في حين أن نموذج التراجع (Coecke et al.، 2010) أثبت أداة قيمة لدراسة الجوانب التركيبية للغة على مستوى الدلالات، فإن اعتمادها القوي على قواعد النحوية التي تطرح قيودا مهمة: أولا، فإنه يمنع التجريبات الكبيرة النطاق بسببعدم وجود محلل pregroup؛وثانيا، فإنه يحد من تعبير النموذج إلى قواعد النحوية الخالية من السياق.في هذه الورقة نحل هذه المشكلات عن طريق إعادة صياغة التراجع كمرور من قواعد النحو التصنيف التنفيذية (CCG) لفئة من دلالات.نبدأ بإظهار أنه يمكن التعبير عن القوس النمسي الصلب القياسي ك فئة ثنائية، حيث تظهر جميع القواعد ككروية من الهوية؛ثم ننتقل إلى نموذج قواعد تحفيز التقليب من خلال استغلال التماثل من الفئة المغلقة المصدق ترميز معنى كلمة.نحن نقدم دليلا على المفهوم لطريقتنا، وتحويل أليس في بلاد العجائب "في شكل ديسكريكا، وهي تجمع أننا نوفر للمجتمع.
While the DisCoCat model (Coecke et al., 2010) has been proved a valuable tool for studying compositional aspects of language at the level of semantics, its strong dependency on pregroup grammars poses important restrictions: first, it prevents large-scale experimentation due to the absence of a pregroup parser; and second, it limits the expressibility of the model to context-free grammars. In this paper we solve these problems by reformulating DisCoCat as a passage from Combinatory Categorial Grammar (CCG) to a category of semantics. We start by showing that standard categorial grammars can be expressed as a biclosed category, where all rules emerge as currying/uncurrying the identity; we then proceed to model permutation-inducing rules by exploiting the symmetry of the compact closed category encoding the word meaning. We provide a proof of concept for our method, converting Alice in Wonderland'' into DisCoCat form, a corpus that we make available to the community.
References used
https://aclanthology.org/
Many recent works have demonstrated that unsupervised sentence representations of neural networks encode syntactic information by observing that neural language models are able to predict the agreement between a verb and its subject. We take a critic
Word representations empowered with additional linguistic information have been widely studied and proved to outperform traditional embeddings. Current methods mainly focus on learning embeddings for words while embeddings of linguistic information (
This study seeks to clarify how Bernard Shaw in his play,
Pygmalion, modifies and modernizes Charles Perrault‘s Cinderella.
In this play, Shaw presents his heroine not only as a romantic
heroine, but also as an emerging feminist unwilling to settl
Pimentel et al. (2020) recently analysed probing from an information-theoretic perspective. They argue that probing should be seen as approximating a mutual information. This led to the rather unintuitive conclusion that representations encode exactl
Driving simulators are valuable research tool for conducting driving studies instead of conducting these studies on the real roads. However, to be accepted as a representative of the real world, a driving simulator must provide an acceptable degree o