Struct CorefDocument 

pub struct CorefDocument {
    pub text: String,
    pub doc_id: Option<String>,
    pub chains: Vec<CorefChain>,
    pub includes_singletons: bool,
}

A document with coreference annotations.

Contains the source text and all coreference chains.

Fields

text: String

Document text.

doc_id: Option<String>

Document identifier.

chains: Vec<CorefChain>

Coreference chains (clusters).

includes_singletons: bool

Whether singletons are included.

Implementations

impl CorefDocument

pub fn new(text: impl Into<String>, chains: Vec<CorefChain>) -> CorefDocument

Create a new document with chains.

use anno_core::core::coref::{CorefDocument, CorefChain, Mention};

let chain = CorefChain::new(vec![
    Mention::new("John", 0, 4),
    Mention::new("He", 24, 26),
]);
let doc = CorefDocument::new("John went to the store. He bought milk.", vec![chain]);
assert_eq!(doc.mention_count(), 2);
assert_eq!(doc.chain_count(), 1);

pub fn with_id( text: impl Into<String>, doc_id: impl Into<String>, chains: Vec<CorefChain>, ) -> CorefDocument

Create document with ID.

pub fn mention_count(&self) -> usize

Total number of mentions across all chains.

pub fn chain_count(&self) -> usize

Number of chains (clusters).

pub fn non_singleton_count(&self) -> usize

Number of non-singleton chains.

pub fn all_mentions(&self) -> Vec<&Mention>

Get all mentions in document order.

pub fn find_chain(&self, start: usize, end: usize) -> Option<&CorefChain>

Find which chain contains a mention span.

pub fn mention_to_chain_index(&self) -> HashMap<(usize, usize), usize>

Build mention-to-chain index for fast lookup.

pub fn without_singletons(&self) -> CorefDocument

Filter to only non-singleton chains.

Trait Implementations

impl Clone for CorefDocument

fn clone(&self) -> CorefDocument

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CorefDocument

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for CorefDocument

fn deserialize<__D>( __deserializer: __D, ) -> Result<CorefDocument, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for CorefDocument

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.