Related papers: Evolutionary Context Search for Automated Skill Ac…

We propose a novel language-independent approach to improve the efficiency for Grammatical Error Correction (GEC) by dividing the task into two subtasks: Erroneous Span Detection (ESD) and Erroneous Span Correction (ESC). ESD identifies…

Performance metrics-driven context caching has a profound impact on throughput and response time in distributed context management systems for real-time context queries. This paper proposes a reinforcement learning based approach to…

Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity between a query and documents. However, the scalar similarity…

End-to-end (E2E) automatic speech recognition (ASR) models have become standard practice for various commercial applications. However, in real-world scenarios, the long-tailed nature of word distribution often leads E2E ASR models to…

Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and…

Accurate alignment between languages is fundamental for improving cross-lingual pre-trained language models (XLMs). Motivated by the natural phenomenon of code-switching (CS) in multilingual speakers, CS has been used as an effective data…

Retrieval-Augmented Generation (RAG) compensates for the static knowledge limitations of Large Language Models (LLMs) by integrating external knowledge, producing responses with enhanced factual correctness and query-specific…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously described…

Humans do not memorize everything. Thus, humans recognize scene changes by exploring the past images. However, available past (i.e., reference) images typically represent nearby viewpoints of the present (i.e., query) scene, rather than the…

Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the true gradient) is…

Retrieval-augmented language models have demonstrated performance comparable to much larger models while requiring fewer computational resources. The effectiveness of these models crucially depends on the overlap between query and retrieved…

Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

We consider the problem of how to improve automatic target recognition by fusing the naive sensor-level classification decisions with "intuition," or context, in a mathematically principled way. This is a general approach that is compatible…

Generic sentence embeddings provide a coarse-grained approximation of semantic textual similarity but ignore specific aspects that make texts similar. Conversely, aspect-based sentence embeddings provide similarities between texts based on…

Large Language Models (LLMs) excel in language tasks but are prone to hallucinations and outdated knowledge. Retrieval-Augmented Generation (RAG) mitigates these by grounding LLMs in external knowledge. However, in complex domains involving…

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Automated Short Answer Scoring (ASAS) is a critical component in educational assessment. While traditional ASAS systems relied on rule-based algorithms or complex deep learning methods, recent advancements in Generative Language Models…

In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We…