You are now leaving the DARPA.mil website that is under the control and management of DARPA. The appearance of hyperlinks does not constitute endorsement by DARPA of non-U.S. Government sites or the information, products, or services contained therein. Although DARPA may or may not use these sites as additional distribution channels for Department of Defense information, it does not exercise editorial control over all of the information that you may find at these locations. Such links are provided consistent with the stated purpose of this website.

After reading this message, click to continue immediately.

Go Back

/ Information Innovation Office (I2O)

Broad Operational Language Translation (BOLT)

The Broad Operational Language Translation (BOLT) program is aimed at enabling communication with non-English-speaking populations and identifying important information in foreign-language sources by: 1) allowing English-speakers to understand foreign-language sources of all genres, including chat, messaging and informal conversation; 2) providing English-speakers the ability to quickly identify targeted information in foreign-language sources using natural-language queries; and 3) enabling multi-turn communication in text and speech with non-English speakers. If successful, BOLT would deliver all capabilities free from domain or genre limitations.

Program Manager: Dr. Boyan Onyshkevych

Contact: boyan.onyshkevych@darpa.mil

The content below has been generated by organizations that are partially funded by DARPA; the views and conclusions contained therein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of DARPA or the U.S. Government.

Report a problem: opencatalog@darpa.mil

Last updated: November 13, 2015

TeamProjectCategoryCodeDescriptionLicense
THUnderBOLT - Sub OOV and Name Detection OOV and Name Detection ostendor@u.washington.edu The OOV and Name Detection module detects out-of-vocabulary (OOV) and name regions in ASR output. The software developed under BOLT includes code for wrapping the MALLET and Stanford parser, for performing feature extraction and various data manipulation, and for scoring outputs. Development under BOLT also includes modifications to Stanford parser, which include grammar changes for OOV/error rules and for epsilon arcs in confusion networks, as well as code changes to train a log-linear model that is used for scoring the added rules. (Perl/Java) UGPR
THUnderBOLT - Sub Error Processing and Answer Merging Error Processing and Answer Merging frederic.bechet@lif.univ-mrs.fr The Error Processing and Answer Merging module includes error processing and answer merging. The error processing component processes and extends error segments from the ASR Error Detection component and OOV and Name Detection component so that the error segments are easy to clarify. The answer merging component merges clarification with user's initial utterance. (C++) UGPR
THUnderBOLT - Sub macaon Natural Language Processing benoit.favre@lif.univ-mrs.fr macaon is a tool suite for standard Natural Language Processing tasks (tagging, parsing...) that can process hypotheses. (C/C++) GPL
THUnderBOLT - Sub Word Sense Induction Suite Word Sense Induction james@cs.rochester.edu Word Sense Induction Suite is a suite of scripts used to induce word senses from bilingual alignments, and cluster senses for different words into semantically related sets. (Perl) GPR, COTS
THUnderBOLT - Sub Word Sense Tagger Word Sense Tagging james@cs.rochester.edu The Word Sense Tagger is used to: 1) train statistical models for tagging text with word senses; and 2) apply those models for tagging new text with word senses. (Ruby/JRuby) GPR, CPL, GPL, LGPL, COTS
ASTRAL - BBN BBN BOLT Arabic MT System Machine Translation BOLT-software-requests@bbn.com Software translates Arabic input text to English. (C++/Perl) UGPR
ASTRAL - BBN BBN BOLT Arabic MT Trainer Machine Translation BOLT-software-requests@bbn.com Software trains models of Arabic-English MT system. (C++/Perl) UGPR
ASTRAL - BBN BBN BOLT Chinese MT System Machine Translation BOLT-software-requests@bbn.com Software translates Chinese input text to English. (C++/Perl) UGPR
