Skip to main content

MultilingualEmbeddingAligner

Struct MultilingualEmbeddingAligner 

Source
pub struct MultilingualEmbeddingAligner {
    pub config: MeaAlignerConfig,
    pub language_spaces: HashMap<LangId, LanguageSpace>,
    pub alignment_matrices: HashMap<(LangId, LangId), AlignmentMatrix>,
    pub alignment_history: VecDeque<AlignmentRecord>,
    /* private fields */
}
Expand description

Multilingual embedding aligner: maps embeddings from different language spaces to a shared cross-lingual embedding space.

Fields§

§config: MeaAlignerConfig§language_spaces: HashMap<LangId, LanguageSpace>§alignment_matrices: HashMap<(LangId, LangId), AlignmentMatrix>§alignment_history: VecDeque<AlignmentRecord>

Implementations§

Source§

impl MultilingualEmbeddingAligner

Source

pub fn new(config: MeaAlignerConfig) -> Self

Create a new aligner with the given configuration.

Source

pub fn with_defaults() -> Self

Create an aligner with default config.

Source

pub fn add_language(&mut self, id: LangId, name: String, dim: usize)

Register a new language space.

Source

pub fn remove_language(&mut self, id: LangId)

Remove a language space and all alignment matrices involving it.

Source

pub fn add_embedding( &mut self, lang_id: LangId, emb_id: u64, vector: Vec<f64>, ) -> Result<(), MeaError>

Add an embedding to a language space.

Source

pub fn remove_embedding( &mut self, lang_id: LangId, emb_id: u64, ) -> Result<(), MeaError>

Remove an embedding from a language space.

Source

pub fn compute_alignment( &mut self, src: LangId, tgt: LangId, anchors: &[(u64, u64)], ) -> Result<(), MeaError>

Compute and store an alignment matrix from srctgt.

anchors is a list of (src_emb_id, tgt_emb_id) pairs that are known to be translation equivalents.

Source

pub fn align_embedding( &self, src: LangId, tgt: LangId, vector: &[f64], ) -> Result<Vec<f64>, MeaError>

Apply the stored alignment matrix to transform vector from src space to tgt space.

Search in target_lang’s embedding space using a query from query_lang.

Returns top-k (emb_id, cosine_score) pairs, sorted by descending score.

Source

pub fn alignment_quality(&self, src: LangId, tgt: LangId) -> Option<f64>

Return the stored alignment quality for a (src, tgt) pair.

Source

pub fn compute_centroid( &mut self, lang_id: LangId, ) -> Result<Vec<f64>, MeaError>

Compute and cache the centroid of a language space.

Source

pub fn aligner_stats(&self) -> MeaAlignerStats

Aggregate statistics about the aligner state.

Source

pub fn embedding_count(&self, lang_id: LangId) -> Option<usize>

Number of embeddings in a language space.

Source

pub fn get_alignment_matrix( &self, src: LangId, tgt: LangId, ) -> Option<&AlignmentMatrix>

Retrieve a stored alignment matrix (immutable borrow).

Source

pub fn language_ids(&self) -> Vec<LangId>

List all registered language IDs.

Source

pub fn has_alignment(&self, src: LangId, tgt: LangId) -> bool

Check whether an alignment exists for the given pair.

Source

pub fn centroid(&self, lang_id: LangId) -> Option<&Vec<f64>>

Retrieve the centroid of a language space without recomputing.

Source

pub fn history(&self, limit: usize) -> Vec<&AlignmentRecord>

Recent alignment history entries (newest first).

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Allocation for T
where T: RefUnwindSafe + Send + Sync,

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<'a, T, E> AsTaggedExplicit<'a, E> for T
where T: 'a,

Source§

fn explicit(self, class: Class, tag: u32) -> TaggedParser<'a, Explicit, Self, E>

Source§

impl<'a, T, E> AsTaggedImplicit<'a, E> for T
where T: 'a,

Source§

fn implicit( self, class: Class, constructed: bool, tag: u32, ) -> TaggedParser<'a, Implicit, Self, E>

Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
where ST: ?Sized, DT: ?Sized,

Source§

impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
where ST: ?Sized, DT: ?Sized,

Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T> Instrument for T

Source§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more
Source§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> IntoEither for T

Source§

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

impl<T> Pointable for T

Source§

const ALIGN: usize

The alignment of pointer.
Source§

type Init = T

The type for initializers.
Source§

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more
Source§

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more
Source§

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more
Source§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more
Source§

impl<T> Read<Exclusive, BecauseExclusive> for T
where T: ?Sized,

Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
Source§

impl<SS, SP> SupersetOf<SS> for SP
where SS: SubsetOf<SP>,

Source§

fn to_subset(&self) -> Option<SS>

The inverse inclusion map: attempts to construct self from the equivalent element of its superset. Read more
Source§

fn is_in_subset(&self) -> bool

Checks if self is actually part of its subset T (and can be converted to it).
Source§

fn to_subset_unchecked(&self) -> SS

Use with care! Same as self.to_subset but without any property checks. Always succeeds.
Source§

fn from_subset(element: &SS) -> SP

The inclusion map: converts self to the equivalent element of its superset.
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
Source§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

Source§

fn vzip(self) -> V

Source§

impl<T> WithSubscriber for T

Source§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more