Release notes¶
0.4.3¶
Changed:
Documentation has now been moved to a [dedicated repository](https://github.com/CQCL/lambeq-docs) and got a new URL (https://cqcl.github.io/lambeq-docs/).
Changed the landing page and some visuals in the online documentation.
Updated README to reflect the new docs structure.
Fixed:
Fixed minor issues on some documentation pages and the README file.
0.4.2¶
Added:
Added timing information to training logs and model checkpoints.
Changed:
Changed theme of online documentation.
Updated required version of
pytket
to 1.31.0.
Fixed:
Fixed bug in generation of single-legged quantum spiders.
Fixed bug when evaluating quantum circuits using Tket.
Removed:
Removed support for Python 3.9.
0.4.1¶
Added:
Support for Python 3.12.
A new
Sim4Ansatz
based on the Sim et al. paper [SJAG19].A new argument in
Trainer.fit()
for specifying anearly_stopping_criterion
other than validation loss.A new argument
collapse_noun_phrases
in methods ofCCGParser
andCCGTree
classes (for example, seeCCGParser.sentence2diagram()
) that allows the user to maintain noun phrases in the derivation or collapse them into nouns as desired.Raised meaningful exception when users try to convert to/from DisCoPy 1.1.0
Changed:
An internal refactoring of module
backend.drawing
in view of planned new features.Updated random number generation in
TketModel
by using the recommendednumpy.random.default_rnd()
method.
Fixed:
Handling of possible empty
Bra
s andKet
s during conversion from DisCoPy.Fixed a bug in JIT compilation of mixed circuit evaluations.
0.4.0¶
Added:
A new integrated backend that replaces DisCoPy, which until now was providing the low-level functionality of
lambeq
. The new backend offers better performance, increased stability, faster training speeds, and a simplified high-level interface to the user. The new backend consists of the following sub-modules:lambeq.backend.grammar
: Contains the building blocks for creating string diagrams.lambeq.backend.tensor
: Contains the necessary classes to create tensor diagrams.lambeq.backend.quantum
: Adds quantum-specific functionality to the backend and provides a circuit simulator based on the TensorNetwork library.lambeq.backend.pennylane
: Interface with PennyLane.lambeq.backend.tk
: Inteface with Tket.lambeq.backend.numerical_backend
: Common interface for numerical backends (such as Numpy, Jax, PyTorch, TensorFlow)lambeq.backend.drawing
: Contains drawing functionality for diagrams and circuits.
BobcatParser
: Added a special case for adjectival conjunction in tree translation.TreeReader
: Diagrams now are created straight from theCCGTree
.CCGRule
apply method: Addedapply()
method to classCCGRule
.
Changed:
Diagram-level rewriters: Rewrite functions
remove_cups()
andremove_swaps()
are now refactored as diagram-level rewriters,RemoveCupsRewriter
andRemoveSwapsRewriter
correspondingly.Extra whitespace is now ignored in the
Tokeniser
.
Fixed:
UnknownWordsRewriteRule
: Fixed rewriting of non-word boxes.
Removed:
0.3.3¶
This update features contributions from participants in unitaryHACK 2023:
Two new optimisers:
The Nelder-Mead optimiser. (credit: Gopal Dahale)
The Rotosolve optimiser. (credit: Ahmed Darwish)
A new rewrite rule for handling unknown words. (credit: WingCode)
Many thanks to all who participated.
This update also contains the following changes:
Added:
DiagramRewriter
is a new class that rewrites diagrams by looking at the diagram as a whole rather than by using rewrite rules on individual boxes. This includes an exampleUnifyCodomainRewriter
which adds an extra box to the end of diagrams to change the output to a specified type. (credit: A.C.E07)Added an early stopping mechanism to
Trainer
using the parameterearly_stopping_interval
.
Fixed:
In
PennyLaneModel
, SymPy symbols are now substituted during the forward pass so that gradients are back-propagated to the original parameters.A pickling error that prevented CCG trees produced by
BobcatParser
from being unpickled has been fixed.