ASTRAL - BBN BBN BOLT Chinese MT Trainer Machine Translation BOLT-software-requests@bbn.com Software trains models of Chinese-English MT system. (C++/Perl) UGPR
ASTRAL - BBN Neural Network Trainer Machine Translation BOLT-software-requests@bbn.com Software trains neural network models. (C++) UGPR
ASTRAL - BBN Unsupervised Morphological Segmenter Machine Translation BOLT-software-requests@bbn.com Software trains unsupervised models of morphological segmenter. (Java) UGPR
ASTRAL - BBN English paraphraser Machine Translation BOLT-software-requests@bbn.com Software generates paraphrases of English sentences. (C++) UGPR
ASTRAL - BBN BBN BOLT IR Retrieval System Information Retrieval BOLT-software-requests@bbn.com Software provides lists of ranked snippets from a large corpus in response to a natural language query. (C++/Python) UGPR
ASTRAL - BBN BBN BOLT IR Clustering System Information Retrieval BOLT-software-requests@bbn.com Software groups lists of snippets into thematic clusters with labels. (C++/Python) UGPR
ASTRAL - BBN BBN TransTalk: Speech-to-Speech Translator with Interactive Error Detection and Resolution Speech-to-Speech Translation BOLT-software-requests@bbn.com The software system is a speech-to-speech translation application for Windows-based devices that allows speakers to communicate across language barriers. The system includes novel functionality to prevent communication failure that detects speech recognition and translation errors and engages in interactive dialog with the users to recover from those errors. (Java/C++) COTS, UGPR
ASTRAL - BBN WMS2 Informal Content Analyzer for Arabic NLP BOLT-software-requests@bbn.com This is the core text content analysis engine for informal Arabic integrated into BBN Web Monitoring System. This engine integrates with the LW informal MT product. (C++/C#) COTS
ASTRAL - BBN WMS2 Informal Content Analyzer for Chinese NLP BOLT-software-requests@bbn.com This is the core text content analysis engine for informal Chinese integrated into BBN Web Monitoring System. This engine integrates with the LW informal MT product. (C++/C#) COTS
ASTRAL - SDL Informal Arabic-English MT Engine Machine Translation bolt.software.requests@sdl.com This is Informal Arabic-English COTS machine translation software that is commercialized by SDL Government. (C++) COTS
ASTRAL - SDL Informal Chinese-English MT Engine Machine Translation bolt.software.requests@sdl.com This is Informal Chinese-English COTS machine translation software that is commercialized by SDL Government. (C++) COTS
ASTRAL - CADIM MADAMIRA: Base Phrase Chunking Component NLP, shallow parsing cadim@ccls.columbia.edu Base Phrase Chunking (BPC), also known as shallow syntactic parsing, is the process by which adjacent words are grouped together to form nonrecursive chunks in a sentence. The base chunks we currently recognize are: ADJP (Adjectival phrase), ADVP (Adverbial phrase), CONJP (Conjunctive phrase), FRAG (Fragment), INTJ (Interjective phrase), LST (List), NAC (Not a Constituent), NP (Noun phrase), PP (Prepositional phrase), PRN (Parenthetical phrase), S (Sentence marker), SBAR (Subjunctive construction), SBARQ (Subjunctive question), VP (Verb phrase), WHADVP (Adverbial phrase 'Wh' question), WHNP (Noun phrase 'Wh' question), and WHPP (Prepositional phrase 'Wh' question). (Java/Perl) NCSLA
ASTRAL - CADIM MADAMIRA: NER component NLP, Named Entity Identification and Classification cadim@ccls.columbia.edu MADAMIRA NER component is designed to identify and classify all occurrences of named entities in an Arabic text. The three categories that a named entity can fall under are: ORGANIZATION, LOCATION, and PERSON. (Java) NCSLA
ASTRAL - CADIM MADAMIRA: tokenization, lemmatization, diacritization, POS tagging Tokenization, lemmatization, diacritization, POS tagging, segmentation, MSA, Dialectal Arabic cadim@ccls.columbia.edu MADAMIRA is a system for Morphological Analysis and Disambiguation for Arabic. Its primary purpose is to derive as much linguistic information as possible about each word in a given text, thereby reducing or eliminating any ambiguity surrounding the word. MADAMIRA's core functionality includes: tokenization, part-of-speech tagging, morphological disambiguation for a full range of morphological features, lemmatization, diacritization, named entity recognition, and base phrase chunking. (Java/Perl) NCSLA
