Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userModeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars
نمذجة تجهيز الجملة المعالجة مع قواعد الركن الناجم عن الشبكة العصبية المتكررة
205
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في اللغويات الحسابية، فقد تبين أن الهياكل الهرمية تجعل نماذج اللغة (LMS) أكثر تشبه الإنسان. ومع ذلك، فإن الأدب السابق كان غير ملائم حول استراتيجية تحليل النماذج الهرمية. في هذه الورقة، قامنا بالتحقيق في ما إذا كانت الهياكل الهرمية تجعل LMS أكثر تشبه الإنسان، وإذا كان الأمر كذلك، ما هي استراتيجية التحليل أكثر منطقية. من أجل معالجة هذا السؤال، قمنا بتقييم ثلاثة LMS ضد أوقات القراءة البشرية باللغة اليابانية مع هياكل المتفرعة اليسرى في الرأس: ذاكرة طويلة الأجل الطويلة (LSTM) كطراز متتابع ونواسيب الشبكة العصبية المتكررة (RNNGS) مع أعلى إلى أسفل واستراتيجيات تحليل الركن الأيسر كنماذج هرمية. أظهرت النمذجة الحاسوبية لدينا أن RNNGS الركن الأيسر تفوقت على RNNGS و LSTM من أعلى إلى أسفل، مما يشير إلى أن هياكل التسلسل الهرمي واليسرى من المعقول أكثر منطقية أكثر من الأعلى إلى أسفل أو هندسة متسلسلة. بالإضافة إلى ذلك، سيتم مناقشة العلاقات بين المعقول المعرفي و (1) حيرة، (2) تحليل، و (III) بحجم شعاع.
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 investigated 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.
References used
https://aclanthology.org/
rate research
Read More
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-spa
rsity 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.
The relationship between precipitation and surface runoff is one of
the fundamental components of the hydrological cycle of water in
nature and is one of the most complex and difficult to understand
because of the large number of parameters involv
ed in the
modeling of physical processes and the breadth of parmetry and
temporary change in basin specifications. Multiple rainfall models
Modeling the relationship between precipitation and runoff is very
important for engineering design and integrated water resources
management, as well as flood forecasting and risk prevention.
Explaining neural network models is important for increasing their trustworthiness in real-world applications. Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or detecting
interactions between adjacent features. However, for models with text pairs as inputs (e.g., paraphrase identification), existing methods are not sufficient to capture feature interactions between two texts and their simple extension of computing all word-pair interactions between two texts is computationally inefficient. In this work, we propose the Group Mask (GMASK) method to implicitly detect word correlations by grouping correlated words from the input text pair together and measure their contribution to the corresponding NLP tasks as a whole. The proposed method is evaluated with two different model architectures (decomposable attention model and BERT) across four datasets, including natural language inference and paraphrase identification tasks. Experiments show the effectiveness of GMASK in providing faithful explanations to these models.
The quality of fully automated text simplification systems is not good enough for use in real-world settings; instead, human simplifications are used. In this paper, we examine how to improve the cost and quality of human simplifications by leveragin
g crowdsourcing. We introduce a graph-based sentence fusion approach to augment human simplifications and a reranking approach to both select high quality simplifications and to allow for targeting simplifications with varying levels of simplicity. Using the Newsela dataset (Xu et al., 2015) we show consistent improvements over experts at varying simplification levels and find that the additional sentence fusion simplifications allow for simpler output than the human simplifications alone.
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.
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
