Text Simplification as Tree Transduction

نویسندگان

  • Gustavo Paetzold
  • Lucia Specia
چکیده

Lexical and syntactic simplification aim to make texts more accessible to certain audiences. Syntactic simplification uses either hand-crafted linguistic rules for deep syntactic transformations, or machine learning techniques to model simpler transformations. Lexical simplification performs a lookup for synonyms followed by context and/or frequency-based models. In this paper we investigate modelling both syntactic and lexical simplification through the learning of general tree transduction rules. Experiments with the Simple English Wikipedia corpus show promising results but highlight the need for clever filtering strategies to remove noisy transformations. Resumo. A simplificação em nı́vel lexical e sintático objetiva tornar textos mais acessı́veis a certos públicos-alvo. Simplificação em nı́vel sintático usa regras confeccionadas manualmente para empregar transformações sintáticas, ou técnicas de aprendizado de máquina para modelar transformações mais simples. Simplificação em nı́vel lexical emprega busca por sinônimos para palavras complexas seguida por análise de contexto e/ou busca em modelos de frequência de palavras. Neste trabalho investiga-se a modelagem de ambas estratégias de simplificação em nı́vel sintático e lexical pelo aprendizado de regras através da transdução de árvores. Experimentos com dados da Simple English Wikipedia mostram resultados promissores, porém destacam a necessidade de estratégias inteligentes de filtragem para remover transformações ruidosas.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Text Simplification as Tree Labeling

We present a new, structured approach to text simplification using conditional random fields over top-down traversals of dependency graphs that jointly predicts possible compressions and paraphrases. Our model reaches readability scores comparable to word-based compression approaches across a range of metrics and human judgements while maintaining more of the important information.

متن کامل

Sentence Simplification as Tree Transduction

In this paper, we introduce a syntax-based sentence simplifier that models simplification using a probabilistic synchronous tree substitution grammar (STSG). To improve the STSG model specificity we utilize a multi-level backoff model with additional syntactic annotations that allow for better discrimination over previous STSG formulations. We compare our approach to T3 (Cohn and Lapata, 2009),...

متن کامل

Hybrid text simplification using synchronous dependency grammars with hand-written and automatically harvested rules

We present an approach to text simplification based on synchronous dependency grammars. The higher level of abstraction afforded by dependency representations allows for a linguistically sound treatment of complex constructs requiring reordering and morphological change, such as conversion of passive voice to active. We present a synchronous grammar formalism in which it is easy to write rules ...

متن کامل

The Effect of Reducing Lexical and Syntactic Complexity of Texts on Reading Comprehension

The present study investigated the effect of different types of text simplification (i.e., reducing the lexical and syntactic complexity of texts) on reading comprehension of English as a Foreign Language learners (EFL). Sixty female intermediate EFL learners from three intact classes in Tabarestan Language Institute in Tehran participated in the study. The intact classes were assigned to three...

متن کامل

Extreme Model Simplification for Forest Rendering

Models of large forest scenes are of a geometric complexity that surpasses even the capabilities of current high end graphics hardware. We propose an extreme simplification method which allows us to render such scenes in realtime. Our work is an extension of the image based-simplification method of Billboard Clouds. We automatically generate tree model representations of 15-50 textured polygons...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013