ASTRAL - CADIM MADA-ARZ Tokenization, lemmatization, diacritization, POS tagging, segmentation, Egyptian Arabic cadim@ccls.columbia.edu MADA-ARZ is an adaptation of MADA (Version 3.2), built to handle the Egyptian dialect. For the most part, the operation of MADA-ARZ is the same as MADA 3.2. MADA 3.2 is a system for Morphological Analysis and Disambiguation for Arabic. Its primary purpose is to derive as much linguistic information as possible about each word in a given text, thereby reducing or eliminating any ambiguity surrounding the word. MADA 3.2 also contains a general tokenizer. (Perl) NCSLA
DELPHI - IBM IBM Arabic Front-End Processor Statistical Machine Translation resweb@us.ibm.com Software for processing Arabic input and performing source-side analysis, including segmentation, tokenization, number classing, orthography normalization, and light spelling correction. (C++) GPR
DELPHI - IBM IBM Chinese Front-End Processor Statistical Machine Translation resweb@us.ibm.com Software for processing Chinese input and performing source-side analysis, including segmentation, tokenization, and number classing. (C++) GPR
DELPHI - IBM IBM DTM2 Decoder Statistical Machine Translation resweb@us.ibm.com A maximum-entropy, phrase-based decoder for statistical machine translation. (C++) GPR
DELPHI - IBM IBM ForSyn Decoder Statistical Machine Translation resweb@us.ibm.com A Formal Syntax Statistical Machine translation decoder. The decoder is a forest-to-string, hierarchical decoder. (C++) GPR
DELPHI - IBM IBM XML parsing and reformatting scripts Statistical Machine Translation resweb@us.ibm.com A collection of scripts to convert from and to the XML format required by NIST to deliver BOLT input/output. (Perl) GPR
Linguistic Data Consortium LDC2014E112 BOLT Uzbek Language Pack and LDC2014E115 BOLT Turkish Language Pack Linguistics ldc@ldc.upenn.edu Support linguistic research in leveraging language-universal resources, projecting from related-language resources, and fully exploiting a broad range of language-specific resources. NCSLA
TeamTitleLink
BBN Trait-Based Hypothesis Selection For Machine Translation
BBN, Microsoft Research, Johns Hopkins University Machine Translation of Arabic Dialects
BBN Systematic Comparison of Professional and Crowdsourced Reference Translations for Machine Translation
BBN Factored Soft Source Syntactic Constraints for Hierarchical Machine Translation
BBN Semi-Supervised Word Sense Disambiguation for Mixed-Initiative Conversational Spoken Language Translation
BBN Variable-Span Out-of-Vocabulary Named Entity Detection
BBN Interactive Error Resolution Strategies for Speech-to-Speech Translation Systems
BBN Incremental Topic-Based Translation Model Adaptation for Conversational Spoken Language Translation
BBN ASR Error Detection in a Conversational Spoken Language Translation System
BBN Batch-mode Semi-supervised Active Learning for Statistical Machine Translation
BBN Active Error Detection and Resolution for Speech-to-Speech Translation
BBN Detecting OOV Named Entities in Conversational Speech
BBN Automatic Pronunciation Prediction for Text-to-Speech Synthesis of Dialectal Arabic in a Speech-to-Speech Translation System
BBN Speech Paralinguistic Event Detection Using Probabilistic Time-Series Smoothing and Masking
BBN A Study on the Effect of Prosodic Emphasis on Overall Speech Translation Quality
BBN, USC, University of Cambridge, Columbia University, University of Oxford, University of Edinburgh, University of Southern California Semantics-Based Machine Translation with Hyperedge Replacement Grammars
(Team BBN) Columbia University, Nuance Communications Dependency Parsing of Modern Standard Arabic with Lexical and Inflectional Features
(Team BBN) Columbia University Automatic Extraction of Morphological Lexicons from Morphologically Annotated Corpora
