نحن نصف خسارة اهتمام مدفوع المستوى الذي يحسن التعميم التركيبي في المحللين الدلاليين.يعتمد نهجنا على الخسائر القائمة التي تشجع على خرائط الاهتمام في نماذج التسلسل العصبي إلى التسلسل لتقليد إخراج خوارزميات محاذاة الكلمة الكلاسيكية.حيث استخدم العمل السابق محاذاة على مستوى الكلمات، ونحن نركز على يمتد؛اقتراض الأفكار من الترجمة الآلية القائمة على العبارة، نحن محاذاة السكتة الدلالية في تبييل الدلالي إلى امتداد جمل المدخلات، وتشجيع آليات الاهتمام العصبي لتقليد هذه المحاذاة.تعمل هذه الطريقة على تحسين أداء المحولات، RNNs، والكفران الهيكلية على ثلاثة معايير للتعميم التركيبي.
We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers. Our approach builds on existing losses that encourage attention maps in neural sequence-to-sequence models to imitate the output of classical word alignment algorithms. Where past work has used word-level alignments, we focus on spans; borrowing ideas from phrase-based machine translation, we align subtrees in semantic parses to spans of input sentences, and encourage neural attention mechanisms to mimic these alignments. This method improves the performance of transformers, RNNs, and structured decoders on three benchmarks of compositional generalization.
References used
https://aclanthology.org/
Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen components. Motivated by trad
AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of t
In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing. Instead of predicting a probability, our model predicts a real-valued score at each step and does not suffer from the label bias problem. Exp
In practical applications of semantic parsing, we often want to rapidly change the behavior of the parser, such as enabling it to handle queries in a new domain, or changing its predictions on certain targeted queries. While we can introduce new trai
Searching for legal documents is a specialized Information Retrieval task that is relevant for expert users (lawyers and their assistants) and for non-expert users. By searching previous court decisions (cases), a user can better prepare the legal re