We report the findings of the 2024 Multilingual Lexical Simplification Pipeline shared task. We released a new dataset comprising 5,927 instances of lexical complexity prediction and lexical simplification on common contexts across 10 languages, split into trial (300) and test (5,627). 10 teams participated across 2 tracks and 10 languages with 233 runs evaluated across all systems. Five teams participated in all languages for the lexical complexity prediction task and 4 teams participated in all languages for the lexical simplification task. Teams employed a range of strategies, making use of open and closed source large language models for lexical simplification, as well as feature-based approaches for lexical complexity prediction. The highest scoring team on the combined multilingual data was able to obtain a Pearson’s correlation of 0.6241 and an ACC@1@Top1 of 0.3772, both demonstrating that there is still room for improvement on two difficult sub-tasks of the lexical simplification pipeline.
We present preliminary findings on the MultiLS dataset, developed in support of the 2024 Multilingual Lexical Simplification Pipeline (MLSP) Shared Task. This dataset currently comprises of 300 instances of lexical complexity prediction and lexical simplification across 10 languages. In this paper, we (1) describe the annotation protocol in support of the contribution of future datasets and (2) present summary statistics on the existing data that we have gathered. Multilingual lexical simplification can be used to support low-ability readers to engage with otherwise difficult texts in their native, often low-resourced, languages.
Question and answer generation (QAG) consists of generating a set of question-answer pairs given a context (e.g. a paragraph). This task has a variety of applications, such as data augmentation for question answering (QA) models, information retrieval and education. In this paper, we establish baselines with three different QAG methodologies that leverage sequence-to-sequence language model (LM) fine-tuning. Experiments show that an end-to-end QAG model, which is computationally light at both training and inference times, is generally robust and outperforms other more convoluted approaches. However, there are differences depending on the underlying generative LM. Finally, our analysis shows that QA models fine-tuned solely on generated question-answer pairs can be competitive when compared to supervised QA models trained on human-labeled data.
We investigate how text genre influences the performance of models for controlled text simplification. Regarding datasets from Wikipedia and PubMed as two different genres, we compare the performance of genre-specific models trained by transfer learning and prompt-only GPT-like large language models. Our experiments showed that: (1) the performance loss of genre-specific models on general tasks can be limited to 2%, (2) transfer learning can improve performance on genre-specific datasets up to 10% in SARI score from the base model without transfer learning, (3) simplifications generated by the smaller but more customized models show similar performance in simplicity and a better meaning reservation capability to the larger generic models in both automatic and human evaluations.
We present BLESS, a comprehensive performance benchmark of the most recent state-of-the-art Large Language Models (LLMs) on the task of text simplification (TS). We examine how well off-the-shelf LLMs can solve this challenging task, assessing a total of 44 models, differing in size, architecture, pre-training methods, and accessibility, on three test sets from different domains (Wikipedia, news, and medical) under a few-shot setting. Our analysis considers a suite of automatic metrics, as well as a large-scale quantitative investigation into the types of common edit operations performed by the different models. Furthermore, we perform a manual qualitative analysis on a subset of model outputs to better gauge the quality of the generated simplifications. Our evaluation indicates that the best LLMs, despite not being trained on TS perform comparably with state-of-the-art TS baselines. Additionally, we find that certain LLMs demonstrate a greater range and diversity of edit operations. Our performance benchmark will be available as a resource for the development of future TS methods and evaluation metrics.
Generating questions along with associated answers from a text has applications in several domains, such as creating reading comprehension tests for students, or improving document search by providing auxiliary questions and answers based on the query. Training models for question and answer generation (QAG) is not straightforward due to the expected structured output (i.e. a list of question and answer pairs), as it requires more than generating a single sentence. This results in a small number of publicly accessible QAG models. In this paper, we introduce AutoQG, an online service for multilingual QAG along with lmqg, an all-in-one python package for model fine-tuning, generation, and evaluation. We also release QAG models in eight languages fine-tuned on a few variants of pre-trained encoder-decoder language models, which can be used online via AutoQG or locally via lmqg. With these resources, practitioners of any level can benefit from a toolkit that includes a web interface for end users, and easy-to-use code for developers who require custom models or fine-grained controls for generation.
