اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدPCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols
99
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Probabilistic context-free grammars (PCFGs) with neural parameterization have been shown to be effective in unsupervised phrase-structure grammar induction. However, due to the cubic computational complexity of PCFG representation and parsing, previous approaches cannot scale up to a relatively large number of (nonterminal and preterminal) symbols. In this work, we present a new parameterization form of PCFGs based on tensor decomposition, which has at most quadratic computational complexity in the symbol number and therefore allows us to use a much larger number of symbols. We further use neural parameterization for the new form to improve unsupervised parsing performance. We evaluate our model across ten languages and empirically demonstrate the effectiveness of using more symbols. Our code: https://github.com/sustcsonglin/TN-PCFG
قيم البحث
اقرأ أيضاً
Two formalisms, both based on context-free grammars, have recently been proposed as a basis for a non-uniform random generation of combinatorial objects. The former, introduced by Denise et al, associates weights with letters, while the latter, recen
tly explored by Weinberg et al in the context of random generation, associates weights to transitions. In this short note, we use a simple modification of the Greibach Normal Form transformation algorithm, due to Blum and Koch, to show the equivalent expressivities, in term of their induced distributions, of these two formalisms.
Translation models based on hierarchical phrase-based statistical machine translation (HSMT) have shown better performances than the non-hierarchical phrase-based counterparts for some language pairs. The standard approach to HSMT learns and apply a
synchronous context-free grammar with a single non-terminal. The hypothesis behind the grammar refinement algorithm presented in this work is that this single non-terminal is overloaded, and insufficiently discriminative, and therefore, an adequate split of it into more specialised symbols could lead to improved models. This paper presents a method to learn synchronous context-free grammars with a huge number of initial non-terminals, which are then grouped via a clustering algorithm. Our experiments show that the resulting smaller set of non-terminals correctly capture the contextual information that makes it possible to statistically significantly improve the BLEU score of the standard HSMT approach.
Context-Free Grammars (CFGs) and Parsing Expression Grammars (PEGs) have several similarities and a few differences in both their syntax and semantics, but they are usually presented through formalisms that hinder a proper comparison. In this paper w
e present a new formalism for CFGs that highlights the similarities and differences between them. The new formalism borrows from PEGs the use of parsing expressions and the recognition-based semantics. We show how one way of removing non-determinism from this formalism yields a formalism with the semantics of PEGs. We also prove, based on these new formalisms, how LL(1) grammars define the same language whether interpreted as CFGs or as PEGs, and also show how strong-LL(k), right-linear, and LL-regular grammars have simple language-preserving translations from CFGs to PEGs.
Neural predictive models have achieved remarkable performance improvements in various natural language processing tasks. However, most neural predictive models suffer from the lack of explainability of predictions, limiting their practical utility. T
his paper proposes a neural predictive approach to make a prediction and generate its corresponding explanation simultaneously. It leverages the knowledge entailed in explanations as an additional distillation signal for more efficient learning. We conduct a preliminary study on Chinese medical multiple-choice question answering, English natural language inference, and commonsense question answering tasks. The experimental results show that the proposed approach can generate reasonable explanations for its predictions even with a small-scale training corpus. The proposed method also achieves improved prediction accuracy on three datasets, which indicates that making predictions can benefit from generating the explanation in the decision process.
This paper proposes the use of ``pattern-based context-free grammars as a basis for building machine translation (MT) systems, which are now being adopted as personal tools by a broad range of users in the cyberspace society. We discuss major require
ments for such tools, including easy customization for diverse domains, the efficiency of the translation algorithm, and scalability (incremental improvement in translation quality through user interaction), and describe how our approach meets these requirements.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