(Team BBN) Aix-Marseille University, Multimedia, InfoRmation Systems and Advanced Computing Laboratory, Columbia University The Effects of Factorizing Root and Pattern Mapping in Translating between Tunisian Arabic and Standard Arabic
(Team BBN) Columbia University Morphological Analysis and Disambiguation for Dialectal Arabic
(Team BBN) Columbia University Automatic Morphological Enrichment of a Morphologically Underspecified Treebank
(Team BBN) Columbia University Dialectal Arabic to English Machine Translation: Pivoting through Modern Standard Arabic
(Team BBN) Columbia University Processing Spontaneous Orthography
(Team BBN) Columbia University Automatic Correction and Extension of Morphological Annotations
(Team BBN) Columbia University Elissa: A Dialectal to Standard Arabic Machine Translation System
(Team BBN) Columbia University Lost and Found in Translation: The Impact of Machine Translated Results on Translingual Information Retrieval
(Team BBN) Columbia University Can Automatic Post-Editing Make MT More Meaningful?
(Team BBN) Columbia University Identifying Broken Plurals, Irregular Gender, and Rationality in Arabic Text
(Team BBN) Columbia University ASMA: A system for Automatic Segmentation and Morpho-syntactic Disambiguation of Modern Standard Arabic
(Team BBN) Columbia University, George Washington University Sentence-Level Dialect Identification in Arabic
(Team BBN) Columbia University Code-Switch Point Detection in Arabic
(Team BBN) Columbia University Multiword Expressions in the Context of Statistical Machine Translation
(Team BBN) Columbia University ANEAR: Automatic Named Entity Aliasing Resolution
(Team BBN) Columbia University Building a Lexical Semantic Resource for Arabic Morphological Patterns
(Team BBN) Columbia University Token Level Identification of Linguistic Code Switching
(Team BBN) Columbia University Simplified Guidelines for the Creation of Large Scale Dialectal Arabic Annotations
(Team BBN) Columbia University Building an Arabic Multiword Expressions Repository
(Team BBN) Columbia University A Pilot PropBank Annotation for Quranic Arabic
(Team BBN) University of California - Berkeley Easy Victories and Uphill Battles in Coreference Resolution
(Team BBN) University of California - Berkeley Error-Driven Analysis of Challenges in Coreference Resolution
(Team BBN) University of California - Berkeley Decentralized Entity-Level Modeling for Coreference Resolution
(Team BBN) University of California - Berkeley Training Factored PCFGs with Expectation Propagation
(Team BBN) University of California - Berkeley Fast Inference in Phrase Extraction Models with Belief Propagation
(Team BBN) University of California - Berkeley Large-Scale Syntactic Language Modeling with Treelets
(Team BBN) University of California - Berkeley Coreference Semantics from Web Features
(Team BBN) University of California - Berkeley Transforming Trees to Improve Syntactic Convergence
(Team BBN) National Research Council Simulating Discriminative Training for Linear Mixture Adaptation in Statistical Machine Translation
(Team BBN) National Research Council Vector Space Model for Adaptation in Statistical Machine Translation
(Team BBN) National Research Council, University of Maryland, University of Chicago, Johns Hopkins University, IBM SenseSpotting: Never Let your Parallel Data Tie You to an Old Domain
(Team BBN) National Research Council Improved Reordering for Phrase-Based Translation Using Sparse Features
(Team BBN) National Research Council Adaptation of Reordering Models for Statistical Machine Translation
(Team BBN) National Research Council A Semantic Evaluation of Machine Translation Lexical Choice
(Team BBN) National Research Council NRC: A Machine Translation Approach to Cross-Lingual Word Sense Disambiguation
(Team BBN) Hong Kong University of Science and Technology LTG vs. ITG Coverage of Cross-Lingual Verb Frame Alternations
(Team BBN) Hong Kong University of Science and Technology Fully Automatic Semantic MT Evaluation
(Team BBN) Hong Kong University of Science and Technology Towards a Predicate-Argument Evaluation for MT
(Team BBN) Hong Kong University of Science and Technology Unsupervised vs. Supervised Weight Estimation for Semantic MT Evaluation Metrics