Automatic Readability Assessment aims at assigning a complexity level to a given text, which could help improve the accessibility to information in specific domains, such as the administrative one. In this paper, we investigate the behavior of a Neural Pairwise Ranking Model (NPRM) for sentence-level readability assessment of Italian administrative texts. To deal with data scarcity, we experiment with cross-lingual, cross- and in-domain approaches, and test our models on Admin-It, a new parallel corpus in the Italian administrative language, containing sentences simplified using three different rewriting strategies. We show that NPRMs are effective in zero-shot scenarios (~0.78 ranking accuracy), especially with ranking pairs containing simplifications produced by overall rewriting at the sentence-level, and that the best results are obtained by adding in-domain data (achieving perfect performance for such sentence pairs). Finally, we investigate where NPRMs failed, showing that the characteristics of the training data, rather than its size, have a bigger effect on a model’s performance.
Specialist high-quality information is typically first available in English, and it is written in a language that may be difficult to understand by most readers. While Machine Translation technologies contribute to mitigate the first issue, the translated content will most likely still contain complex language. In order to investigate and address both problems simultaneously, we introduce Simple TICO-19, a new language resource containing manual simplifications of the English and Spanish portions of the TICO-19 corpus for Machine Translation of COVID-19 literature. We provide an in-depth description of the annotation process, which entailed designing an annotation manual and employing four annotators (two native English speakers and two native Spanish speakers) who simplified over 6,000 sentences from the English and Spanish portions of the TICO-19 corpus. We report several statistics on the new dataset, focusing on analysing the improvements in readability from the original texts to their simplified versions. In addition, we propose baseline methodologies for automatically generating the simplifications, translations and joint translation and simplifications contained in our dataset.
Powerful generative models have led to recent progress in question generation (QG). However, it is difficult to measure advances in QG research since there are no standardized resources that allow a uniform comparison among approaches. In this paper, we introduce QG-Bench, a multilingual and multidomain benchmark for QG that unifies existing question answering datasets by converting them to a standard QG setting. It includes general-purpose datasets such as SQuAD for English, datasets from ten domains and two styles, as well as datasets in eight different languages. Using QG-Bench as a reference, we perform an extensive analysis of the capabilities of language models for the task. First, we propose robust QG baselines based on fine-tuning generative language models. Then, we complement automatic evaluation based on standard metrics with an extensive manual evaluation, which in turn sheds light on the difficulty of evaluating QG models. Finally, we analyse both the domain adaptability of these models as well as the effectiveness of multilingual models in languages other than English.QG-Bench is released along with the fine-tuned models presented in the paper (https://github.com/asahi417/lm-question-generation), which are also available as a demo (https://autoqg.net/).
We propose an approach for comparing curricula of study programs in higher education. Pre-trained word embeddings are fine-tuned in a study program classification task, where each curriculum is represented by the names and content of its courses. By combining metric learning with a novel course-guided attention mechanism, our method obtains more accurate curriculum representations than strong baselines. Experiments on a new dataset with curricula of computing programs demonstrate the intuitive power of our approach via attention weights, topic modeling, and embeddings visualizations. We also present a use case comparing computing curricula from USA and Latin America to showcase the capabilities of our improved embeddings representations.
Video-based datasets for Continuous Sign Language are scarce due to the challenging task of recording videos from native signers and the reduced number of people who can annotate sign language. COVID-19 has evidenced the key role of sign language interpreters in delivering nationwide health messages to deaf communities. In this paper, we present a framework for creating a multi-modal sign language interpretation dataset based on videos and we use it to create the first dataset for Peruvian Sign Language (LSP) interpretation annotated by hearing volunteers who have intermediate knowledge of PSL guided by the video audio. We rely on hearing people to produce a first version of the annotations, which should be reviewed by native signers in the future. Our contributions: i) we design a framework to annotate a sign Language dataset; ii) we release the first annotated LSP multi-modal interpretation dataset (AEC); iii) we evaluate the annotation done by hearing people by training a sign language recognition model. Our model reaches up to 80.3% of accuracy among a minimum of five classes (signs) AEC dataset, and 52.4% in a second dataset. Nevertheless, analysis by subject in the second dataset show variations worth to discuss.
We release a new benchmark for Automated Readability Assessment (ARA) of texts in Spanish. We combined existing corpora with suitable texts collected from the Web, thus creating the largest available dataset for ARA of Spanish texts. All data was pre-processed and categorised to allow experimenting with ARA models that make predictions at two (simple and complex) or three (basic, intermediate, and advanced) readability levels, and at two text granularities (paragraphs and sentences). An analysis based on readability indices shows that our proposed datasets groupings are suitable for their designated readability level. We use our benchmark to train neural ARA models based on BERT in zero-shot, few-shot, and cross-lingual settings. Results show that either a monolingual or multilingual pre-trained model can achieve good results when fine-tuned in language-specific data. In addition, all mod- els decrease their performance when predicting three classes instead of two, showing opportunities for the development of better ARA models for Spanish with existing resources.
