Linguistic Structure and Meaning

Morphemes, inflection, derivation, compounding, and why word structure matters for language models.

Finite-state and neural approaches to analyzing and generating morphologically rich language.

Context-free grammars, phrase structure, constituency trees, and the limits of symbolic grammars.

Head-dependent relations, dependency trees, projectivity, and cross-lingual annotation with Universal Dependencies.

Transition-based, graph-based, chart, and neural parsing methods with their decoding trade-offs.

Dynamic programming, constrained decoding, labeled attachment, span scores, and meaningful parser error analysis.

Polysemy, synonymy, lexical resources, contextual word senses, and word-sense disambiguation.

Compositional meaning, entailment, contradiction, presupposition, and robust NLI evaluation.

Predicates, arguments, thematic roles, frame semantics, and semantic role labeling.

Extracting relations, events, arguments, and timelines from documents rather than isolated sentences.

Linking mentions to entities, resolving ambiguity, and building provenance-aware knowledge graphs.

Logical forms, AMR, text-to-SQL, executable meaning representations, and constrained generation.

Mention detection, entity clusters, pronoun resolution, long-document coreference, and evaluation.

Discourse structure, rhetorical relations, coherence modeling, and long-form generation failures.

Speaker intent, common ground, deixis, implicature, and what literal next-token prediction misses.

Turn-taking, grounding, repair, dialogue acts, state tracking, and multi-party conversation.

Claims, evidence, stance, argument structure, persuasion, and responsible evaluation.