Fixes for Release 0.5

docs/api/lambeq.ansatz.rst

@@ -1,3 +1,5 @@
+.. _api-ansatz:
+
 lambeq.ansatz
 =============
 

docs/api/lambeq.rewrite.rst

@@ -1,3 +1,5 @@
+.. _api-rewrite:
+
 lambeq.rewrite
 ==============
 

docs/api/lambeq.text2diagram.rst

@@ -1,3 +1,5 @@
+.. _api-text2diagram:
+
 lambeq.text2diagram
 ===================
 

docs/cite.rst

@@ -9,16 +9,30 @@ If you use ``lambeq`` for your research, please cite the accompanying paper :cit
 
    @article{kartsaklis2021lambeq,
       title={lambeq: {A}n {E}fficient {H}igh-{L}evel {P}ython {L}ibrary for {Q}uantum {NLP}},
-      author={Dimitri Kartsaklis 
-              and Ian Fan 
-              and Richie Yeung 
-              and Anna Pearson 
-              and Robin Lorenz 
-              and Alexis Toumi 
-              and Giovanni de Felice 
-              and Konstantinos Meichanetzidis 
-              and Stephen Clark 
+      author={Dimitri Kartsaklis
+              and Ian Fan
+              and Richie Yeung
+              and Anna Pearson
+              and Robin Lorenz
+              and Alexis Toumi
+              and Giovanni de Felice
+              and Konstantinos Meichanetzidis
+              and Stephen Clark
               and Bob Coecke},
       year={2021},
       journal={arXiv preprint arXiv:2110.04236},
    }
+
+The :py:term:`DisCoCirc` extension introduced in Release :ref:`rel-0.5.0` is described in detail in this paper :cite:p:`krawchuk_2025`:
+
+.. code-block:: bash
+
+   @article{krawchuk2025,
+      title={Efficient {G}eneration of {P}arameterised {Q}uantum {C}ircuits from {L}arge {T}exts,
+      author={Colin Krawchuk
+              and Nikhil Khatri
+              and Neil John Ortega
+              and Dimitri Kartsaklis
+      year={2025},
+      journal={arXiv preprint arXiv:2505.13208},
+   }

docs/glossary.rst

@@ -39,7 +39,7 @@ Glossary
         A model that produces semantic representations of sentences by composing together the semantic representations of the words within them. An example of a compositional model is :term:`DisCoCat`.
 
     coreference resolution
-        A task whose goal is to identify which linguistic expressions in a text refer to the same real-world entity. In ``lambeq``, coreference resolution is mainly used in the context of :term:`DisCoCirc` models, and utilises the :term:`spaCy` NLP toolkit.
+        A task whose goal is to identify which linguistic expressions in a text refer to the same real-world entity. In ``lambeq``, coreference resolution is mainly used in the context of :term:`DisCoCirc` models, and utilises the :term:`spaCy` NLP toolkit and the `Maverick <https://github.com/SapienzaNLP/maverick-coref>`_ package.
 
     cup
         A special morphism in a :term:`rigid category`, which, together with a :term:`cap` morphism, obey certain conditions called :term:`snake equations`. In diagrammatic form, a cup is depicted as a wire with upward concavity (:math:`\cup`). In the context of :term:`DisCoCat`, a cup usually represents a tensor contraction between two-word representations.
@@ -55,9 +55,9 @@ Glossary
 
     DisCoPy
         DIStributional COmpositional PYthon. A Python library for working with :term:`monoidal categories <monoidal category>` :cite:p:`de_felice_2021`. It includes abstractions for creating all standard :term:`quantum gates <quantum gate>` and building :term:`quantum circuits <quantum circuit>`. Additionally, it is equipped with many language-related features, such as support for :term:`pregroup grammars <pregroup grammar>` and :term:`functors <functor>` for implementing :term:`compositional models <compositional model>`.
-    
+
     frame
-        In ``lambeq``'s :term:`string diagrams <string diagram>`, a special type of box that can contain other boxes or frames. Frames are mainly used in the context of :term:`DisCoCirc` models, representing higher-level linguistic expressions. 
+        In ``lambeq``'s :term:`string diagrams <string diagram>`, a special type of box that can contain other boxes or frames. Frames are mainly used in the context of :term:`DisCoCirc` models, representing higher-level linguistic expressions.
 
     Frobenius algebra
         In the context of a :term:`symmetric monoidal category`, a Frobenius algebra provides morphisms :math:`\Delta: A \to A\otimes A` and :math:`\mu: A\otimes A \to A` for any object :math:`A`, satisfying certain conditions (the so-called Frobenius equations) and implementing the notion of a :term:`spider`. In ``lambeq`` and :term:`DisCoCat`, spiders can be used to implement :term:`rewrite rules <rewrite rule>` :cite:p:`kartsaklis_2016a,kartsaklis_2016b,sadrzadeh_2013,sadrzadeh_2014`.
@@ -89,6 +89,9 @@ Glossary
     noise
         Undesired artefacts that cause the measurement outcome of a :term:`quantum circuit` to deviate from the ideal distribution.
 
