalized stochastic modeling of constraint-based grammars using log-linear measures and em training
• (ACL ID: P01-1010) what is the minimal set of fragments that achieves maximal parse accuracy?
• (ACL ID: P01-1035) serial combination of rules and statistics
• (ACL ID: P01-1042) joint and conditional estimation of tagging and parsing models
• (ACL ID: P01-1050) towards a unified approach to memory- and statistical-based machine translation
• (ACL ID: P02-1006) learning surface text patterns for a question answering system
• (ACL ID: P02-1023) improving language model size reduction using better pruning criteria
• (ACL ID: P02-1035) parsing the wall street journal using a lexical-functional grammar and discriminative estimation techniques
• (ACL ID: P02-1036) dynamic programming for parsing and estimation of stochastic unification-based grammars
• (ACL ID: P02-1038) discriminative training and maximum entropy models for statistical machine translation
• (ACL ID: P02-1047) an unsupervised approach to recognizing discourse relations
• (ACL ID: P02-1057) a noisy-channel model for document compression
• (ACL ID: P03-1006) generalized algorithms for constructing statistical language models
• (ACL ID: P03-1008) syntactic features and word similarity for supervised metonymy resolution
• (ACL ID: P03-1013) probabilistic parsing for german using sister-head dependencies
• (ACL ID: P03-1021) minimum error rate training in statistical machine translation
• (ACL ID: P03-1036) unsupervised segmentation of words using prior distributions of morph length and frequency
• (ACL ID: P03-1037) parametric models of linguistic count data
• (ACL ID: P03-1038) self-organizing markov models and their application to part-of-speech tagging
• (ACL ID: P03-1041) effective phrase translation extraction from alignment models
• (ACL ID: P03-1043) a bootstrapping approach to named entity classification using successive learners
• (ACL ID: P03-1054) accurate unlexicalized parsing
• (ACL ID: P03-1060) a syllable based word recognition model for korean noun extraction
• (ACL ID: P03-1066) unsupervised learning of dependency structure for language modeling
• (ACL ID: P04-1007) discriminative language modeling with conditional random fields and the perceptron algorithm
• (ACL ID: P04-1013) discriminative training of a neural network statistical parser
• (ACL ID: P04-1021) a joint source-channel model for machine transliteration
• (ACL ID: P04-1023) statistical machine translation with word- and sentence-aligned parallel corpora
• (ACL ID: P04-1030) head-driven parsing for word lattices
• (ACL ID: P04-1039) relieving the data acquisition bottleneck in word sense disambiguation
• (ACL ID: P04-1055) classifying semantic relations in bioscience texts
• (ACL ID: P04-1062) annealing techniques for unsupervised statistical language learning
• (ACL ID: P04-1066) improving ibm word alignment model 1
• (ACL ID: P04-1070) an alternative method of training probabilistic lr parsers
• (ACL ID: P04-1074) applying machine learning to chinese temporal relation resolution
• (ACL ID: P04-1083) statistical machine translation by parsing
• (ACL ID: P04-2001) determining the specificity of terms using compositional and contextual information
• (ACL ID: P04-2007) towards a semantic classification of spanish verbs based on subcategorisation information
• (ACL ID: P04-3024) a new feature selection score for multinomial naive bayes text classification based on kl-divergence
• (ACL ID: P05-1023) data-defined kernels for parse reranking derived from probabilistic models
• (ACL ID: P05-1032) scaling phrase-based statistical machine translation to larger corpora and longer phrases
• (ACL ID: P05-1034) dependency treelet translation
• (ACL ID: P05-1038) lexicalization in crosslinguistic probabilistic parsing
• (ACL ID: P05-1042) a dynamic bayesian framework to model context and memory in edit distance learning
• (ACL ID: P05-1045) incorporating non-local information into information extraction systems by gibbs sampling
• (ACL ID: P05-1046) unsupervised learning of field segmentation models for information extraction