This project investigates the capabilities of Machine Translation models for generating translations at varying levels of readability, focusing on texts related to COVID-19. Whilst it is possible to automatically translate this information, the resulting text may contain specialised terminology, or may be written in a style that is difficult for lay readers to understand. So far, we have collected a new dataset with manual simplifications for English and Spanish sentences in the TICO-19 dataset, as well as implemented baseline pipelines combining Machine Translation and Text Simplification models.
Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that are trained end-to-end to perform all these operations simultaneously. However, such systems limit themselves to mostly deleting words and cannot easily adapt to the requirements of different target audiences. In this paper, we propose a novel hybrid approach that leverages linguistically-motivated rules for splitting and deletion, and couples them with a neural paraphrasing model to produce varied rewriting styles. We introduce a new data augmentation method to improve the paraphrasing capability of our model. Through automatic and manual evaluations, we show that our proposed model establishes a new state-of-the-art for the task, paraphrasing more often than the existing systems, and can control the degree of each simplification operation applied to the input texts.
In modern computer-aided translation workflows, Machine Translation (MT) systems are used to produce a draft that is then checked and edited where needed by human translators. In this scenario, a Quality Estimation (QE) tool can be used to score MT outputs, and a threshold on the QE scores can be applied to decide whether an MT output can be used as-is or requires human post-edition. While this could reduce cost and turnaround times, it could harm translation quality, as QE models are not 100% accurate. In the framework of the APE-QUEST project (Automated Post-Editing and Quality Estimation), we set up a case-study on the trade-off between speed, cost and quality, investigating the benefits of QE models in a real-world scenario, where we rely on end-user acceptability as quality metric. Using data in the public administration domain for English-Dutch and English-French, we experimented with two use cases: assimilation and dissemination. Results shed some light on how QE scores can be explored to establish thresholds that suit each use case and target language, and demonstrate the potential benefits of adding QE to a translation workflow.
This paper describes our submission to SemEval-2021 Task 1: predicting the complexity score for single words. Our model leverages standard morphosyntactic and frequency-based features that proved helpful for Complex Word Identification (a related task), and combines them with predictions made by Transformer-based pre-trained models that were fine-tuned on the Shared Task data. Our submission system stacks all previous models with a LightGBM at the top. One novelty of our approach is the use of multi-task learning for fine-tuning a pre-trained model for both Lexical Complexity Prediction and Word Sense Disambiguation. Our analysis shows that all independent models achieve a good performance in the task, but that stacking them obtains a Pearson correlation of 0.7704, merely 0.018 points behind the winning submission.
In order to simplify sentences, several rewriting operations can be performed, such as replacing complex words per simpler synonyms, deleting unnecessary information, and splitting long sentences. Despite this multi-operation nature, evaluation of automatic simplification systems relies on metrics that moderately correlate with human judgments on the simplicity achieved by executing specific operations (e.g., simplicity gain based on lexical replacements). In this article, we investigate how well existing metrics can assess sentence-level simplifications where multiple operations may have been applied and which, therefore, require more general simplicity judgments. For that, we first collect a new and more reliable data set for evaluating the correlation of metrics and human judgments of overall simplicity. Second, we conduct the first meta-evaluation of automatic metrics in Text Simplification, using our new data set (and other existing data) to analyze the variation of the correlation between metrics’ scores and human judgments across three dimensions: the perceived simplicity level, the system type, and the set of references used for computation. We show that these three aspects affect the correlations and, in particular, highlight the limitations of commonly used operation-specific metrics. Finally, based on our findings, we propose a set of recommendations for automatic evaluation of multi-operation simplifications, suggesting which metrics to compute and how to interpret their scores.
We introduce deepQuest-py, a framework for training and evaluation of large and light-weight models for Quality Estimation (QE). deepQuest-py provides access to (1) state-of-the-art models based on pre-trained Transformers for sentence-level and word-level QE; (2) light-weight and efficient sentence-level models implemented via knowledge distillation; and (3) a web interface for testing models and visualising their predictions. deepQuest-py is available at https://github.com/sheffieldnlp/deepQuest-py under a CC BY-NC-SA licence.
Sentence Simplification (SS) aims to modify a sentence in order to make it easier to read and understand. In order to do so, several rewriting transformations can be performed such as replacement, reordering, and splitting. Executing these transformations while keeping sentences grammatical, preserving their main idea, and generating simpler output, is a challenging and still far from solved problem. In this article, we survey research on SS, focusing on approaches that attempt to learn how to simplify using corpora of aligned original-simplified sentence pairs in English, which is the dominant paradigm nowadays. We also include a benchmark of different approaches on common data sets so as to compare them and highlight their strengths and limitations. We expect that this survey will serve as a starting point for researchers interested in the task and help spark new ideas for future developments.
