Struct JointModel 

pub struct JointModel { /* private fields */ }

Joint model for entity analysis.

Combines NER, coreference, and entity linking in a single factor graph following Durrett & Klein (2014).

Implementations

impl JointModel

pub fn new(config: JointConfig) -> Result<Self>

Create a new joint model.

pub fn with_knowledge(self, store: Arc<WikipediaKnowledgeStore>) -> Self

Add Wikipedia knowledge store for semantics lookups (Link+NER factors).

pub fn with_ner_provider(self, provider: Arc<dyn NerScoreProvider>) -> Self

Attach a custom NER score provider.

pub fn with_coref_provider(self, provider: Arc<dyn CorefScoreProvider>) -> Self

Attach a custom coreference score provider.

pub fn with_link_provider(self, provider: Arc<dyn LinkScoreProvider>) -> Self

Attach a custom link score provider.

pub fn analyze(&self, text: &str, entities: &[Entity]) -> Result<JointResult>

Analyze text jointly for entities, coreference, and links.

pub fn config(&self) -> &JointConfig

Get configuration.

pub fn extract_entities_from_mentions( &self, text: &str, mentions: &[JointMention], ) -> Result<Vec<Entity>>

Extract entities from raw text (requires external NER first).

This is a convenience method for pipelines that want to use JointModel as the final step after mention detection.

Trait Implementations

impl CoreferenceResolver for JointModel

Implement the CoreferenceResolver trait for JointModel.

fn resolve(&self, entities: &[Entity]) -> Vec<Entity>

Resolve coreference, assigning canonical IDs to entities.

fn name(&self) -> &'static str

Get resolver name.

fn resolve_to_chains(&self, entities: &[Entity]) -> Vec<CorefChain>

Resolve directly to chains.

impl Default for JointModel

fn default() -> Self

Returns the “default value” for a type.

impl Model for JointModel

Implement the Model trait for JointModel to allow it to be used as an NER backend.

Note: JointModel requires pre-extracted entities as input, so extract_entities uses an internal regex-based mention detector as a fallback.

fn extract_entities( &self, text: &str, _language: Option<&str>, ) -> Result<Vec<Entity>>

Extract entities from text.

fn supported_types(&self) -> Vec<EntityType>

Get supported entity types.

fn is_available(&self) -> bool

Check if model is available and ready.

fn name(&self) -> &'static str

Get the model name/identifier.

fn description(&self) -> &'static str

Get a description of the model.

fn capabilities(&self) -> ModelCapabilities

Get capability summary for this model.

fn version(&self) -> String

Get a version identifier for the model configuration/weights.