(Team BBN) Hong Kong University of Science and Technology Accuracy and Robustness in Measuring the Lexical Similarity of Semantic Role Fillers for Automatic Semantic MT Evaluation
(Team BBN) Hong Kong University of Science and Technology From Finite-State to Inversion Transductions: Toward Unsupervised Bilingual Grammar Induction
(Team BBN) Hong Kong University of Science and Technology Combining Top-down and Bottom-up Search for Unsupervised Induction of Transduction Grammars
(Team BBN) Hong Kong University of Science and Technology Iterative Rule Segmentation under Minimum Description Length for Unsupervised Transduction Grammar Induction
(Team BBN) Hong Kong University of Science and Technology MEANT at WMT 2013: A Tunable, Accurate yet Inexpensive Semantic Frame Based MT Evaluation Metric
(Team BBN) Hong Kong University of Science and Technology Unsupervised Transduction Grammar Induction via Minimum Description Length
(Team BBN) Hong Kong University of Science and Technology Improving Machine Translation by Training Against an Automatic Semantic Frame Based Evaluation Metric
(Team BBN) Hong Kong University of Science and Technology FREESTYLE: A Challenge-Response System for Hip Hop Lyrics via Unsupervised Induction of Stochastic Transduction Grammars
(Team BBN) Hong Kong University of Science and Technology Can Informal Genres be Better Translated by Tuning on Automatic Semantic Metrics?
(Team BBN) Hong Kong University of Science and Technology Modeling Hip Hop Challenge-Response Lyrics as Machine Translation
(Team BBN) Hong Kong University of Science and Technology Segmenting vs. Chunking: Unsupervised ITG Induction via Minimum Conditional Description Length
(Team BBN) Hong Kong University of Science and Technology Bayesian Induction of Bracketing Inversion Transduction Grammars
(Team BBN) Hong Kong University of Science and Technology Learning to Freestyle: Hip Hop Challenge-Response Induction via Transduction Rule Segmentation
(Team IBM) University of Maryland Why Not Grab a Free Lunch? Mining Large Corpora for Parallel Sentences to Improve Translation Modeling
(Team IBM) University of Maryland Encouraging Consistent Translation Choices
(Team IBM) University of Maryland Meaning Matching for Cross-Language Information Retrieval
(Team IBM) University of Maryland Topic Models for Dynamic Translation Model Adaptation
(Team IBM) University of Maryland Looking Inside the Box: Context-Sensitive Translation for Cross-Language Information Retrieval
(Team IBM) University of Maryland Combining Statistical Translation Techniques for Cross-Language Information Retrieval
(Team IBM) University of Maryland Leveraging Statistical Transliteration for Dictionary-Based English-Bengali CLIR of OCR'd Text
(Team IBM) University of Maryland Two Algorithms for Finding k Shortest Paths of a Weighted Pushdown Automaton
(Team IBM) University of Maryland, Johns Hopkins University Massively Parallel Suffix Array Queries and On-Demand Phrase Extraction for Statistical Machine Translation Using GPUs
(Team IBM) University of Maryland Modeling Syntactic and Semantic Structures in Hierarchical Phrase-based Translation
(Team IBM) University of Maryland Flat vs. Hierarchical Phrase-Based Translation Models for Cross-Language Information Retrieval
(Team IBM) University of Maryland Sequential Testing in Classifier Evaluation Yields Biased Estimates of Effectiveness
(Team IBM) University of Maryland Mr. MIRA: Open-Source Large-Margin Structured Learning on MapReduce
(Team IBM) University of Maryland Online Relative Margin Maximization for Statistical Machine Translation
(Team IBM) University of Maryland Marginal Matching for Translation Model Adaptation
(Team IBM) University of Maryland Simulating Early-Termination Search for Verbose Spoken Queries
(Team IBM) University of Maryland, National Research Council Canada, SDL Research Measuring Machine Translation Errors in New Domains
(Team IBM) RWTH Aachen University A Phrase Orientation Model for Hierarchical Machine Translation
(Team IBM) RWTH Aachen University Length-incremental Phrase Training for SMT