In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components, and/or delete information deemed unnecessary. Despite these varied range of possible text alterations, current models for automatic sentence simplification are evaluated using datasets that are focused on a single transformation, such as lexical paraphrasing or splitting. This makes it impossible to understand the ability of simplification models in more realistic settings. To alleviate this limitation, this paper introduces ASSET, a new dataset for assessing sentence simplification in English. ASSET is a crowdsourced multi-reference corpus where each simplification was produced by executing several rewriting transformations. Through quantitative and qualitative experiments, we show that simplifications in ASSET are better at capturing characteristics of simplicity when compared to other standard evaluation datasets for the task. Furthermore, we motivate the need for developing better methods for automatic evaluation using ASSET, since we show that current popular metrics may not be suitable when multiple simplification transformations are performed.
Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience. The latest CWI Shared Task released data for two settings: monolingual (i.e. train and test in the same language) and cross-lingual (i.e. test in a language not seen during training). The best monolingual models relied on language-dependent features, which do not generalise in the cross-lingual setting, while the best cross-lingual model used neural networks with multi-task learning. In this paper, we present monolingual and cross-lingual CWI models that perform as well as (or better than) most models submitted to the latest CWI Shared Task. We show that carefully selected features and simple learning models can achieve state-of-the-art performance, and result in strong baselines for future development in this area. Finally, we discuss how inconsistencies in the annotation of the data can explain some of the results obtained.
We introduce EASSE, a Python package aiming to facilitate and standardise automatic evaluation and comparison of Sentence Simplification (SS) systems. EASSE provides a single access point to a broad range of evaluation resources: standard automatic metrics for assessing SS outputs (e.g. SARI), word-level accuracy scores for certain simplification transformations, reference-independent quality estimation features (e.g. compression ratio), and standard test data for SS evaluation (e.g. TurkCorpus). Finally, EASSE generates easy-to-visualise reports on the various metrics and features above and on how a particular SS output fares against reference simplifications. Through experiments, we show that these functionalities allow for better comparison and understanding of the performance of SS systems.
Current approaches to Text Simplification focus on simplifying sentences individually. However, certain simplification transformations span beyond single sentences (e.g. joining and re-ordering sentences). In this paper, we motivate the need for modelling the simplification task at the document level, and assess the performance of sequence-to-sequence neural models in this setup. We analyse parallel original-simplified documents created by professional editors and show that there are frequent rewriting transformations that are not restricted to sentence boundaries. We also propose strategies to automatically evaluate the performance of a simplification model on these cross-sentence transformations. Our experiments show the inability of standard sequence-to-sequence neural models to learn these transformations, and suggest directions towards document-level simplification.
Current research in text simplification has been hampered by two central problems: (i) the small amount of high-quality parallel simplification data available, and (ii) the lack of explicit annotations of simplification operations, such as deletions or substitutions, on existing data. While the recently introduced Newsela corpus has alleviated the first problem, simplifications still need to be learned directly from parallel text using black-box, end-to-end approaches rather than from explicit annotations. These complex-simple parallel sentence pairs often differ to such a high degree that generalization becomes difficult. End-to-end models also make it hard to interpret what is actually learned from data. We propose a method that decomposes the task of TS into its sub-problems. We devise a way to automatically identify operations in a parallel corpus and introduce a sequence-labeling approach based on these annotations. Finally, we provide insights on the types of transformations that different approaches can model.
We introduce MASSAlign: a Python library for the alignment and annotation of monolingual comparable documents. MASSAlign offers easy-to-use access to state of the art algorithms for paragraph and sentence-level alignment, as well as novel algorithms for word-level annotation of transformation operations between aligned sentences. In addition, MASSAlign provides a visualization module to display and analyze the alignments and annotations performed.
Text Complexity Analysis is an useful task in Education. For example, it can help teachers select appropriate texts for their students according to their educational level. This task requires the analysis of several text features that people do mostly manually (e.g. syntactic complexity, words variety, etc.). In this paper, we present a tool useful for Complexity Analysis, called Coh-Metrix-Esp. This is the Spanish version of Coh-Metrix and is able to calculate 45 readability indices. We analyse how these indices behave in a corpus of “simple” and “complex” documents, and also use them as features in a complexity binary classifier for texts in Spanish. After some experiments with machine learning algorithms, we got 0.9 F-measure for a corpus that contains tales for kids and adults and 0.82 F-measure for a corpus with texts written for students of Spanish as a foreign language.