• (ACL ID: P05-1057) log-linear models for word alignment
• (ACL ID: P05-1065) reading level assessment using support vector machines and statistical language models
• (ACL ID: P05-1069) a localized prediction model for statistical machine translation
• (ACL ID: P05-1074) paraphrasing with bilingual parallel corpora
• (ACL ID: P05-2001) hybrid methods for pos guessing of chinese unknown words
• (ACL ID: P05-2004) jointly labeling multiple sequences
• (ACL ID: P05-2016) dependency-based statistical machine translation
• (ACL ID: P05-2026) a domain-specific statistical surface realizer
• (ACL ID: P06-1009) discriminative word alignment with conditional random fields
• (ACL ID: P06-1061) segment-based hidden markov models for information extraction
• (ACL ID: P06-1062) a dom tree alignment model for mining parallel data from the web
• (ACL ID: P06-1065) improved discriminative bilingual word alignment
• (ACL ID: P06-1071) a progressive feature selection algorithm for ultra large feature spaces
• (ACL ID: P06-1080) self-organizing n-gram model for automatic word spacing
• (ACL ID: P06-1085) contextual dependencies in unsupervised word segmentation
• (ACL ID: P06-1088) multi-tagging for lexicalized-grammar parsing
• (ACL ID: P06-1097) semi-supervised training for statistical word alignment
• (ACL ID: P06-1109) an all-subtrees approach to unsupervised parsing
• (ACL ID: P06-1122) modelling lexical redundancy for machine translation
• (ACL ID: P06-1125) a phonetic-based approach to chinese chat text normalization
• (ACL ID: P06-1136) reranking answers for definitional qa using language modeling
• (ACL ID: P06-1141) an effective two-stage model for exploiting non-local dependencies in named entity recognition
• (ACL ID: P06-2005) a phrase-based statistical model for sms text normalization
• (ACL ID: P06-2017) analysis and synthesis of the distribution of consonants over languages
• (ACL ID: P06-2025) a modified joint source-channel model for transliteration
• (ACL ID: P06-2029) the benefit of stochastic pp attachment to a rule-based parser
• (ACL ID: P06-2043) improving english subcategorization acquisition with diathesis alternations as heuristic information
• (ACL ID: P06-2069) examining the content load of part of speech blocks for information retrieval
• (ACL ID: P06-2073) segmented and unsegmented dialogue-act annotation with statistical dialogue models
• (ACL ID: P06-2084) combining association measures for collocation extraction
• (ACL ID: P06-2088) simultaneous english-japanese spoken language translation based on incremental dependency parsing and transfer
• (ACL ID: P06-2101) minimum risk annealing for training log-linear models
• (ACL ID: P06-2107) statistical phrase-based models for interactive computer-assisted translation
• (ACL ID: P06-3015) clavius
• (ACL ID: P91-1023) a program for aligning sentences in bilingual corpora
• (ACL ID: P91-1039) factorization of language constraints in speech recognition
• (ACL ID: P92-1024) development and evaluation of a broad-coverage probabilistic grammar of english-language computer manuals
• (ACL ID: P93-1022) contextual word similarity and estimation from sparse data
• (ACL ID: P93-1024) distributional clustering of english words
• (ACL ID: P94-1004) hidden understanding models of natural language
• (ACL ID: P94-1010) a stochastic finite-state word-segmentation algorithm for chinese
• (ACL ID: P94-1020) word-sense disambiguation using decomposable models
• (ACL ID: P94-1025) part-of-speech tagging using a variable memory markov model
• (ACL ID: P94-1038) similarity-based estimation of word cooccurrence probabilities
• (ACL ID: P95-1025) statistical sense disambiguation with relatively small corpora using dictionary definitions
• (ACL ID: P95-1027) a quantitative evaluation of linguistic tests for the automatic prediction of semantic markedness
• (ACL ID: P95-1033) an algorithm for simultaneously bracketing parallel texts by aligning words
• (ACL ID: P96-1014) computing optimal descriptions for optimality theory grammars with context-free position structures
• (ACL ID: P96-1025) a new statistical parser based on bigram lexical dependencies
• (ACL ID: P96-1030) fast parsing using pruning and grammar specialization
• (ACL ID: P96-1041) an empirical study of smoothing techniques for language modeling
• (ACL ID: P96-1042) minimizing manual annotation cost in supervised training from corpora
• (ACL ID: P97-1003) three generative, lexicalised models for statistical parsing
• (ACL ID: P97-1005) automatic detection of text genre
• (ACL ID: P97-1006) document classification using a finite mixture model
• (ACL ID: P97-1008) similarity-based methods for word sense disambiguation
• (ACL ID: P97-1022) fertility models for statistical natural language understanding
• (ACL ID: P97-1024) independence assumptions considered harmful
• (ACL ID: P97-1030) mistake-driven mixture of hierarchical tag context trees
• (ACL ID: P97-1037) a dp-based search using monotone alignments in statistical translation
• (ACL ID: P97-1056) memory-based learning
• (ACL ID: P97-1063) a word-to-word model of translational equivalence
• (ACL ID: P98-1006) automatic acquisition of hierarchical transduction models for machine translation
• (ACL ID: P98-1047) learning a syntagmatic and paradigmatic structure from language data with a bi-multigram model
• (ACL ID: P98-1074) flow network models for word alignment and terminology extraction from bilingual corpora
• (ACL ID: P98-1080) tagging inlective languages
• (ACL ID: P98-2124) word clustering and disambiguation based on co-occurrence data
• (ACL ID: P98-2127) automatic retrieval and clustering of similar words
• (ACL ID: P98-2162) improving statistical natural language translation with categories and rules
• (ACL ID: P99-1014) inducing a semantically annotated lexicon via em-based clustering
• (ACL ID: P99-1032) development and use of a gold-standard data set for subjectivity classifications
• (ACL ID: P99-1041) automatic identification of non-compositional phrases
• (ACL ID: P99-1054) efficient probabilistic top-down and left-corner parsing
• (ACL ID: P99-1069) estimators for stochastic "unification-based" grammars
• (ACL ID: P99-1070) relating probabilistic grammars and automata
• (ACL ID: W00-0707) incorporating position information into a maximum entropy/minimum divergence translation model
• (ACL ID: W00-0728) a context sensitive maximum likelihood approach to chunking
• (ACL ID: W00-1308) enriching the knowledge sources used in a maximum entropy part-of-speech tagger
• (ACL ID: W00-1321) reducing parsing complexity by intra-sentence segmentation based on maximum entropy model
• (ACL ID: W00-1325) statistical filtering and subcategorization frame acquisition
• (ACL ID: W00-1326) one sense per collocation and genre/topic variations
• (ACL ID: W00-1327) using semantically motivated estimates to help subcategorization acquisition
• (ACL ID: W01-0707) probabilistic models for pp-attachment resolution and np analysis
• (ACL ID: W01-0712) learning computational grammars
• (ACL ID: W01-0713) unsupervised induction of stochastic context-free grammars using distributional clustering
• (ACL ID: W01-0714) distributional phrase structure induction
• (ACL ID: W01-1404) approximating context-free by rational transduction for example-based mt
• (ACL ID: W01-1405) stochastic modelling
• (ACL ID: W02-0214) topic identification in natural language dialogues using neural networks
• (ACL ID: W02-0602) unsupervised learning of morphology using a novel directed search algorithm
• (ACL ID: W02-0603) unsupervised discovery of morphemes
• (ACL ID: W02-0706) architectures for speech-to-speech translation using finite-state models
• (ACL ID: W02-0903) boosting automatic lexical acquisition with morphological information
• (ACL ID: W02-1004) modeling consensus
• (ACL ID: W02-1005) augmented mixture models for lexical disambiguation
• (ACL ID: W02-1009) transformational priors over grammars
• (ACL ID: W02-1019) minimum bayes-risk word alignments of bilingual texts
• (ACL ID: W02-1031) the superarv language model
• (ACL ID: W02-1032) exploiting headword dependency and predictive clustering for language modeling
• (ACL ID: W02-1211) constructing of a large-scale chinese-english parallel corpus
• (ACL ID: W02-2016) japanese dependency analysis using cascaded chunking
• (ACL ID: W02-2018) a comparison of algorithms for maximum entropy parameter estimation
• (ACL ID: W03-0317) acquisition of english-chinese transliterated word pairs from parallel-aligned texts using a statistical machine transliteration model
• (ACL ID: W03-0401) a model of syntactic disambiguation based on lexicalized grammars
• (ACL ID: W03-0413) confidence estimation for translation prediction
• (ACL ID: W03-0416) an efficient clustering algorithm for class-based language models
• (ACL ID: W03-0417) training a naive bayes classifier via the em algorithm with a class distribution constraint
• (ACL ID: W03-0429) named entity recognition using hundreds of thousands of features
• (ACL ID: W03-0602) words and pictures in the news
• (ACL ID: W03-1003) cross-lingual lexical triggers in statistical language modeling
• (ACL ID: W03-1009) variation of entropy and parse trees of sentences as a function of the sentence number
• (ACL ID: W03-1012) using ltag based features in parse reranking
• (ACL ID: W03-1019) investigating loss functions and optimization methods for discriminative learning of label sequences
• (ACL ID: W03-1202) using thematic information in statistical headline generation
• (ACL ID: W03-1209) statistical qa - classifier vs. re-ranker
• (ACL ID: W03-1211) question answering on a case insensitive corpus
• (ACL ID: W03-1701) unsupervised training for overlapping ambiguity resolution in chinese word segmentation
• (ACL ID: W03-1702) class based sense definition model for word sense tagging and disambiguation
• (ACL ID: W03-1710) modeling of long distance context dependency in chinese
• (ACL ID: W03-1723) a two-stage statistical word segmentation system for chinese
• (ACL ID: W04-0302) stochastically evaluating the validity of partial parse trees in incremental parsing
• (ACL ID: W04-0307) a statistical constraint dependency grammar (cdg) parser
• (ACL ID: W04-0404) translation by machine of complex nominals
• (ACL ID: W04-0842) wsd system based on specialized hidden markov model (upv-shmm-eaw)
• (ACL ID: W04-0847) optimizing feature set for chinese word sense disambiguation
• (ACL ID: W04-0857) generative models for semantic role labeling
• (ACL ID: W04-1104) adaptive compression-based approach for chinese pinyin input
• (ACL ID: W04-1119) a semi-supervised approach to build annotated corpus for chinese named entity recognition
• (ACL ID: W04-1215) annotating multiple types of biomedical entities
• (ACL ID: W04-1612) automatic diacritization of arabic for acoustic modeling in speech recognition
• (ACL ID: W04-2002) robust models of human parsing
• (ACL ID: W04-2314) bootstrapping spoken dialog systems with data reuse
• (ACL ID: W04-2402) semantic lexicon construction
• (ACL ID: W04-2408) modeling category structures with a kernel function
• (ACL ID: W04-2410) thesauruses for prepositional phrase attachment
• (ACL ID: W04-2413) semantic role labelling with chunk sequences
• (ACL ID: W04-2505) intentions, implicatures and processing of complex questions
• (ACL ID: W04-2602) towards full automation of lexicon construction
• (ACL ID: W04-2901) a system for searching and browsing spoken communications
• (ACL ID: W04-2904) scoring algorithms for wordspotting systems
• (ACL ID: W04-3007) robustness issues in a data-driven spoken language understanding system
• (ACL ID: W04-3201) max-margin parsing
• (ACL ID: W04-3207) bilingual parsing with factored estimation
• (ACL ID: W04-3209) comparing and combining generative and posterior probability models
• (ACL ID: W04-3213) unsupervised semantic role labellin
• (ACL ID: W04-3216) a phrase-based hmm approach to document/abstract alignment
• (ACL ID: W04-3220) verb sense and subcategorization
• (ACL ID: W04-3227) phrase pair rescoring with term weighting for statistical machine translatio
• (ACL ID: W04-3230) applying conditional random fields to japanese morphological analysis
