This focuses on computational approaches to understanding, processing, and generating human languages.
The article discusses the use of Parameter-Efficient Fine-Tuning (PEFT) in speech processing. The authors conducted experiments to compare different PEFT methods and their layer-wise placement using Differentiable Architecture Search (DARTS)….
Continue readingThe article presents a research on evaluating the quality and variability of text generated by Large Language Models (LLMs). Conventional evaluation methods often fail to capture the holistic semantic equivalence,…
Continue readingThis academic article discusses the potential of GPT-4V (multi-modal large language models) in marine analysis. Despite the success of GPT-4V in various fields, its use in domain-specific analysis like marine…
Continue readingThe research paper presents the work of Team Shayona on two tasks of SMMH4-23. Task 1 involved the binary classification of English tweets self-reporting a COVID-19 diagnosis, and Task 4…
Continue readingThe article presents a new method for answering tourism-related questions that seek Point-of-Interest (POI) recommendations. Traditional methods of encoding each pair of question and POI become inefficient with an increase…
Continue readingThe article presents DIALIGHT, a toolkit for developing and evaluating multilingual Task-Oriented Dialogue (TOD) systems. It’s designed to facilitate systematic evaluations and comparisons between TOD systems using Pretrained Language Models…
Continue readingThe article discusses the limitations of existing Temporal Knowledge Graph Question Answering (TKGQA) models. These models often fail to handle complex questions involving multiple temporal facts. To address this, the…
Continue readingThis article presents L3Cube-IndicNews, a multilingual text classification corpus aimed at creating a high-quality dataset for Indian regional languages. The focus is on news headlines and articles in 10 prominent…
Continue readingThe paper titled ‘Rethinking Response Evaluation from Interlocutor’s Eye for Open-Domain Dialogue Systems’ focuses on the need for more accurate evaluation methods for open-domain dialogue systems. The authors argue that…
Continue readingThe study investigates the robustness of Large Pre-Trained Language Models (LLMs) for spoken task-oriented dialogues. It highlights that while LLMs have shown excellent performance in written dialogues, their effectiveness in…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
