Table of contents

Anthology	Volume	Papers
P04-1	Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)	89
P04-2	Proceedings of the ACL Student Research Workshop	13
P04-3	Proceedings of the ACL Interactive Poster and Demonstration Sessions	35

Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)

Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)
[P04-1000]:

Optimization in Multimodal Interpretation
[P04-1001]: Joyce Y. Chai | Pengyu Hong | Michelle X. Xhou | Zahar Prasov

Constructivist Development of Grounded Construction Grammar
[P04-1002]: Luc Steels

A Distributional Model of Semantic Context Effects in Lexical Processing
[P04-1003]: Scott McDonald | Chris Brew

Analysis of Mixed Natural and Symbolic Input in Mathematical Dialogs
[P04-1004]: Magdalena Wolska | Ivana Kruijff-Korbayova

A TAG-based noisy-channel model of speech repairs
[P04-1005]: Mark Johnson | Eugene Charniak

Attention Shifting for Parsing Speech
[P04-1006]: Keith B. Hall | Mark Johnson

Discriminative Language Modeling with Conditional Random Fields and the Perceptron Algorithm
[P04-1007]: Brian Roark | Murat Saraclar | Michael Collins | Mark Johnson

Statistical Modeling for Unit Selection in Speech Synthesis
[P04-1008]: Mehryar Mohri | Cyril Allauzen | Michael Riley

Developing a Flexible Spoken Dialog System Using Simulation
[P04-1009]: Grace Chung

Data-Driven Strategies for an Automated Dialogue System
[P04-1010]: Hilda Hardy | Tomek Strzalkowski | Min Wu | Cristian Ursu | Nick Webb | Alan Biermann | R. Bryce Inouye | Ashley McKenzie

Trainable Sentence Planning for Complex Information Presentations in Spoken Dialog Systems
[P04-1011]: Amanda Stent | Rashmi Prassad | Marilyn Walker

User Expertise Modeling and Adaptivity in a Speech-Based E-Mail System
[P04-1012]: Kristiina Jokinen | Kari Kanto

Discriminative Training of a Neural Network Statistical Parser
[P04-1013]: James Henderson

Parsing the WSJ Using CCG and Log-Linear Models
[P04-1014]: Stephen Clark | James R. Curran

Incremental Parsing with the Perceptron Algorithm
[P04-1015]: Michael Collins | Brian Roark

Convolution Kernels with Feature Selection for Natural Language Processing Tasks
[P04-1016]: Jun Suzuki | Hideki Isozaki | Eisaku Maeda

Improving Pronoun Resolution by Incorporating Coreferential Information of Candidates
[P04-1017]: Xiaofeng Yang | Jian Su | Guodong Zhou | Chew-Lim Tan

A Mention-Synchronous Coreference Resolution Algorithm Based On the Bell Tree
[P04-1018]: Xiaoqiang Luo | Abe Ittycheriah | Hongyan Jing | Nanda Kambhatla | Salim Roukos

Learning to Resolve Bridging References
[P04-1019]: Massimo Poesio | Rahul Mehta | Axel Maroudas | Janet Hitzeman

Learning Noun Phrase Anaphoricity to Improve Conference Resolution: Issues in Representation and Optimization
[P04-1020]: Vincent Ng

A Joint Source-Channel Model for Machine Transliteration
[P04-1021]: Haizhou Li | Min Zhang | Jian Su

Collocation Translation Acquisition Using Monolingual Corpora
[P04-1022]: Yajuan Lü | Ming Zhou

Statistical Machine Translation with Word- and Sentence-Aligned Parallel Corpora
[P04-1023]: Chris Callison-Burch | David Talbot | Miles Osborne

Finding Ideographic Representations of Japanese Names Written in Latin Script via Language Identification and Corpus Validation
[P04-1024]: Yan Qu | Gregory Grefenstette

Extracting Regulatory Gene Expression Networks From Pubmed
[P04-1025]: Jasmin Saric | Lars J. Jensen | Peer Bork | Rossitza Ouzounova | Isabel Rojas

Linguistic Profiling for Authorship Recognition and Verification
[P04-1026]: Hans van Halteren

An Empirical Study of Information Synthesis Task
[P04-1027]: Enrique Amigo | Julio Gonzalo | Victor Peinado | Anselmo Peñas | Felisa Verdejo

Mining Metalinguistic Activity in Corpora to Create Lexical Resources Using Information Extraction Techniques: the MOP System
[P04-1028]: Carlos Rodriguez Penagos

Optimizing Typed Feature Structure Grammar Parsing through Non-Statistical Indexing
[P04-1029]: Cosmin Munteanu | Gerald Penn

Head-Driven Parsing for Word Lattices
[P04-1030]: Christopher Collins | Bob Carpenter | Gerald Penn

Balancing Clarity and Efficiency in Typed Feature Logic Through Delaying
[P04-1031]: Gerald Penn

Minimal Recursion Semantics as Dominance Constraints: Translation, Evaluation, and Analysis
[P04-1032]: Ruth Fuchss | Alexander Koller | Joachim Niehren | Stefan Thater

Learning with Unlabeled Data for Text Categorization Using a Bootstrapping and a Feature Projection Technique
[P04-1033]: Youngjoong Ko | Jungyun Seo

The Sentimental Factor: Improving Review Classification Via Human-Provided Information
[P04-1034]: Philip Beineke | Trevor Hastie | Shivakumar Vaithyanathan

A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts
[P04-1035]: Bo Pang | Lillian Lee

Finding Predominant Word Senses in Untagged Text
[P04-1036]: Diana McCarthy | Rob Koeling | Julie Weeds | John Carroll

Unsupervised Sense Disambiguation Using Bilingual Probabilistic Models
[P04-1037]: Indrajit Bhattacharya | Lise Getoor | Yoshua Bengio

Chinese Verb Sense Discrimination Using an EM Clustering Model with Rich Linguistic Features
[P04-1038]: Jinying Chen | Martha Palmer

Relieving the data Acquisition Bottleneck in Word Sense Disambiguation
[P04-1039]: Mona Diab

Enriching the Output of a Parser Using Memory-based Learning
[P04-1040]: Valentin Jijkoun | Maarten de Rijke

Long-Distance Dependency Resolution in Automatically Acquired Wide-Coverage PCFG-Based LFG Approximations
[P04-1041]: Aoife Cahill | Michael Burke | Ruth O'Donovan | Josef Van Genabith | Andy Way

Deep Dependencies from Context-Free Statistical Parsers: Correcting the Surface Dependency Approximation
[P04-1042]: Roger Levy | Christopher Manning

A Study on Convolution Kernels for Shallow Statistic Parsing
[P04-1043]: Alessandro Moschitti

Combining Acoustic and Pragmatic Features to Predict Recognition Performance in Spoken Dialogue Systems
[P04-1044]: Malte Gabsdil | Oliver Lemon

Predicting Student Emotions in Computer-Human Tutoring Dialogues
[P04-1045]: Diane J. Litman | Kate Forbes-Riley

Building Verb Predicates: A Computational View
[P04-1046]: Fernando Gomez

Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II Treebank
[P04-1047]: Ruth O'Donovan | Michael Burke | Aoife Cahill | Josef Van Genabith | Andy Way

Inducing Frame Semantic Verb Classes from WordNet and LDOCE
[P04-1048]: Rebecca Green | Bonnie J. Dorr | Philip Resnik

Paragraph-, Word-, and Coherence-based Approaches to Sentence Ranking: A Comparison of Algorithm and Human Performance
[P04-1049]: Florian Wolf | Edward Gibson

Evaluating Centering-Based Metrics of Coherence
[P04-1050]: Nikiforos Karamanis | Massimo Poesio | Chris Mellish | Jon Oberlander

Computing Locally Coherent Discourses
[P04-1051]: Ernst Althaus | Nikiforos Karamanis | Alexander Koller

Generating Referring Expressions in Open Domains
[P04-1052]: Advaith Siddharthan | Ann Copestake

Discovering Relations among Named Entities from Large Corpora
[P04-1053]: Takaaki Hasegawa | Satoshi Sekine | Ralph Grishman

Dependency Tree Kernels for Relation Extraction
[P04-1054]: Aron Culotta | Jeffrey Sorensen

Classifying Semantic Relations in Bioscience Texts
[P04-1055]: Barbara Rosario | Marti Hearst

Collective Information Extraction with Relational Markov Networks
[P04-1056]: Razvan Bunescu | Raymond Mooney

Error Mining for Wide-Coverage Grammar Engineering
[P04-1057]: Gertjan van Noord

Alternative approaches for Generating Bodies of Grammar Rules
[P04-1058]: Gabriel Infante-Lopez | Maarten de Rijke

Adaptive Chinese Word Segmentation
[P04-1059]: Jianfeng Gao | Andi Wu | Cheng-Ning Huang | Hong qiao Li | Xinsong Xia | Hauwei Qin

Experiments in parallel-text based grammar induction
[P04-1060]: Jonas Kuhn

Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency
[P04-1061]: Dan Klein | Christopher Manning

Annealing Techniques For Unsupervised Statistical Language Learning
[P04-1062]: Noah A. Smith | Jason Eisner

Multi-Engine Machine Translation with Voted Language Model
[P04-1063]: Tadashi Nomoto

Aligning words using matrix factorisation
[P04-1064]: Cyril Goutte | Kenji Yamada | Eric Gaussier