(Team IBM) RWTH Aachen University Phrase Training Based Adaptation for Statistical Machine Translation
(Team IBM) RWTH Aachen University A Simple and Effective Weighted Phrase Extraction for Machine Translation Adaptation
(Team IBM) RWTH Aachen University A Performance Study of Cube Pruning for Large-Scale Hierarchical Machine Translation
(Team IBM) RWTH Aachen University Sequence Labeling-based Reordering Model for Phrase-based SMT
(Team IBM) RWTH Aachen University Semantic Cohesion Model for Phrase-Based SMT
(Team IBM) RWTH Aachen University A Tagging-style Reordering Model for Phrase-based SMT
IBM Flexible and Efficient Hypergraph Interactions for Joint Hierarchical and Forest-to-String Decoding
IBM, Chinese Academy of Sciences, QCCUNY Violation-Fixing Perceptron and Forced Decoding for Scalable MT Training
IBM, University of Massachusetts Incorporating Social Anchors for Ad Hoc Retrieval
(Team IBM) University of Massachusetts Bi-directional Linkability From Wikipedia to Documents and Back Again: UMass at TREC 2012 Knowledge Base Acceleration Track
(Team IBM) University of Massachusetts A Neighborhood Relevance Model for Entity Linking
(Team IBM) University of Massachusetts Sentiment Diversification with Different Biases
(Team IBM) University of Massachusetts Term Level Search Result Diversification
(Team IBM) University of Massachusetts Extracting Query Facets from Search Results
(Team IBM) University of Massachusetts Retrieving Opinions from Discussion Forums
(Team IBM) University of Massachusetts Constructing Query-Specific Knowledge Bases
(Team IBM) Stanford University Bilingual Word Embeddings for Phrase-Based Machine Translation
(Team IBM) Stanford University Parsing Models for Identifying Multiword Expressions
(Team IBM) Stanford University Positive Diversity Tuning for Machine Translation System Combination
(Team IBM) Stanford University Feature-Rich Phrase-based Translation: Stanford University's Submission to the WMT 2013 Translation Task
(Team IBM) Stanford University Fast and Adaptive Online Training of Feature-Rich Translation Models
(Team IBM) Stanford University The Stanford Post-Editing Corpus: Collection and Analysis
(Team IBM) Stanford University A Class-Based Agreement Model for Generating Accurately Inflected Translations
(Team IBM) Stanford University, Johns Hopkins University Entity Clustering Across Languages
(Team IBM) University of Le Mans Semi-supervised Transliteration Mining from Parallel and Comparable Corpora
(Team IBM) University of Le Mans Phrase Probabilities Calculation for Statistical Machine Translation by using Belief Functions
(Team IBM) University of Le Mans Continuous Space Translation Models for Phrase-Based Statistical Machine Translation
(Team IBM) University of Le Mans CSLM - A modular Open-Source Continuous Space Language Modeling Toolkit
LDC Expanding Arabic Treebank to Speech: Results from Broadcast News
(Team BBN) Columbia University Conventional Orthography for Dialectal Arabic
(Team BBN) Columbia University A Morphological Analyzer for Egyptian Arabic
(Team LDC) Brandeis University Extending and Scaling up the Chinese Treebank Annotation
(Team LDC) Brandeis University Building a Chinese Lexical Taxonomy
(Team LDC) Brandeis University A Lattice-Based Framework for Joint Chinese Word Segmentation, POS-Tagging and Parsing
(Team LDC) University of Colorado Renewing and Revising SemLink
SDL HyTER: Meaning-Equivalent Semantics for Translation Evaluation
(Team BBN) Columbia University AIDA: Automatic Identification & Glossing of Dialectal Arabic
(Team BBN) Columbia University Learning to Automatically Post-Edit Dropped Words in MT
(Team BBN) CUNY Freeform Text Summarization in Social Sensing
(Team LDC) QCCUNY Linguistic Resources for Entity Linking Evaluation: from Mono-lingual to Cross-lingual
CUNY Combining Flat and Structured Approaches for Temporal Slot Filling or: How Much to Compress?
(Team SRI) QCCUNY, University of Illinois - Urbana-Champaign Analysis and Refinement of Cross-lingual Entity Linking
(Team BBN) CUNY Uncertainty Reduction for Knowledge Discovery and Information Extraction on WWW
