Technology in the Field of Language Technology

The organisation of the technologies follows the structure of the upcoming second edition of the HLT-Survey:Language Technology - A Survey of the State of the Art. For each technology, we provide a definition, pointers to the most important players and resources, and the corresponding section from the first edition of the HLT-Survey.

Authoring Tools

Automatic Hyperlinking, Language Checking, Spell Checking, Structure-Based Authoring Assistants.

Coding and Compression

Speech Coding, Speech Enhancement, Text Compression, Text Encryption.

Discourse and Dialogue

Dialogue Modeling, Discourse Modeling, Spoken Dialogue Systems, Spoken Language Dialogue.

Evaluation

Deep Parser Performance Evaluation, Evaluation of Broad-Coverage Natural-Language Parsers, Evaluation of Machine Translation and Translation Tools, Human Factors and User Acceptability, Information Retrieval Evaluation, Speech Input Assessment and Evaluation, Speech Synthesis Evaluation, Usability and Interface Design.

Information Extraction

Answer Extraction, Multimedia Information Extraction, Named Entity Recognition, Relation Extraction, Summarisation, Text Data Mining.

Information Retrieval

Categorisation, Clustering, Multilingual Information Retrieval, Multimedia Retrieval, Presentation and Visualisation, Relevance Ranking, Speech Retrieval, Spoken Document Retrieval, Topic Detection.

Knowledge Representation and Discovery

Automatic Hyperlinking, Knowledge Discovery, Ontologies, Semantic Web.

LT in General

Language Technology.

Language Analysis

Categorial Grammar, Dependency Grammar, Government and Binding Theory / Minimalist Framework, Grammar Models and Formalisms, Head-Driven Phrase Structure Grammar, Lexical-Functional Grammar, Lexicons for Constraint-Based Grammars, Morphological Analysis, Natural Language Parsing, Optimality Theory in Syntax, Parsing Techniques, Part-of-Speech Tagging, Probabilistic Context-free Grammars, Shallow Parsing, Systemic Functional Linguistics, Tokenization and Segmentation, Tree-Adjoining Grammar.

Language Resources

Grammars, Lexicons, Linguistically Annotated Corpora, Multilingual Corpora, Spoken Language Corpora, Standards, Thesauri WordNets, Written Language Corpora.

Language Understanding

Computational Pragmatics, Computational Psycholinguistics, Computational Semantics, Word Sense Disambiguation.

Mathematical Methods

Conditional Random Fields, Connectionist Techniques, DSP Techniques, Emerging Computing Paradigms, Finite State Technology, HMM Methods, Inductive Logic Programming, Latent Semantic Analysis, Maximum Entropy Methods, Optimization and Search in Speech and Language Processing, Statistical Modeling and Classification, Support Vector Machines.

Multilinguality

Automatic Language Identification, Example-Based Translation and Translation Memories, Human Aided Machine Translation, Machine Translation, Machine-Aided Human Translation, Multilingual Generation, Multilingual Speech Processing, Statistical Machine Translation.

Multimodality

Modality Integration: Facial Movement and Speech, Representations of Space and Time.

Natural Language Generation

Deep Generation, Shallow Generation, Syntactic Generation, Written Language Generation.

Spoken Language Input

Acoustic Modelling in Speech Recognition, Emotion Recognition, Language Modelling, Prosody Information Processing, Signal Analysis and Representation, Speaker Recognition, Speech Recognition, Spoken Language Understanding.

Spoken Language Output Technologies

Spoken Language Generation, Text-to-Speech Synthesis.

Written Language Input

Document Image Analysis, OCR: Handwriting, OCR: Print.