FSA: An Efficient and Flexible C++ Toolkit for Finite State Automata Using On-Demand Computation
[P04-1065]: Stephan Kanthak | Hermann Ney

Improving IBM Word Alignment Model 1
[P04-1066]: Robert C. Moore

A Geometric View on Bilingual Lexicon Extraction from Comparable Corpora
[P04-1067]: Eric Gaussier | J.M. Renders | I. Matveeva | C. Goutte | H. Dejean

Creating Multilingual Translation Lexicons with Regional Variations Using Web Corpora
[P04-1068]: Pu-Jen Cheng | Wen-Hsiang Lu | Jei-Wen Teng | Lee-Feng Chien

Probabilistic Parsing Strategies
[P04-1069]: Mark-Jan Nederhof | Giorgio Satta

An Alternative Method of Training Probabilistic LR Parsers
[P04-1070]: Mark-Jan Nederhof | Giorgio Satta

Wrapping of Trees
[P04-1071]: James Rogers

Splitting Complex Temporal Questions for Question Answering Systems
[P04-1072]: E. Saquete | P. Martínez-Barco | R. Muñoz | J.L. Vicedo

Question Answering Using Constraint Satisfaction: QA-By-Dossier-With-Contraints
[P04-1073]: John Prager | Jennifer Chu-Carroll | Krzysztof Czuba

Applying Machine Learning to Chinese Temporal Relation Resolution
[P04-1074]: Wenjie Li | Kam-Fai Wong | Guihong Cao | Chunfa Yuan

Multi-Criteria-based Active Learning for Named Entity Recognition
[P04-1075]: Dan Shen | Jie Zhang | Jian Su | Guodong Zhou | Chew-Lim Tan

Weakly Supervised Learning for Cross-document Person Name Disambiguation Supported by Information Extraction
[P04-1076]: Cheng Niu | Wei Li | Rohini K. Srihari

Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics
[P04-1077]: Chin-Yew Lin | Franz Josef Och

A Unified Framework For Automatic Evaluation Using 4-Gram Co-occurrence Statistics
[P04-1078]: Radu Soricut | Eric Brill

Extending the BLEU MT Evaluation Method with Frequency Weightings
[P04-1079]: Bogdan Babych | Tony Hartley

Learning Word Sense With Feature Selection and Order Identification Capabilities
[P04-1080]: Zheng-Yu Niu | Dong-Hong Ji | Chew-Lim Tan

A Kernel PCA Method for Superior Word Sense Disambiguation
[P04-1081]: Dekai Wu | Weifeng Su | Marine Carpuat

Using Linguistic Principles to Recover Empty Categories
[P04-1082]: Richard Campbell

Statistical Machine Translation by Parsing
[P04-1083]: I. Dan Melamed

Generalized Multitext Grammars
[P04-1084]: I. Dan Melamed | Giorgio Satta | Benjamin Wellington

Identifying Agreement and Disagreement in Conversational Speech: Use of Bayesian Networks to Model Pragmatic Dependencies
[P04-1085]: Michel Galley | Kathleen McKeown | Julia Hirschberg | Elizabeth Shriberg

Using Conditional Random Fields to Predict Pitch Accents in Conversational Speech
[P04-1086]: Michelle Gregory | Yasemin Altun

Acquiring the Meaning of Discourse Markers
[P04-1087]: Ben Hutchinson

FLSA: Extending Latent Semantic Analysis with Features for Dialogue Act Classification
[P04-1088]: Riccardo Serafin | Barbara Di Eugenio

Proceedings of the ACL Student Research Workshop

Proceedings of the ACL Student Research Workshop
[P04-2000]:

Determining the Specificity of Terms using Compositional and Contextual Information
[P04-2001]: Pum-Mo Ryu

Minimizing the Length of Non-Mixed Initiative Dialogs
[P04-2002]: R. Bryce Inouye

Searching for Topics in a Large Collection of Texts
[P04-2003]: Martin Holub | Jiri Semecky | Jiri Divis

Temporal Context: Applications and Implications for Computational Linguistics
[P04-2004]: Robert Leibscher

Automatic Acquisition of English Topic Signatures Based on a Second Language
[P04-2005]: Xinglong Wang

iSTART: Paraphrase Recognition
[P04-2006]: Chutima Boonthum

Towards a Semantic Classification of Spanish Verbs Based on Subcategorisation Information
[P04-2007]: Eva Esteve Ferrer

Improving the Accuracy of Subcategorizations Acquired from Corpora
[P04-2008]: Naoki Yoshinaga

Robust VPE Detection using Automatically Parsed Text
[P04-2009]: Leif Arda Nielsen

A Machine Learning Approach to German Pronoun Resolution
[P04-2010]: Beata Kouchnir

Beyond N in N-gram Tagging
[P04-2011]: Robbert Prins

A Framework for Unsupervised Natural Language Morphology Induction
[P04-2012]: Christian Monson

Proceedings of the ACL Interactive Poster and Demonstration Sessions

Proceedings of the ACL Interactive Poster and Demonstration Sessions
[P04-3000]:

TransType2 - An Innovative Computer-Assisted Translation System
[P04-3001]: José Esteban | José Lorenzo | Antonio S. Valderrábanos | Guy Lapalme

Improving Domain-Specific Word Alignment for Computer Assisted Translation
[P04-3002]: Wu Hua | Wang Haifeng

Constructing Transliteration Lexicons from Web Corpora
[P04-3003]: Jin-Shea Kuo | Ying-Kuei Yang

Subsentential Translation Memory for Computer Assisted Writing and Translation
[P04-3004]: Jian-Cheng Wu | Thomas C. Chuang | Wen-Chi Shei | Jason S. Chang

Customizing Parallel Corpora at the Document Level
[P04-3005]: Monica Rogati | Yiming Yang

An Automatic Filter for Non-Parallel Texts
[P04-3006]: Chris Pike | I. Dan Melamed

Exploiting Aggregate Properties of Bilingual Dictionaries For Distinguishing Senses of English Words and Inducing English Sense Clusters
[P04-3007]: Charles Schafer | David Yarowsky

Interactive grammar development with WCDG
[P04-3008]: Kilian A. Foth | Michael Daum | Wolfgang Menzel

Wide Coverage Symbolic Surface Realization
[P04-3009]: Charles Callaway

Part-of-Speech Tagging Considering Surface Form for an Agglutinative Language
[P04-3010]: Do-Gil Lee | Hae-Chang Rim

Is Conceptual Combination Influenced by Word Order?
[P04-3011]: Phil Maguire | Arthur Cater

Corpus representativeness for syntactic information acquisition
[P04-3012]: Núria Bel

Exploiting Unannotated Corpora for Tagging and Chunking
[P04-3013]: Rie Kubota Ando

Improving Bitext Word Alignments via Syntax-based Reordering of English
[P04-3014]: Elliott Franco Drabek | David Yarowsky

Hierarchy Extraction based on Inclusion of Appearance
[P04-3015]: Eiko Yamamoto | Kyoko Kanzaki | Hitoshi Isahara

Knowledge intensive e-mail summarization in CARPANTA
[P04-3016]: Laura Alonso | Irene Castellón | Bernardino Casas | Lluís Padró

Finding Anchor Verbs for Biomedical IE Using Predicate-Argument Structures
[P04-3017]: Akane Yakushiji | Yuka Tateisi | Yusuke Miyao | Jun'ichi Tsujii

Resource Analysis for Question Answering
[P04-3018]: Lucian Vlad Lita | Warren A. Hunt | Eric Nyberg

TANGO: Bilingual Collocational Concordancer
[P04-3019]: Jia-Yan Jian | Yu-Chia Chang | Jason S. Chang

Graph-based Ranking Algorithms for Sentence Extraction, Applied to Text Summarization
[P04-3020]: Rada Mihalcea

Compiling Boostexter Rules into a Finite-state Transducer
[P04-3021]: Srinivas Bangalore

Combining Lexical, Syntactic, and Semantic Features with Maximum Entropy Models for Information Extraction
[P04-3022]: Nanda Kambhatla

On the Equivalence of Weighted Finite-state Transducers
[P04-3023]: Julien Quint

A New Feature Selection Score for Multinomial Naive Bayes Text Classification Based on KL-Divergence
[P04-3024]: Karl-Michael Schneider

Incorporating topic information into semantic analysis models
[P04-3025]: Tony Mullen | Nigel Collier

A Practical Solution to the Problem of Automatic Word Sense Induction
[P04-3026]: Reinhard Rapp

Automatic clustering of collocation for detecting practical sense boundary
[P04-3027]: Saim Shin | Key-Sun Choi

Co-training for Predicting Emotions with Spoken Dialogue Data
[P04-3028]: Beatriz Maeireizo | Diane Litman | Rebecca Hwa

Multimodal Database Access on Handheld Devices
[P04-3029]: Elsa Pecourt | Norbert Reithinger

Wysiwym with wider coverage
[P04-3030]: Richard Power | Roger Evans

NLTK: The Natural Language Toolkit
[P04-3031]: Steven Bird | Edward Loper

Dyna: A Language for Weighted Dynamic Programming
[P04-3032]: Jason Eisner | Eric Goldlust | Noah A. Smith

MATCHkiosk: A Multimodal Interactive City Guide
[P04-3033]: Michael Johnston | Srinivas Bangalore

Fragments and Text Categorization
[P04-3034]: Jan Blaták | Eva Mráková | Lubos Popelínsky