2 citations · 7 across the 12 of their papers we have counts for
12 papers · 1 filter
Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification
Takuma Udagawa, Yang Zhao, Hiroshi Kanayama +1
Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirabl…
Robust ASR Error Correction with Conservative Data Filtering
Takuma Udagawa, Masayuki Suzuki, Masayasu Muraoka +1
Error correction (EC) based on large language models is an emerging technology to enhance the performance of automatic speech recognition (ASR) systems. Generally, training data fo…
INDUS: Effective and Efficient Language Models for Scientific Applications
Bishwaranjan Bhattacharjee, Aashka Trivedi, Masayasu Muraoka +33
Large language models (LLMs) trained on general domain corpora showed remarkable results on natural language processing (NLP) tasks. However, previous research demonstrated LLMs tr…
A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models
Takuma Udagawa, Aashka Trivedi, Michele Merler +1
Large language models have become a vital component in modern NLP, achieving state of the art performance in a variety of tasks. However, they are often inefficient for real-world…
Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata +2
Transferring the knowledge of large language models (LLMs) is a promising technique to incorporate linguistic knowledge into end-to-end automatic speech recognition (ASR) systems.…
Neural Architecture Search for Effective Teacher-Student Knowledge Transfer in Language Models
Aashka Trivedi, Takuma Udagawa, Michele Merler +3
Large pretrained language models have achieved state-of-the-art results on a variety of downstream tasks. Knowledge Distillation (KD) into a smaller student model addresses their i…
Sentence Identification with BOS and EOS Label Combinations
Takuma Udagawa, Hiroshi Kanayama, Issei Yoshida
The sentence is a fundamental unit in many NLP applications. Sentence segmentation is widely used as the first preprocessing task, where an input text is split into consecutive sen…
Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata +2
Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have been successfully applied to ASR N-best rescoring. However, whether or how they can benefit competitive, nea…
Maintaining Common Ground in Dynamic Environments
Takuma Udagawa, Akiko Aizawa
Common grounding is the process of creating and maintaining mutual understandings, which is a critical aspect of sophisticated human communication. While various task settings have…
A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions
Takuma Udagawa, Takato Yamazaki, Akiko Aizawa
Recent models achieve promising results in visually grounded dialogues. However, existing datasets often contain undesirable biases and lack sophisticated linguistic analyses, whic…
An Annotated Corpus of Reference Resolution for Interpreting Common Grounding
Takuma Udagawa, Akiko Aizawa
Common grounding is the process of creating, repairing and updating mutual understandings, which is a fundamental aspect of natural language conversation. However, interpreting the…
A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context
Takuma Udagawa, Akiko Aizawa
Common grounding is the process of creating, repairing and updating mutual understandings, which is a critical aspect of sophisticated human communication. However, traditional dia…