(Team BBN) CUNY Relabeling Distantly Supervised Training Data for Temporal Knowledge Base Population
(Team BBN) CUNY CUNY_BLENDER TAC-KBP2012 Entity Linking System and Slot Filling Validation System
(Team BBN) CUNY Combining Social Cognitive Theories with Linguistic Features for Multi-genre Sentiment Analysis
(Team BBN) CUNY Name-aware Machine Translation
(Team BBN) CUNY Joint Bilingual Name Tagging for Parallel Corpora
(Team BBN) OHSU Robust Kaomoji Detection in Twitter
(Team SRI) University of Washington Semi-supervised learning for text classification using feature affinity regularization
(Team SRI) University of Massachusetts Passage-level Evidence for Cross-Language Information Retrieval
(Team SRI) University of Massachusetts Across-Document Neighborhood Expansion: UMass at TAC KBP 2012 Entity Linking
(Team SRI) University of Massachusetts Incorporating Social Anchors for Ad Hoc Retrieval
(Team SRI) University of Massachusetts A Neighborhood Relevance Model for Entity Linking
(Team SRI) University of Texas - Dallas Sentence Dependency Tagging in Online Question Answering Forums
(Team SRI) University of Texas - Dallas Sequence Labeling with Non-Negative Weighted Higher Order Features
(Team SRI) University of Texas - Dallas A Two-step Approach to Sentence Compression of Spoken Utterances
(Team SRI) University of Texas - Dallas Normalization of Text Messages for Text-to-Speech
(Team SRI) University of Texas - Dallas Joint Chinese Word Segmentation, POS Tagging and Parsing
(Team SRI) University of Texas - Dallas Evaluating the effect of normalizing informal text on TTS output
(Team SRI) University of Texas - Dallas Improving Text Normalization Using Character-blocks based Models and System Combination
(Team BBN) CMU, University of Edinburgh Language Model Rest Costs and Space-Efficient Storage
University of Cambridge Extending Hiero Decoding in Moses with Cube Growing
(Team BBN) Hong Kong University of Science and Technology Unsupervised vs. Supervised Weight Estimation for Semantic MT Evaluation Metrics
(Team SRI) Aix-Marseille University ASR Error Segment Localization for Spoken Recovery Strategy
SRI Can You Give Me Another Word for Hyperbaric?: Improving Speech Translation Using Targeted Clarification Questions
(Team BBN) University of Rochester SALL-E: A Situated Agent for Language Learning
(Team BBN) University of Rochester Automatically Deriving Event Ontologies for a CommonSense Knowledge Base
(Team SRI) University of Washington Using Syntactic and Confusion Network Structure for Out-of-vocabulary Word Detection
(Team SRI) Columbia University Localized Detection of Speech Recognition Errors
(Team SRI) Columbia University Clarification Questions with Feedback
LDC Annotation Trees: LDC's Customizable, Extensible, Scalable Annotation Infrastructure
Kneser-Ney Smoothing on Expected Counts
Decoding with Large-Scale Neural Language Models Improves Translation
Automatic Transliteration of Romanized Dialectal Arabic
Sentence Level Dialect Identification for Machine Translation System Selection
A Multidialectal Parallel Corpus of Arabic
Tharwa: A Large Scale Dialectal Arabic - Standard Arabic - English Lexicon
Developing an Egyptian Arabic Treebank: Impact of Dialectal Morphology on Annotation and Tool Development
A Conventional Orthography for Tunisian Arabic
MADAMIRA: A Fast, Comprehensive Tool for Morphological Analysis and Disambiguation of Arabic
Classification of Clean and Noisy Bilingual Movie Audio for Speech-to-Speech Translation Corpora Design
Fusion of Diverse Denoising Systems for Robust Automatic Speech Recognition
Training Ensemble of Diverse Classifiers on Feature Subsets
Toward Transfer of Acoustic Cues of Emphasis Across Languages
Empirical Link Between Hypothesis Diversity and Fusion Performance in an Ensemble of Automatic Speech Recognition Systems
Fast and Robust Neural Network Joint Models for Statistical Machine Translation
Lightly-Supervised Word Sense Translation Error Detection for an Interactive Conversational Spoken Language Translation System
Source-Error Aware Phrase-Based Decoding for Robust Conversational Spoken Language Translation

Software

Publications