Related papers: Semistructured Merge with Language-Specific Syntac…

We present SentAlign, an accurate sentence alignment tool designed to handle very large parallel document pairs. Given user-defined parameters, the alignment algorithm evaluates all possible alignment paths in fairly large documents of…

Effective Service Function Chain (SFC) provisioning requires precise orchestration in dynamic and latency-sensitive networks. Reinforcement Learning (RL) improves adaptability but often ignores structured domain knowledge, which limits…

Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging due to inter-domain interference. To overcome this challenge, we propose a…

Low-resource languages (LRLs) often lack high-quality, large-scale datasets for training effective text embedding models, hindering their application in tasks like retrieval-augmented generation (RAG) and semantic search. In this work, we…

Large Language Models (LLMs) are frequently used for multi-faceted language generation and evaluation tasks that involve satisfying intricate user constraints or taking into account multiple aspects and criteria. However, their performance…

Recent work on curvilinear structure segmentation has mostly focused on backbone network design and loss engineering. The challenge of collecting labelled data, an expensive and labor intensive process, has been overlooked. While labelled…

Technical support problems are often long and complex. They typically contain user descriptions of the problem, the setup, and steps for attempted resolution. Often they also contain various non-natural language text elements like outputs…

The increasing capability of large language models (LLMs) to generate synthetic content has heightened concerns about their misuse, driving the development of Machine-Generated Text (MGT) detection models. However, these detectors face…

The growing complexity of legal cases has lead to an increasing interest in legal information retrieval systems that can effectively satisfy user-specific information needs. However, such downstream systems typically require documents to be…

Efficient deployment of resource-intensive transformers on edge devices necessitates cross-stack optimization. We thus study the interrelation between structured pruning and systolic acceleration, matching the size of pruned blocks with the…

Supervised fine-tuning (SFT) on instruction-following corpus is a crucial approach toward the alignment of large language models (LLMs). However, the performance of LLMs on standard knowledge and reasoning benchmarks tends to suffer from…

Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two complementary representations of the same computer program. Traditionally, designers of machine learning models have relied predominantly either on Structure…

The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…

Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. However, current approaches often overlook the importance of…

We study model merging as a practical alternative to conventional adaptation strategies for code-mixed NLP. Starting from a multilingual base model, we: (i) perform continued pre-training (CPT) on unlabeled code-mixed text to obtain an…

This paper introduces SemRAG, an enhanced Retrieval Augmented Generation (RAG) framework that efficiently integrates domain-specific knowledge using semantic chunking and knowledge graphs without extensive fine-tuning. Integrating…

Deep-learning based speech separation models confront poor generalization problem that even the state-of-the-art models could abruptly fail when evaluating them in mismatch conditions. To address this problem, we propose an…

Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context…

Learned Sparse Retrieval (LSR) combines the efficiency of bi-encoders with the transparency of lexical matching, but existing approaches struggle to scale beyond English. We introduce MILCO, an LSR architecture that maps queries and…

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…