+    Oncilla
+        A new experimental end-to-end parser that simplifies the process of generating diagrams from text, minimizing or even eliminating exposure of the user to CCG representations and functionality. This parser utilises the :term:`pregroup tree` representation of diagrams.
+
     parser
         A statistical tool that converts a sentence into a hierarchical representation that reflects the syntactic relationships between the words (a :term:`syntax tree`) based on a specific grammar formalism.
 

docs/guide/lambeq-basic.rst

@@ -25,6 +25,6 @@ Related research
 ----------------
 
 - The idea of using category theory to represent language was first introduced in :cite:p:`coecke_2010`, which detailed a framework that later became known as :term:`DisCoCat`. DisCoCat is supported in ``lambeq`` along with many other compositional schemes.
-- An extension of DisCoCat that allows the compositional encoding of full paragraphs or documents into quantum circuits is described in :cite:p:`coecke_2021a`. ``lambeq`` provides experimental support for :term:`DisCoCirc` models through the :py:mod:`lambeq.experimental.discocirc` package.
+- An extension of DisCoCat that allows the compositional encoding of full paragraphs or documents into quantum circuits is described in :cite:p:`coecke_2021a`. ``lambeq`` provides experimental support for :term:`DisCoCirc` models through the :py:mod:`lambeq.experimental.discocirc` package :cite:p:`krawchuk_2025`.
 - An early, yet-unreleased version of ``lambeq`` was used in :cite:p:`lorenz_2023`, a paper that described one of the first small-scale NLP experiments on a real quantum computer. The 40-pages paper provides a detailed introduction to the theoretical framework and the principles on which ``lambeq`` is now based, and it's an excellent starting point for the interested readers.
 

docs/guide/parsing.rst

@@ -5,12 +5,16 @@ Syntactic parsing
 
 ``lambeq``'s :ref:`string diagrams <sec-string-diagrams>` are based on a :ref:`pregroup grammar <sec-pregroup-grammars>` to keep track of the types and the interactions between the words in a sentence. When a detailed syntactic derivation is required (as in the case of :term:`DisCoCat`), a :term:`syntax tree` needs to be provided by a statistical :term:`parser`. However, since the :term:`pregroup grammar` formalism is not particularly well-known in the :term:`NLP <natural language processing (NLP)>` community, there is currently no wide-coverage pregroup :term:`parser` that can automatically provide the syntactic derivations. To address this problem, ``lambeq`` provides a passage from a derivation in the closest alternative grammar formalism, namely :term:`Combinatory Categorial Grammar (CCG)`, to a :term:`string diagram` which faithfully encodes the syntactic structure of the sentence in a pregroup-like form :cite:p:`yeung_2021`. Due to the availability of many robust :term:`CCG <Combinatory Categorial Grammar (CCG)>` :term:`parsing tools <parser>`, this allows the conversion of large corpora with sentences of arbitrary length and syntactic structure into :term:`pregroup <pregroup grammar>` and :term:`DisCoCat` form.
 
-Since Release :ref:`rel-0.2.0`, the standard ``lambeq`` installation includes a state-of-the-art CCG parser based on :cite:p:`clark_2021`, fully integrated into the toolkit. This parser is provided under the name :term:`Bobcat`. Additionally, ``lambeq`` implements a detailed interface in the :py:mod:`.text2diagram` package that allows connection to one of the many external CCG parsing tools that are currently available. For example, ``lambeq`` is also shipped with support for :term:`depccg` [#f1]_ :cite:p:`yoshikawa_2017`, a fast parser that comes with a convenient Python interface.
+The standard ``lambeq`` installation includes a state-of-the-art CCG parser based on :cite:p:`clark_2021`, fully integrated into the toolkit. This parser is provided under the name :term:`Bobcat`. Additionally, ``lambeq`` implements a detailed interface in the :py:mod:`.text2diagram` package that allows connection to one of the many external CCG parsing tools that are currently available. For example, ``lambeq`` is also shipped with support for :term:`depccg` [#f1]_ :cite:p:`yoshikawa_2017`, a fast parser that comes with a convenient Python interface.
 
 Additional external parsers can be made available to ``lambeq`` by extending the :py:class:`.CCGParser` class in order to create a wrapper subclass that encapsulates the necessary calls and translates the respective parser's output into :py:class:`.CCGTree` format.
 
 Finally, for users who prefer to keep the installation of the toolkit light, ``lambeq`` also includes a web-based parser class that sends parsing queries to an online API, so that local installation of a full CCG parser is not strictly necessary anymore -- although strongly recommended for most practical uses of the toolkit.
 
+Oncilla parser
+--------------
+Since Release :ref:`rel-0.5.0`, ``lambeq`` provides a new end-to-end parser class, :py:class:`~lambeq.text2diagram.OncillaParser`, that simplifies the process of generating diagrams from text, minimizing or even eliminating exposure of the user to CCG representations and functionality. This parser utilises the :term:`pregroup tree` representation of diagrams, offering accuracy and coverage similar to Bobcat in much faster speeds -- up to three times faster. :term:`Oncilla` parser is currently available as an experimental feature.
+
 Reading CCGBank
 ---------------
 

docs/installation.rst

@@ -19,6 +19,9 @@ To install ``lambeq`` with optional dependencies for experimental features::
 
    pip install lambeq[experimental]
 
+.. note::
+   For best results with the experimental features, use Python 3.11.
+
 DepCCG support
 --------------
 

docs/references.bib

@@ -404,3 +404,12 @@ @misc{tull_2024
       primaryClass={cs.AI},
       url={https://arxiv.org/abs/2406.17583},
 }
+
+@misc{krawchuk_2025,
+   title="{Efficient Generation of Parameterized Quantum Circuits from Large Texts}",
+   author={Colin Krawchuk and Nikhil Khatri and Neil John Ortega and Dimitri Kartsaklis},
+   year={2025},
+   eprint={2505.13208},
+   primaryClass={quant-ph},
+   url={https://arxiv.org/abs/2505.13208},
+}