SENTA: Sentence Simplification System for Slovene (2024.lrec-main)

Copied to clipboard

Challenge: Sentence simplification involves converting complex sentences into more accessible forms while preserving their meaning and context.
Approach: They propose a system for sentence simplification in Slovene that uses a neural classifier to identify sentences that need simplification and a large Slovenen language model to refine sentences into a simpler form.
Outcome: The proposed system achieves an excellent SARI score of 41 for a large Slovene language model based on T5 architecture . it is integrated into a freely accessible, user-friendly user interface, offering a valuable service to less-fluent Slovenen users.

Similar Papers

Sentence Simplification with Memory-Augmented Neural Networks (N18-2)

Copied to clipboard

Challenge: Sentence simplification aims to simplify the content and structure of complex sentences . prior work has focused on monolingual machine translation (MT) and tree-based MT (TBMT).
Approach: They adapt an architecture with augmented memory capacities called Neural Semantic Encoders for sentence simplification.
Outcome: The proposed architecture improves on different datasets and improves human judgments.
Controllable Sentence Simplification (2020.lrec-1)

Copied to clipboard

Challenge: Text simplification is often considered an all-purpose generic task where the same simplifications are suitable for all but multiple audiences can benefit from simplified text in different ways.
Approach: They propose a controllable simplification model that provides explicit control on simplification systems based on Sequence-to-Sequence models.
Outcome: The proposed model outperforms standard models on simplification benchmarks.
COSTRA 1.0: A Dataset of Complex Sentence Transformations (2020.lrec-1)

Copied to clipboard

Challenge: Several studies have shown word vector representations capture syntactic and semantic regularities.
Approach: They present a dataset of sentence-level embeddings in Czech and plan to use it in other languages.
Outcome: The proposed dataset is limited to Czech but will be used in other languages.
A Detailed Evaluation of Neural Sequence-to-Sequence Models for In-domain and Cross-domain Text Simplification (L18-1)

Copied to clipboard

Challenge: Xu et al., 2016) show that a simple neural architecture can be efficiently used for in-domain and cross-domain text simplification.
Approach: They evaluate neural sequence-to-sequence models for text simplification on Wikipedia and Newsela datasets.
Outcome: The proposed model can generalize across corpora and overcome challenges when tested on Wikipedia and Newsela datasets.
Neural CRF Model for Sentence Alignment in Text Simplification (2020.acl-main)

Copied to clipboard

Challenge: Text simplification systems are based on the quality and quantity of complex-simple sentence pairs extracted by aligning sentences between parallel articles.
Approach: They propose a neural CRF alignment model which leverages the sequential nature of sentences in parallel documents and utilizes a sentence pair model to capture semantic similarity.
Outcome: The proposed model outperforms previous work on monolingual sentence alignment task by more than 5 points in F1.
Integrating Transformer and Paraphrase Rules for Sentence Simplification (D18-1)

Copied to clipboard

Challenge: Current models for sentence simplification adopted ideas from machine translation studies and implicitly learned simplification mapping rules from normal-simple sentence pairs.
Approach: They propose a novel model based on a multi-layer and multi-head attention architecture and two innovative approaches to integrate a paraphrase knowledge base for simplification.
Outcome: The proposed model outperforms state-of-the-art models for sentence simplification . it seeks to select more accurate simplification rules, the authors show .
Text Simplification from Professionally Produced Corpora (L18-1)

Copied to clipboard

Challenge: Existing approaches to Text Simplification rely on the Wikipedia-Simple Wikipedia parallel corpus, which is used for many tasks.
Approach: They propose to use the Newsela corpus to extract 550, 644 complex-simple sentence pairs from the corpus and introduce a lexical simplifier that uses the corpu to generate candidate simplifications.
Outcome: The proposed model outperforms state-of-the-art approaches and generates candidate simplifications from the newsela corpus.
Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to train automatic text simplification systems for languages other than English are limited by the lack of parallel data.
Approach: They propose to use German Easy Language as a corpus of automatic text simplification systems to fine-tune language models to the style characteristics of the language.
Outcome: The proposed language models adapt to the style characteristics of Easy Language and output more accessible texts.
Adapting Sentence-level Automatic Metrics for Document-level Simplification Evaluation (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies on text simplification have focused on sentence simplification, but these metrics often underperform on longer texts.
Approach: They propose to adapt existing sentence-level metrics for paragraph- or document-level simplification by incorporating a new approach to the evaluation of text simplification metrics.
Outcome: The proposed approach outperforms existing sentence-level metrics in terms of correlation with human judgment and the sensitivity and robustness of various metrics to different types of errors produced by existing systems.
Controllable Sentence Simplification in Swedish Using Control Prefixes and Mined Paraphrases (2024.lrec-main)

Copied to clipboard

Challenge: Automated Text Simplification (ATS) systems aim to facilitate readability and comprehension by reducing linguistic complexity.
Approach: They propose to use a dataset of Swedish paraphrases to train ATS models utilizing prefix-tuning with control prefixes to provide more control over the simplification.
Outcome: The proposed model improves on the baseline model and compares with previous models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations