• About
    • Mission & History
    • Board of Directors
  • People
    • AI Committee
    • Affiliated Faculty
    • Students
    • Alumni
  • Research
    • Computer Vision
    • Computational Biology and Medicine
    • Human Computer Interaction
    • Machine Learning
    • Multimedia Signal Processing
    • Natural Language Processing
    • Robotics
    • Systems and AI
  • Projects
    • Blog
    • Sponsored Projects
    • Publications
  • Education
    • Courses and Educational Resources
    • Programs
  • Industry
    • Industrial Affiliates
    • How to engage
  • Resources
    • Data
    • Software
    • Hardware
  • Join Us
    • Graduate Admissions
    • Postdoc Positions
    • Faculty Positions
    • FAQ
  • About
  • Mission & History
  • Board of Directors
  • People
  • AI Committee
  • Affiliated Faculty
  • Students
  • Alumni
  • Research
  • Computer Vision
  • Computational Biology and Medicine
  • Human Computer Interaction
  • Machine Learning
  • Multimedia Signal Processing
  • Natural Language Processing
  • Robotics
  • Systems and AI
  • Projects
  • Blog
  • Sponsored Projects
  • Publications
  • Education
  • Courses and Educational Resources
  • Programs
  • Industry
  • Industrial Affiliates
  • How to engage
  • Resources
  • Data
  • Software
  • Hardware
  • Join Us
  • Graduate Admissions
  • Postdoc Positions
  • Faculty Positions
  • FAQ
Type the word you want to search for and press ENTER.
A-Z Content, Page Guide
ABC-ÇDEFGHI-İLMNPRS-ŞTU-Ü
A
AboutArabic-ALBERTA Prediction Framework for Fast Sparse Triangular SolvesAvailable Positions: Learning Rare Events in Autonomous DrivingA new single input multiple output deep temporal regression network (DTRN)AffectON: Incorporating Affect Into Dialog GenerationAll NewsAll EventsAll AnnouncementsArtificial IntelligenceAI FellowshipsAI CommitteeAffiliated FacultyAll BlogsApplicationAlumniAI Meetings
B
BeyondMoore: Pioneering a New Path in Parallel Programming Beyond Moore’s LawBoard of Directors
C-Ç
Courses and Educational ResourcesCan Learned Frame-Prediction Compete with Block-Motion Compensation for Video Coding?College of Engineering Outstanding Faculty AwardCyberphysical Blockchain-Enabled Peer-to-Peer Energy TradingCRAFT: A Benchmark for Causal Reasoning About Forces and InTeractionsCourses offeredComputer VisionComputational Biology and Medicine
D
DataDiagnostic Tools for Communication Pathologies in Parallel ArchitecturesDeep Learning for Image/Video Restoration and CompressionData AnalyticsDigital Signal ProcessingDL for Image/Video Nonlinear Signal ProcessingDL for BioinformaticsDisplaying Realistic Haptic Feedback on Touch Surfaces Using Machine/Deep LearningDistributed Systems Intelligence
E
EducationEmotion Dependent Domain Adaptation for Speech Driven Affective Facial Feature SynthesisEstimation of human force in physical human-robot interaction (pHRI) via machine/deep learningEducational Resources
F
Frequently Asked QuestionsFaculty Positions
G
Graduate ProgramsGraduate AdmissionsGrounded Language Understanding
H
HardwareHow to engageHuman Computer Interaction
I-İ
Industrial AffiliatesIndustryIntention Detection for Physical Human-Robot Interaction Using Machine/Deep Learning
L
Latest Computational Biology and Medicine PublicationsLatest Computer Vision PublicationsLatest Human-Computer Interaction PublicationsLatest Machine Learning PublicationsLatest Multimedia Signal Processing PublicationsLatest Natural Language Processing PublicationsLatest Robotics PublicationsLatest Systems and AI PublicationsLatest Multimodal Signal Processing PublicationsLatest Human Computer Interaction PublicationsLatest Systems & AI Publications
M
Mission & HistoryMultimedia Signal ProcessingMachine LearningMO-RL of SC for ManipulatorsMachine Learning for Multimodal and Intelligent User Interfaces
N
NewsNatural Language ProcessingNonequilibrium Physics and Machine Learning
P
ProgramsPostdoctoral ResearcherProfessional ProgramsProjectsPublicationsPositionsPostdoc PositionsPeoplePast ProjectsPast AI Meetings
R
ResourcesResearchReward Learning From Very Few DemonstrationsRoboticsResearch Highlights
S-Ş
SoftwareSparCity: Optimization and Co-design Framework for Sparse ComputationState-of-the-art Techniques for Deep Edge IntelligenceSample PageSupport LettersSystems and AISummer InternshipsStudents
T
The Road Less Travelled: One-Shot Learning of Rare Events in Autonomous Driving
U-Ü
Undergraduate Tracks
2
20202019201820172016
3
3D Perception for Creativity Assistance
HomeLatest Natural Language Processing Publications
Latest Natural Language Processing Publications
  • Publications
    • Computer Vision
    • Computational Biology & Medicine
    • Human Computer Interaction
    • Machine Learning
    • Multimedia Signal Processing
    • Natural Language Processing
    • Robotics
    • Systems And AI
  • Relational symbol grounding through affordance learning: An overview of the reground project Grounding Language Understanding (GLU 2017) ISCA Satellite Workshop of Interspeech 2017
    L Antanas,OA Can,J DavisHide
    2017

