Related papers: EASSE: Easier Automatic Sentence Simplification Ev…

This study illustrates how incorporating feedback-oriented annotations into the scoring pipeline can enhance the accuracy of automated essay scoring (AES). This approach is demonstrated with the Persuasive Essays for Rating, Selecting, and…

Usability evaluation has received considerable attention from both the research and practice communities. While there are many evaluation tools available, the Software Usability Scale (SUS) is the most widely used. In this paper, we…

Speech recognition applications cover a range of different audio and text distributions, with different speaking styles, background noise, transcription punctuation and character casing. However, many speech recognition systems require…

Machine learning models are vulnerable to maliciously crafted Adversarial Examples (AEs). Training a machine learning model with AEs improves its robustness and stability against adversarial attacks. It is essential to develop models that…

Automatic short answer grading (ASAG) techniques are designed to automatically assess short answers to questions in natural language, having a length of a few words to a few sentences. Supervised ASAG techniques have been demonstrated to be…

Access to higher education is critical for minority populations and emergent bilingual students. However, the language used by higher education institutions to communicate with prospective students is often too complex; concretely, many…

Ensembles of separate neural networks (NNs) have shown superior accuracy and confidence calibration over single NN across tasks. To improve the hardware efficiency of ensembles of separate NNs, recent methods create ensembles within a…

Automatic Speech Recognition (ASR) systems are commonly evaluated using aggregate metrics such as Word Error Rate (WER), which do not capture the linguistic structure of errors. Fine-grained analysis, such as Part-of-Speech (PoS)-wise error…

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

Controllable text simplification is a crucial assistive technique for language learning and teaching. One of the primary factors hindering its advancement is the lack of a corpus annotated with sentence difficulty levels based on language…

As large language models (LLMs) achieve strong performance on traditional benchmarks, there is an urgent need for more challenging evaluation frameworks that probe deeper aspects of semantic understanding. We introduce SAGE (Semantic…

Automated text scoring (ATS) tasks, such as automated essay scoring and readability assessment, are important educational applications of natural language processing. Due to their interpretability of models and predictions, traditional…

Is it possible to build a general and automatic natural language generation (NLG) evaluation metric? Existing learned metrics either perform unsatisfactorily or are restricted to tasks where large human rating data is already available. We…

Semi-Supervised Variational Autoencoders (SSVAEs) are widely used models for data efficient learning. In this paper, we question the adequacy of the standard design of sequence SSVAEs for the task of text classification as we exhibit two…

Measuring Sentence Textual Similarity (STS) is a classic task that can be applied to many downstream NLP applications such as text generation and retrieval. In this paper, we focus on unsupervised STS that works on various domains but only…

High-quality Machine Translation (MT) evaluation relies heavily on human judgments. Comprehensive error classification methods, such as Multidimensional Quality Metrics (MQM), are expensive as they are time-consuming and can only be done by…

We present SacreROUGE, an open-source library for using and developing summarization evaluation metrics. SacreROUGE removes many obstacles that researchers face when using or developing metrics: (1) The library provides Python wrappers…

End-to-end (E2E) approaches to keyword search (KWS) are considerably simpler in terms of training and indexing complexity when compared to approaches which use the output of automatic speech recognition (ASR) systems. This simplification…

We present ESPnet-SE, which is designed for the quick development of speech enhancement and speech separation systems in a single framework, along with the optional downstream speech recognition module. ESPnet-SE is a new project which…

Sentence embedding refers to a set of effective and versatile techniques for converting raw text into numerical vector representations that can be used in a wide range of natural language processing (NLP) applications. The majority of these…