Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userUniversal Recurrent Neural Network Grammar
قواعد الشبكة العصبية المتكررة
280
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الأساليب الحديثة لتحليل الدوائر الانتخابية هي مناهج إشراف أحادية اللغات التي تتطلب كمية كبيرة من البيانات المسمى التي سيتم تدريبها على، مما يحد من فائدتها إلى حفنة فقط من لغات الموارد العالية فقط. لمعالجة هذه المسألة في هذه المسألة لغات الموارد المنخفضة، نقترح نواعد الشبكة العصبية المتكررة عالمية (UNIRNNG) وهي متغير متعدد اللغات من نموذج قواعد الشبكة العصبية المتكررة (RNNG) المتكررة (RNNG) لتحليل الدوائر الانتخابية. ينطوي UNIRNNG على تعلم التحويل عبر اللغات لمهمة تحليل الدوائر الانتخابية. يتم إلهام بنية UNIRNNG من حيث المبدأ ونظرية المعلمة التي اقترحها نام تشومسكي. تستخدم UNIRNNG المعرفة النموذجية اللغوية المتاحة كقيم ميزة داخل قاعدة بيانات WALS، للتعميم على لغات متعددة. بمجرد التدريب على Corpus PolyGlot PolyGlot المتنوع بما فيه الكفاية، يمكن تطبيقه على أي لغة طبيعية مما يجعلها محلل الدائرة الانتخابية اللازمة للغات. تكشف التجارب أن نهج خطوط خط الأساس المتوفرة في UNIRNNG المتفوقة بالنسبة لنا أكبر من أجل معظم اللغات المستهدفة التي تم اختبارها.
Modern approaches to Constituency Parsing are mono-lingual supervised approaches which require large amount of labelled data to be trained on, thus limiting their utility to only a handful of high-resource languages. To address this issue of data-sparsity for low-resource languages we propose Universal Recurrent Neural Network Grammars (UniRNNG) which is a multi-lingual variant of the popular Recurrent Neural Network Grammars (RNNG) model for constituency parsing. UniRNNG involves Cross-lingual Transfer Learning for Constituency Parsing task. The architecture of UniRNNG is inspired by Principle and Parameter theory proposed by Noam Chomsky. UniRNNG utilises the linguistic typology knowledge available as feature-values within WALS database, to generalize over multiple languages. Once trained on sufficiently diverse polyglot corpus UniRNNG can be applied to any natural language thus making it Language-agnostic constituency parser. Experiments reveal that our proposed UniRNNG outperform state-of-the-art baseline approaches for most of the target languages, for which these are tested.
References used
https://aclanthology.org/
rate research
Read More
In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the previous literature has been agnostic about a parsing strategy of the hierarchical models. In this paper, we investi
gated whether hierarchical structures make LMs more human-like, and if so, which parsing strategy is most cognitively plausible. In order to address this question, we evaluated three LMs against human reading times in Japanese with head-final left-branching structures: Long Short-Term Memory (LSTM) as a sequential model and Recurrent Neural Network Grammars (RNNGs) with top-down and left-corner parsing strategies as hierarchical models. Our computational modeling demonstrated that left-corner RNNGs outperformed top-down RNNGs and LSTM, suggesting that hierarchical and left-corner architectures are more cognitively plausible than top-down or sequential architectures. In addition, the relationships between the cognitive plausibility and (i) perplexity, (ii) parsing, and (iii) beam size will also be discussed.
Machine translation usually relies on parallel corpora to provide parallel signals for training. The advent of unsupervised machine translation has brought machine translation away from this reliance, though performance still lags behind traditional
supervised machine translation. In unsupervised machine translation, the model seeks symmetric language similarities as a source of weak parallel signal to achieve translation. Chomsky's Universal Grammar theory postulates that grammar is an innate form of knowledge to humans and is governed by universal principles and constraints. Therefore, in this paper, we seek to leverage such shared grammar clues to provide more explicit language parallel signals to enhance the training of unsupervised machine translation models. Through experiments on multiple typical language pairs, we demonstrate the effectiveness of our proposed approaches.
Source code processing heavily relies on the methods widely used in natural language processing (NLP), but involves specifics that need to be taken into account to achieve higher quality. An example of this specificity is that the semantics of a vari
able is defined not only by its name but also by the contexts in which the variable occurs. In this work, we develop dynamic embeddings, a recurrent mechanism that adjusts the learned semantics of the variable when it obtains more information about the variable's role in the program. We show that using the proposed dynamic embeddings significantly improves the performance of the recurrent neural network, in code completion and bug fixing tasks.
It is now established that modern neural language models can be successfully trained on multiple languages simultaneously without changes to the underlying architecture, providing an easy way to adapt a variety of NLP models to low-resource languages
. But what kind of knowledge is really shared among languages within these models? Does multilingual training mostly lead to an alignment of the lexical representation spaces or does it also enable the sharing of purely grammatical knowledge? In this paper we dissect different forms of cross-lingual transfer and look for its most determining factors, using a variety of models and probing tasks. We find that exposing our LMs to a related language does not always increase grammatical knowledge in the target language, and that optimal conditions for lexical-semantic transfer may not be optimal for syntactic transfer.
Mathematical reasoning aims to infer satisfiable solutions based on the given mathematics questions. Previous natural language processing researches have proven the effectiveness of sequence-to-sequence (Seq2Seq) or related variants on mathematics so
lving. However, few works have been able to explore structural or syntactic information hidden in expressions (e.g., precedence and associativity). This dissertation set out to investigate the usefulness of such untapped information for neural architectures. Firstly, mathematical questions are represented in the format of graphs within syntax analysis. The structured nature of graphs allows them to represent relations of variables or operators while preserving the semantics of the expressions. Having transformed to the new representations, we proposed a graph-to-sequence neural network GraphMR, which can effectively learn the hierarchical information of graphs inputs to solve mathematics and speculate answers. A complete experimental scenario with four classes of mathematical tasks and three Seq2Seq baselines is built to conduct a comprehensive analysis, and results show that GraphMR outperforms others in hidden information learning and mathematics resolving.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