    More

    Abstract

    Symbol grounding is the problem of associating symbols from language with a corresponding referent in the environment. Traditionally, research has focused on identifying single objects and their properties. The ReGround project hypothesizes that the grounding process must consider the full context of the environment, including multiple objects, their properties, and relationships among these objects. ReGround targets the development of a novel framework for “affordance grounding”, by which an agent placed in a new environment...

    View details for http://reground.cs.kuleuven.be/sites/reground.cs.kuleuven.be/files/Relational%20Symbol%20Grounding%20through%20Affordance%20Learning_An%20Overview%20of%20the%20ReGround%20Project.pdf

  • Parsing with context embeddings Proceedings of the CoNLL 2017
    Ö Kırnap,BF Önder,D YuretHide
    2017

    More

    Abstract

    We introduce context embeddings, dense vectors derived from a language model that represent the left/right context of a word instance, and demonstrate that context embeddings significantly improve the accuracy of our transition based parser. Our model consists of a...

    View details for https://www.aclweb.org/anthology/K17-3008.pdf

  • Why neural translations are the right length Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
    X Shi,K Knight,D YuretHide
    2016

    More

    Abstract

    Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2278–2282, Austin, Texas, November 1-5, 2016. c 2016 Association for Computational Linguistics Why Neural Translations are the Right Length Xing Shi1, Kevin Knight1, and Deniz Yuret2 1Information Sciences Institute & Computer Science Department University of Southern California {xingshi,knight}@isi.edu 2Computer Engineering, Koç University dyuret@ku.edu.tr We investigate how neural, encoder-decoder translation systems output target strings of...

    View details for https://www.aclweb.org/anthology/D16-1248.pdf

  • Transfer learning for low-resource neural machine translation Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
    B Zoph,D Yuret,J May,K KnightHide
    2016

    More

    Abstract

    The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves Bleu scores across a range of low-resource languages. Our key idea is to first train a high-resource language pair (the parent model), then transfer some of the learned parameters to the low-resource pair (the child model) to initialize and constrain training. Using our transfer learning method we...

