Wenhan Xiong, Jingyu Liu, Igor Molybog, Hejia Zhang, Prajjwal Bhargava, Rui Hou, Louis Martin, Rashi Rungta, Karthik Abinav Sankararaman, Barlas Oguz, Madian Khabsa, Han Fang, Yashar Mehdad, Sharan Narang, Kshitiz Malik, Angela Fan, Shruti Bhosale, Sergey Edunov, Mike Lewis, Sinong Wang, Hao Ma. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Mattia Atzeni, Mikhail Plekhanov, Frederic Dreyer, Nora Kassner, Simone Merello, Louis Martin, Nicola Cancedda. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Mikel Artetxe, Shruti Bhosale, Naman Goyal, Todor Mihaylov, Myle Ott, Sam Shleifer, Xi Victoria Lin, Jingfei Du, Srinivasan Iyer, Ramakanth Pasunuru, Giridharan Anantharaman, Xian Li, Shuohui Chen, Halil Akin, Mandeep Baines, Louis Martin, Xing Zhou, Punit Singh Koura, Brian O’Horo, Jeffrey Wang, Luke Zettlemoyer, Mona Diab, Zornitsa Kozareva, Veselin Stoyanov. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

Progress in sentence simplification has been hindered by a lack of labeled parallel simplification data, particularly in languages other than English. We introduce MUSS, a Multilingual Unsupervised Sentence Simplification system that does not require labeled simplification data. MUSS uses a novel approach to sentence simplification that trains strong models using sentence-level paraphrase data instead of proper simplification data. These models leverage unsupervised pretraining and controllable generation mechanisms to flexibly adjust attributes such as length and lexical complexity at inference time. We further present a method to mine such paraphrase data in any language from Common Crawl using semantic sentence embeddings, thus removing the need for labeled data. We evaluate our approach on English, French, and Spanish simplification benchmarks and closely match or outperform the previous best supervised results, despite not using any labeled simplification data. We push the state of the art further by incorporating labeled simplification data.

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.

Louis Martin, Benjamin Muller, Pedro Javier Ortiz Suárez, Yoann Dupont, Laurent Romary, Éric de la Clergerie, Djamé Seddah, Benoît Sagot. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.

Text simplification aims at making a text easier to read and understand by simplifying grammar and structure while keeping the underlying information identical. It is often considered an all-purpose generic task where the same simplification is suitable for all; however multiple audiences can benefit from simplified text in different ways. We adapt a discrete parametrization mechanism that provides explicit control on simplification systems based on Sequence-to-Sequence models. As a result, users can condition the simplifications returned by a model on attributes such as length, amount of paraphrasing, lexical complexity and syntactic complexity. We also show that carefully chosen values of these attributes allow out-of-the-box Sequence-to-Sequence models to outperform their standard counterparts on simplification benchmarks. Our model, which we call ACCESS (as shorthand for AudienCe-CEntric Sentence Simplification), establishes the state of the art at 41.87 SARI on the WikiLarge test set, a +1.42 improvement over the best previously reported score.

Summary We present a case study inmodel‐driven developmentof ane‐tourism portalthat we chose to develop throughgenerationfrom adomain modelencoded as anontology. We present (1) the requirements of e‐tourism portal, which dictated its high‐level design; (2) the principles behind our implementation strategy, including the use of adomain ontologyas a starting model within the context of a model‐driven transformational approach; (3) the ontology development process and the code generation strategy used; and (4) the lessons learned. In particular, we compare our experiences to those reported in the model‐driven engineering (MDE) literature along 3 dimensions, ie, (1) the impact of MDE on the development process, (2) the choice of the modeling approach, and (3) the impact of code generation on design and code quality and testing. Overall, our experiences corroboratedsomeof thetheoretical claimsandmanyof thepractical experienceswith MDE. Key findings include (1) model‐driven development makes maintenance, not development, more efficient; (2) it does require a higher skill level than traditional development; (3) clients and managers need to be educated into whatincrementalitymeans in agenerative approach; (4) UML is neither necessary nor sufficient to handle the required representational flexibility; (5) it is difficult to build models that are good for both human consumption and code generation; and (6) it is difficult to generate code that is, simultaneously, efficient, pretty, and easy to maintain. We conclude by summarizing the findings of the paper.

Enterprises build information systems to support their business processes. Some of those business processes are industry or enterprise-specific, but most are common to many industries and are used, modulo a few modifications, in different contexts. To the extent that we can, i) decompose complex business processes into composable generic sub-processes, ii) develop software components that implement such generic processes, and iii) map process specialization and composition operators to corresponding operators on software components, we will be able to develop information systems by modeling the business processes that they are meant to support, and using such models to guide the assembly of the corresponding software components. This is not a new idea, but earlier attempts suffered from the lack of tools, conceptual and otherwise, to perform this mapping. In this paper, we describe the principles underlying our approach and the status of the current implementation in the Eclipse environment.

The authors describe the application of the singular value decomposition Prony (SVDP) algorithm to the analysis of the time-variant structure of a microwave line-of-sight multipath channel. The algorithm deduces the multipath ray delays and associated amplitudes from measurements made in the frequency domain. The capability of this algorithm to resolve closely spaced rays is demonstrated by analyzing both computer simulated data and field measurements. The authors present experimental results of the time-variant structure of the transmittance H(jw,t) and include the evolution in time of the amplitude, group delay, and the constituting rays thus giving direct insight into the underlying multipath mechanism of line-of-sight microwave links.>