• (ACL ID: W04-3235) error measures and bayes decision rules revisited with applications to pos tagging
• (ACL ID: W04-3237) adaptation of maximum entropy capitalizer
• (ACL ID: W04-3238) spelling correction as an iterative process that exploits the collective knowledge of web users
• (ACL ID: W04-3242) random forests in language modelin
• (ACL ID: W04-3243) on log-likelihood-ratios and the significance of rare events
• (ACL ID: W04-3249) unsupervised domain relevance estimation for word sense disambiguation
• (ACL ID: W05-0106) making hidden markov models more transparent
• (ACL ID: W05-0206) automatic essay grading with probabilistic latent semantic analysis
• (ACL ID: W05-0602) a statistical semantic parser that integrates syntax and semantics
• (ACL ID: W05-0604) new experiments in distributional representations of synonymy
• (ACL ID: W05-0614) intentional context in situated natural language learning
• (ACL ID: W05-0708) pos tagging of dialectal arabic
• (ACL ID: W05-0801) association-based bilingual word alignment
• (ACL ID: W05-0804) bilingual word spectral clustering for statistical machine translation
• (ACL ID: W05-0814) isi's participation in the romanian-english alignment task
• (ACL ID: W05-0835) a recursive statistical translation model
• (ACL ID: W05-0836) training and evaluating error minimization decision rules for statistical machine translation
• (ACL ID: W05-1005) automatically distinguishing literal and figurative usages of highly polysemous verbs
• (ACL ID: W05-1202) the distributional similarity of sub-parses
• (ACL ID: W05-1208) a probabilistic setting and lexical coocurrence model for textual entailment
• (ACL ID: W05-1504) parsing with soft and hard constraints on dependency length
• (ACL ID: W05-1509) lexical and structural biases for function parsing
• (ACL ID: W05-1516) strictly lexical dependency parsing
• (ACL ID: W05-1601) statistical generation
• (ACL ID: W05-1628) searching for grammaticality
• (ACL ID: W06-0108) cluster-based language model for sentence retrieval in chinese question answering
• (ACL ID: W06-0112) a hybrid approach to chinese base noun phrase chunking
• (ACL ID: W06-0129) character language models for chinese word segmentation and named entity recognition
• (ACL ID: W06-0131) poc-nlw template for chinese word segmentation
• (ACL ID: W06-0505) efficient hierarchical entity classifier using conditional random fields
• (ACL ID: W06-0705) using scenario knowledge in automatic question answering
• (ACL ID: W06-0805) exploring semantic constraints for document retrieval
• (ACL ID: W06-1208) interpretation of compound nominalisations using corpus and web statistics
• (ACL ID: W06-1303) building effective question answering characters
• (ACL ID: W06-1606) spmt
• (ACL ID: W06-1620) multilingual deep lexical acquisition for hpsgs via supertagging
• (ACL ID: W06-1622) semantic role labeling via instance-based learning
• (ACL ID: W06-1626) distributed language modeling for $n$-best list re-ranking
• (ACL ID: W06-1636) learning phrasal categories
• (ACL ID: W06-1646) corrective models for speech recognition of inflected languages
• (ACL ID: W06-1657) short text authorship attribution via sequence kernels, markov chains and author unmasking
• (ACL ID: W06-1672) discriminative methods for transliteration
• (ACL ID: W06-2205) recognition of synonyms by a lexical graph
• (ACL ID: W06-2207) a hybrid approach for the acquisition of information extraction patterns
• (ACL ID: W06-2303) robust parsing of the proposition bank
• (ACL ID: W06-2407) extending corpus-based identification of light verb constructions using a supervised learning framework
• (ACL ID: W06-2601) maximum entropy tagging with binary and real-valued features
• (ACL ID: W06-2914) word distributions for thematic segmentation in a support vector machine approach
• (ACL ID: W06-2918) using gazetteers in discriminative information extraction
• (ACL ID: W06-2919) a context pattern induction method for named entity extraction
• (ACL ID: W06-2929) vine parsing and minimum risk reranking for speed and precision