    View details for https://arxiv.org/abs/1604.02201

  • Natural language communication with robots Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
    Y Bisk,D Yuret,D MarcuHide
    2016

    More

    Abstract

    We propose a framework for devising empirically testable algorithms for bridging the communication gap between humans and robots. We instantiate our framework in the context of a problem setting in which humans give instructions to robots using unrestricted natural language commands, with instruction sequences being subservient to building complex goal configurations in a blocks world. We show how one can collect meaningful training data and we propose three neural architectures for interpreting contextually...

    View details for https://www.aclweb.org/anthology/N16-1089.pdf

  • Learning grammatical categories using paradigmatic representations: Substitute words for language acquisition Proceedings of COLING 2016
    MA Yatbaz,V Cirik,A Küntay,D YuretHide
    2016

    More

    Abstract

    Learning syntactic categories is a fundamental task in language acquisition. Previous studies show that co-occurrence patterns of preceding and following words are essential to group words into categories. However, the neighboring words, or frames, are rarely repeated exactly in the data. This creates data sparsity and hampers learning for frame based models. In this work, we propose a paradigmatic representation of word context which uses probable substitutes instead of frames. Our experiments on child-directed speech show...

    View details for https://www.aclweb.org/anthology/C16-1068.pdf

  • Charner: Character-level named entity recognition Proceedings of COLING 2016
    O Kuru,OA Can,D YuretHide
    2016

    More

    Abstract

    We describe and evaluate a character-level tagger for language-independent Named Entity Recognition (NER). Instead of words, a sentence is represented as a sequence of characters. The model consists of stacked bidirectional LSTMs which inputs characters and outputs tag probabilities for each character. These probabilities are then converted to consistent word level named entity tags using a Viterbi decoder. We are able to achieve close to state-of-the-art NER performance in seven languages with the same basic model...

    View details for https://www.aclweb.org/anthology/C16-1087.pdf

  • Learning grammatical categories using paradigmatic representations: Substitute words for language acquisition Proceedings of COLING 2016
    MA Yatbaz,V Cirik,A Küntay,D YuretHide
    2016

    More

    Abstract

    Learning syntactic categories is a fundamental task in language acquisition. Previous studies show that co-occurrence patterns of preceding and following words are essential to group words into categories. However, the neighboring words, or frames, are rarely repeated exactly in the data. This creates data sparsity and hampers learning for frame based models. In this work, we propose a paradigmatic representation of word context which uses probable substitutes instead of frames. Our experiments on child-directed speech show...

    View details for https://www.aclweb.org/anthology/C16-1068.pdf

  • Why neural translations are the right length Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
    X Shi,K Knight,D YuretHide
    2016

    More

    Abstract

    We investigate how neural, encoder-decoder translation systems output target strings of...

    View details for https://www.aclweb.org/anthology/D16-1248.pdf

KUIS AI on Social Media
Download Our Mobile App
Contact

Rumelifeneri Yolu 34450
Sarıyer, İstanbul / Türkiye

ai-admissions@ku.edu.tr
Phone (central): 0212 338 1000 Fax: +90 212 338 1205
Access to Campuses and
Transportation Services
© 2021 Koç University
When you visit a website, information is stored in your browser, mostly in the form of cookies. This information may be about you, your preferences or your device, and is often used to make the site work as you expect it to. The information does not usually identify you directly, it is meant to provide you with a more personalized web experience. You can choose not to allow some cookies. Click on the different category headings to learn more and change our default settings. Cookie Notice
Necessary Cookies
These cookies are necessary for the website to function and cannot be turned off in our systems.
Statistical Cookies
These cookies are used to provide insight into how we can improve our service to all our users and to understand how you interact with our website as an anonymous user.
Targeting Cookies
These cookies are used to create your profile and provide ads relevant to your interests. It is also used to limit the number of times you see an ad, as well as help measure the effectiveness of the ad campaign.
Cookie Policy
Cookies are used to personalize content and ads, to provide social media features and to analyze our traffic. You can accept all cookies with the "Allow All" option or you can edit the settings with the "Customize Settings" option.
Customize Settings