0.3.2¶
Added:
Support for DisCoPy >= 1.1.4 (credit: toumix).
replaced
discopy.rigid
withdiscopy.grammar.pregroup
everywhere.replaced
discopy.biclosed
withdiscopy.grammar.categorial
everywhere.Use
Diagram.decode
to account for the change in contructor signatureDiagram(inside, dom, cod)
.updated attribute names that were previously hidden, e.g.
._data
becomes.data
.replaced diagrammatic conjugate with transpose.
swapped left and right currying.
dropped support for legacy DisCoPy.
Added
CCGType
class for utilisation in thebiclosed_type
attribute ofCCGTree
, allowing conversion to and from a discopy categorial object usingdiscopy()
andfrom_discopy()
methods.CCGTree
: added reference to the original tree from parsing by introducing ametadata
field.
Changed:
Internalised DisCoPy quantum ansätze in lambeq.
IQPAnsatz
now ends with a layer of Hadamard gates in the multi-qubit case and the post-selection basis is set to be the computational basis (Pauli Z).
Fixed:
Fixed a bottleneck during the initialisation of the
PennyLaneModel
caused by the inefficient substitution of Sympy symbols in the circuits.Escape special characters in box labels for symbol creation.
Documentation: fixed broken links to DisCoPy documentation.
Documentation: enabled sphinxcontrib.jquery extension for Read the Docs theme.
Fixed disentangling
RealAnsatz
in extend-lambeq tutorial notebook.Fixed model loading in PennyLane notebooks.
Fixed typo in
SPSAOptimizer
(credit: Gopal-Dahale)
Removed:
Removed support for Python 3.8.
0.3.1¶
Changed:
Added example and tutorial notebooks to tests.
Dependencies: pinned the maximum version of Jax and Jaxlib to 0.4.6 to avoid a JIT-compilation error when using the
NumpyModel
.
Fixed:
Documentation: fixed broken DisCoPy links.
Fixed PyTorch datatype errors in example and tutorial notebooks.
Updated custom ansätze in tutorial notebook to match new structure of
CircuitAnsatz
andTensorAnsatz
.
0.3.0¶
Added:
Support for hybrid quantum-classical models using the
PennyLaneModel
. PennyLane is a powerful QML library that allows the development of hybrid ML models by hooking numerically determined gradients of parametrised quantum circuits (PQCs) to the autograd modules of ML libraries like PyTorch or TensorFlow.Add lambeq-native loss functions
LossFunction
to be used in conjunction with theQuantumTrainer
. Currently, we support theCrossEntropyLoss
,BinaryCrossEntropyLoss
, and theMSELoss
loss functions.Python 3.11 support.
An extensive NLP-101 tutorial, covering basic definitions, text preprocessing, tokenisation, handling of unknown words, machine learning best practices, text classification, and other concepts.
Changed:
Improve tensor initialisation in the
PytorchModel
. This enables the training of larger models as all parameters are initialised such that the expected L2 norm of all output vectors is approximately 1. We use a symmetric uniform distribution where the range depends on the output dimension (flow) of each box.Improve the fail-safety of the
BobcatParser
model download method by adding hash checks and atomic transactions.Use type union expression
|
instead ofUnion
in type hints.Use
raise from
syntax for better exception handling.Update the requirements for the documentation.
Fixed:
Fixed bug in
SPSAOptimizer
triggered by the usage of masked arrays.Fixed test for
NumpyModel
that was failing due to a change in the behaviour of Jax.Fixed brittle quote-wrapped strings in error messages.
Fixed 400 response code during Bobcat model download.
Fixed bug where
CircuitAnsatz
would add empty discards and postselections to the circuit.
Removed:
Removed install script due to deprecation.
0.2.8¶
Changed:
Improved the performance of
NumpyModel
when using Jax JIT-compilation.Dependencies: pinned the required version of DisCoPy to 0.5.X.
Fixed:
Fixed incorrectly scaled validation loss in progress bar during model training.
Fixed symbol type mismatch in the quantum models when a circuit was previously converted to tket.