• (ACL ID: W06-3105) why generative phrase models underperform surface heuristics
• (ACL ID: W06-3115) ntt system description for the wmt2006 shared task
• (ACL ID: W06-3124) microsoft research treelet translation system
• (ACL ID: W06-3208) morphology induction from limited noisy data using approximate string matching
• (ACL ID: W06-3309) generative content models for structural analysis of medical abstracts
• (ACL ID: W06-3407) topic-segmentation of dialogue
• (ACL ID: W06-3809) random-walk term weighting for improved text classification
• (ACL ID: W06-3815) context comparison as a minimum cost flow problem
• (ACL ID: W93-0109) the automatic acquisition of frequencies of verb subcategorization frames from tagged corpora
• (ACL ID: W93-0301) robust bilingual word alignment for machine aided translation
• (ACL ID: W94-0101) invited talk
• (ACL ID: W94-0109) integrating symbolic and statistical approches in speech and natural language applications
• (ACL ID: W95-0103) prepositional phrase attachment through a backed-off model
• (ACL ID: W95-0104) a bayesian hybrid method for context-sensitive spelling correction
• (ACL ID: W95-0115) automatic evaluation and uniform filter cascades for inducing n-best translation lexicons
• (ACL ID: W96-0110) statistical models for deep-structure disambiguation
• (ACL ID: W96-0112) a probabilistic disambiguation method based on psycholinguistic principles
• (ACL ID: W96-0113) a re-estimation method for stochastic language modeling from ambiguous observations
• (ACL ID: W96-0114) towards automatic grammar acquisition from a bracketed corpus
• (ACL ID: W96-0203) unsupervised learning of syntactic knowledge
• (ACL ID: W96-0205) automatic extraction of new words from japanese texts using generalized forward-backward search
• (ACL ID: W96-0206) better language models with model merging
• (ACL ID: W96-0213) a maximum entropy model for part-of-speech tagging
• (ACL ID: W97-0104) a statistics-based chinese parser
• (ACL ID: W97-0116) acquiring german prepositional subcategorization frames from corpora
• (ACL ID: W97-0207) measuring semantic entropy
• (ACL ID: W97-0209) selectional preference and sense disambiguation
• (ACL ID: W97-0301) a linear observed time statistical parser based on maximum entropy models
• (ACL ID: W97-0304) text segmentation using exponential models
• (ACL ID: W97-0309) aggregate and mixed-order markov models for statistical language processing
• (ACL ID: W97-0314) inducing terminology for lexical acquisition
• (ACL ID: W97-0322) distinguishing word senses in untagged text
• (ACL ID: W97-0509) application of nlp technologyto production of closed-caption tv. programs in japanese for the hearing impaired
• (ACL ID: W97-1003) a preliminary study of word clustering based on syntactic behavior
• (ACL ID: W97-1005) a statistical decision making method
• (ACL ID: W97-1010) learning stochastic categorial grammars
• (ACL ID: W97-1014) word triggers and the em algorithm
• (ACL ID: W98-0701) general word sense disambiguation method based on a full sentential context
• (ACL ID: W98-1105) semantic tagging using a probabilistic context free grammar
• (ACL ID: W98-1115) edge-based best-first chart parsing
• (ACL ID: W98-1122) automatic acquisition of phrase grammars for stochastic language modeling
• (ACL ID: W98-1206) the effect of alternative tree epresentatmns on tree bank grammars
• (ACL ID: W98-1304) robust parsing using a hidden markov model
• (ACL ID: W99-0604) improved alignment models for statistical machine translation
• (ACL ID: W99-0613) unsupervised models for named entity classification
• (ACL ID: W99-0627) taking the load off the conference chairs-towards a digital paper-routing assistant
• (ACL ID: W99-0631) an iterative approach to estimating frequencies over a semantic hierarchy
• (ACL ID: W99-0702) experiments in unsupervised entropy-based corpus segmentation
• (ACL ID: W99-0908) text classification by bootstrapping with keywords, em and shrinkage
• (ACL ID: X96-1033) a simple probabilistic approach to classification and routing
• (ACL ID: X98-1014) algorithms that learn to extract information bbn