A Constrained Sequence-to-Sequence Neural Model for Sentence Simplification
نویسندگان
چکیده
Sentence simplification reduces semantic complexity to benefit people with language impairments. Previous simplification studies on the sentence level and word level have achieved promising results but also meet great challenges. For sentencelevel studies, sentences after simplification are fluent but sometimes are not really simplified. For word-level studies, words are simplified but also have potential grammar errors due to different usages of words before and after simplification. In this paper, we propose a two-step simplification framework by combining both the word-level and the sentence-level simplifications, making use of their corresponding advantages. Based on the twostep framework, we implement a novel constrained neural generation model to simplify sentences given simplified words. The final results on Wikipedia and Simple Wikipedia aligned datasets indicate that our method yields better performance than various baselines.
منابع مشابه
Constrained Seismic Sequence Stratigraphy of Asmari - Kajhdumi interval with well-log Data
Sequence stratigraphy is a key step in interpretation of the seismic reflection data. It was originally developed by seismic specialists, and then the usage of high-resolution well logs and core data was taken into consideration in its implementation. The current paper aims in performing sequence stratigraphy using three-dimensional seismic data, well logs (gamma ray, sonic, porosity, density, ...
متن کاملA Cuckoo search algorithm (CSA) for Precedence Constrained Sequencing Problem (PCSP)
Precedence constrained sequencing problem (PCSP) is related to locate the optimal sequence with the shortest traveling time among all feasible sequences. In PCSP, precedence relations determine sequence of traveling between any two nodes. Various methods and algorithms for effectively solving the PCSP have been suggested. In this paper we propose a cuckoo search algorithm (CSA) for effectively ...
متن کاملORE extraction and blending optimization model in poly- metallic open PIT mines by chance constrained one-sided goal programming
Determination a sequence of extracting ore is one of the most important problems in mine annual production scheduling. Production scheduling affects mining performance especially in a poly-metallic open pit mine with considering the imposed operational and physical constraints mandated by high levels of reliability in relation to the obtained actual results. One of the important operational con...
متن کاملAn Experimental Study of LSTM Encoder-Decoder Model for Text Simplification
Text simplification (TS) aims to reduce the lexical and structural complexity of a text, while still retaining the semantic meaning. Current automatic TS techniques are limited to either lexical-level applications or manually defining a large amount of rules. Since deep neural networks are powerful models that have achieved excellent performance over many difficult tasks, in this paper, we prop...
متن کاملWord Embedding Attention Network: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
Most recent approaches use the sequenceto-sequence model for paraphrase generation. The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words. Therefore, the generated sentences are often grammatically correct but semantically improper. In this work, we introduce a novel model based on the encoder-de...
متن کاملذخیره 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 ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1704.02312 شماره
صفحات -
تاریخ انتشار 2017