0.2.7¶
Added:
Added support for Japanese to
DepCCGParser
(credit: KentaroAOKI).Overhauled the
CircuitAnsatz
interface, and added three new ansätze.Added helper methods to
CCGTree
to get the children of a tree.Added a new
TreeReader.tree2diagram()
method toTreeReader
, extracted fromTreeReader.sentence2diagram()
.Added a new
TreeReaderMode
namedTreeReaderMode.HEIGHT
.Added new methods to
Checkpoint
for creating, saving and loading checkpoints for training.Documentation: added a section for how to select the right model and trainer for training.
Documentation: added links to glossary terms throughout the documentation.
Documentation: added UML class diagrams for the sub-packages in lambeq.
Changed:
Dependencies: bumped the minimum versions of
discopy
andtorch
.IQPAnsatz
now post-selects in the Hadamard basis.PytorchModel
now initialises usingxavier_uniform
.CCGTree.to_json()
can now be applied toNone
, returningNone
.Several slow imports have been deferred, making lambeq much faster to import for the first time.
In
CCGRule.infer_rule()
, direction checks have been made explicit.UnarySwap
is now specified to be aunaryBoxConstructor
.BobcatParser
has been refactored for easier use with external evaluation tools.Documentation: headings have been organised in the tutorials into subsections.
Fixed:
Fixed how
CCGRule.infer_rule()
assigns apunc + X
instance: if the result isX\X
the assigned rule isCCGRule.CONJUNCTION
, otherwise the rule isCCGRule.REMOVE_PUNCTUATION_LEFT
(similarly for punctuation on the right).
Removed:
Removed unnecessary override of
Model.from_diagrams()
inNumpyModel
.Removed unnecessary
kwargs
parameters from several constructors.Removed unused
special_cases
parameter and_ob
method fromCircuitAnsatz
.
0.2.6¶
Added a strict pregroups mode to the CLI. With this mode enabled, all swaps are removed from the output string diagrams by changing the ordering of the atomic types, converting them into a valid pregroup form as given in [Lam99].
Adjusted the behaviour of output normalisation in quantum models. Now,
NumpyModel
always returns probabilities instead of amplitudes.Removed the prediction from the output of the
SPSAOptimizer
, which now returns just the loss.
0.2.5¶
Added a “swapping” unary rule box to handle unary rules that change the direction of composition, improving the coverage of the
BobcatParser
.Added a
--version
flag to the CLI.Added a
make_checkpoint()
method to all training models.Changed the
WebParser
so that the online service to use is specified by name rather than by URL.Changed the
BobcatParser
to only allow one tree per category in a cell, doubling parsing speed without affecting the structure of the parse trees (in most cases).Fixed the parameter names in
CCGRule
, wheredom
andcod
had inadvertently been swapped.Made the linting of the codebase stricter, enforced by the GitHub action. The flake8 configuration can be viewed in the
setup.cfg
file.
0.2.4¶
Fix a bug that caused the
BobcatParser
and theWebParser
to trigger an SSL certificate error using Windows.Fix false positives in assigning conjunction rule using the
CCGBankParser
. The rule, + X[conj] -> X[conj]
is a case of removing left punctuation, but was being assigned conjunction erroneously.Add support for using
jax
as backend oftensornetwork
when settinguse_jit=True
in theNumpyModel
. The interface is not affected by this change, but performance of the model is significantly improved.
0.2.3¶
Fix a bug that raised a
dtype
error when using theTketModel
on Windows.Fix a bug that caused the normalisation of scalar outputs of circuits without open wires using a
QuantumModel
.Change the behaviour of
spiders_reader
such that the spiders decompose logarithmically. This change also affects other rewrite rules that use spiders, such as coordination and relative pronouns.Rename
AtomicType.PREPOSITION
toAtomicType.PREPOSITIONAL_PHRASE
.CCGRule
: Addsymbol()
method that returns the ASCII symbol of a given CCG rule.CCGTree
: Extendderiv()
method with CCG output. It is now capable of returning standard CCG diagrams.Command-line interface: Add CCG mode. When enabled, the output will be a string representation of the CCG diagram corresponding to the
CCGTree
object produced by the parser, instead of a DisCoPy diagram or circuit.Documentation: Add a troubleshooting page.
0.2.2¶
Add support for Python 3.10.
Unify class hierarchies for parsers and readers:
CCGParser
is now a subclass ofReader
and placed in the common packagetext2diagram
. The old packagesreader
andccg2discocat
are no longer available. Compatibility problems with previous versions should be minimal, since from Release 0.2.0 and onwards alllambeq
classes can be imported from the global namespace.Add
CurryRewriteRule
, which uses map-state duality in order to remove adjoint types from the boxes of a diagram. When used in conjunction withnormal_form()
, this removes cups from the diagram, eliminating post-selection.The Bobcat parser now updates automatically when new versions are made available online.
Update grammar file of Bobcat parser to avoid problems with conflicting unary rules.
Allow customising available root categories for the parser when using the command-line interface.
0.2.1¶
A new
Checkpoint
class that implements pickling and file operations from theTrainer
andModel
.Improvements to the
training
module, allowing multiple diagrams to be accepted as input to theSPSAOptimizer
.Updated documentation, including sub-package structures and class diagrams.
0.2.0¶
A new state-of-the-art CCG parser based on [Cla21], fully integrated with
lambeq
, which replaces depccg as the default parser of the toolkit. The new Bobcat parser has better performance, simplifies installation, and provides compatibility with Windows (which was not supported due to a depccg conflict). depccg is still supported as an alternative external dependency.A
training
package, providing a selection of trainers, models, and optimizers that greatly simplify supervised training for most oflambeq
’s use cases, classical and quantum. The new package adds several new features tolambeq
, such as the ability to save to and restore models from checkpoints.Furthermore, the
training
package uses DisCoPy’s tensor network capability to contract tensor diagrams efficiently. In particular, DisCoPy 0.4.1’s new unitary and density matrix simulators result in substantially faster training speeds compared to the previous version.A command-line interface, which provides most of
lambeq
’s functionality from the command line. For example,lambeq
can now be used as a standard command-line pregroup parser.A web parser class that can send parsing queries to an online API, so that local installation of a parser is not strictly necessary anymore. The web parser is particularly helpful for testing purposes, interactive usage or when a local parser is unavailable, but should not be used for serious experiments.
A new
pregroups
package that provides methods for easy creation of pregroup diagrams, removal of cups, and printing of diagrams in text form (i.e. in a terminal).A new
TreeReader
class that exploits the biclosed structure of CCG grammatical derivations.Three new rewrite rules for relative pronouns [SCC13, SCC14] and coordination [Kar16].
Tokenisation features have been added in all parsers and readers.
Additional generator methods and minor improvements for the
CCGBankParser
class.Improved and more detailed package structure.
Most classes and functions can now be imported from
lambeq
directly, instead of having to import from the sub-packages.The
circuit
andtensor
modules have been combined into anlambeq.ansatz
package. (However, as mentioned above, the classes and functions they define can now be imported directly fromlambeq
and should continue to do so in future releases.)Improved documentation and additional tutorials.
0.1.2¶
Add URLs to the setup file.
Fix logo link in README.
Fix missing version when building docs in GitHub action.
Fix typo in the
description
keyword of the setup file.
0.1.1¶
Update install script to use PyPI package.
Add badges and documentation link to the README file.
Add
lambeq
logo and documentation link to the GitHub repository.Allow documentation to get the package version automatically.
Add keywords and classifiers to the setup file.
Fix: Add
lambeq.circuit
module to top-levellambeq
package.Fix references to license file.
0.1.0¶
The initial release of lambeq
, containing a lot of core material. Main features:
Converting sentences to string diagrams.
CCG parsing, including reading from CCGBank.
Support for the
depccg
parser.DisCoCat, bag-of-words, and word-sequence compositional models.
Support for adding new compositional schemes.
Rewriting of diagrams.
Ansätze for circuits and tensors, including various forms of matrix product states.
Support for JAX and PyTorch integration.
Example notebooks and documentation.