Is it simpler? An Evaluation of an Aligned Corpus of Standard-Simple Sentences
Parallel monolingual resources are imperative for data-driven sentence simplification research. We present the work of aligning, at the sentence level, a corpus of all Swedish public authorities and municipalities web texts in standard and simple Swedish. We compare the performance of three alignment algorithms used for similar work in English (Average Alignment, Maximum Alignment, and Hungarian Alignment), and the best-performing algorithm is used to create a resource of 15,433 unique sentence pairs. We evaluate the resulting corpus using a set of features that has proven to predict text complexity of Swedish texts. The results show that the sentences of the simple sub-corpus are indeed less complex than the sentences of the standard part of the corpus, according to many of the text complexity measures.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceSimilar Papers 제목 키워드 기반
BLEU is Not Suitable for the Evaluation of Text Simplification
BLEU is widely considered to be an informative metric for text-to-text generation, including Text Simplification (TS). TS includes both lexical and structural aspects. In this paper we show that BLEU is not suitable for …
SentenceText GenerationText SimplificationA New Aligned Simple German Corpus
"Leichte Sprache", the German counterpart to Simple English, is a regulated language aiming to facilitate complex written language that would otherwise stay inaccessible to different groups of people. We present a new se…
SentenceForeigner-directed speech is simpler than native-directed: Evidence from social media
I test two hypotheses that play an important role in modern sociolinguistics and language evolution studies: first, that non-native production is simpler than native; second, that production addressed to non-native speak…
Causal Abstractions of Neural Networks
Structural analysis methods (e.g., probing and feature attribution) are increasingly important tools for neural network analysis. We propose a new structural analysis method grounded in a formal theory of causal abstract…
Natural Language InferenceAdversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives
Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target metrics, while neglecting rigorous standar…
Adversarial Robustness