Related papers: Automatic Syntax Error Reporting and Recovery in P…

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

Bagging and boosting, two effective machine learning techniques, are applied to natural language parsing. Experiments using these techniques with a trainable statistical parser are described. The best resulting system provides roughly as…

Retrieval-Augmented Generation (RAG) has become essential for large-scale code generation, grounding predictions in external code corpora to improve actuality. However, a critical yet underexplored aspect of RAG pipelines is chunking -- the…

Retrieval-Augmented Generation (RAG) has become a standard approach for knowledge-intensive question answering, but existing systems remain brittle on multi-hop questions, where solving the task requires chaining multiple retrieval and…

Nowadays, data augmentation through synthetic data has been widely used in the field of Grammatical Error Correction (GEC) to alleviate the problem of data scarcity. However, these synthetic data are mainly used in the pre-training phase…

This study explores enhancing grammatical error correction (GEC) through artificial error generation (AEG) using language models (LMs). Specifically, we fine-tune Llama 2-based LMs for error generation and find that this approach yields…

Ensemble approaches are commonly used techniques to improving a system by combining multiple model predictions. Additionally these schemes allow the uncertainty, as well as the source of the uncertainty, to be derived for the prediction.…

Program synthesis and repair have emerged as an exciting area of research, driven by the potential for revolutionary advances in programmer productivity. Among most promising ideas emerging for synthesis are syntax-driven search,…

This paper presents an improved LLM based model for Grammatical Error Detection (GED), which is a very challenging and equally important problem for many applications. The traditional approach to GED involved hand-designed features, but…

Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Language models, whether fine-tuned or prompted with few-shot…

When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…

Recently, detection of label errors and improvement of label quality in datasets for supervised learning tasks has become an increasingly important goal in both research and industry. The consequences of incorrectly annotated data include…

Can non-programmers annotate natural language utterances with complex programs that represent their meaning? We introduce APEL, a framework in which non-programmers select among candidate programs generated by a seed semantic parser (e.g.,…

While Retrieval-Augmented Generation (RAG) is increasingly adopted to ground Large Language Models (LLMs) in software artifacts, the optimal configuration of its components remains an open question for software engineering (SE) tasks. The…

Recognition of personalized content remains a challenge in end-to-end speech recognition. We explore three novel approaches that use personalized content in a neural rescoring step to improve recognition: gazetteers, prompting, and a…

Automated Essay Scoring (AES) plays a crucial role in assessing language learners' writing quality, reducing grading workload, and providing real-time feedback. The lack of annotated essay datasets inhibits the development of Arabic AES…

Grammatical Error Correction (GEC) is the task of correcting errorful sentences into grammatically correct, semantically consistent, and coherent sentences. Popular GEC models either use large-scale synthetic corpora or use a large number…

Annotated data has become the most important bottleneck in training accurate machine learning models, especially for areas that require domain expertise. A recent approach to deal with the above issue proposes using natural language…

The correctness of a compiler affects the correctness of every program written in the language, and thus must be thoroughly evaluated. Existing automatic compiler testing methods however either rely on weak oracles (e.g., a program behaves…

Retrieval-Augmented Generation (RAG) fine-tuning has shown substantial improvements over vanilla RAG, yet most studies target document question answering and often rely on standard NLP metrics that can obscure factual differences. We…