Ayush KumarNAACL 2024 —Overview of key themes in space of Large Language Models (LLMs)After attending EMNLP 2023 in Singapore, where many talked about Large Language Models (LLMs), I was eager to see what NAACL 2024 would…Aug 4Aug 4
Ayush KumarSynthetic Data for Human-Preference Modelling: EMNLP 2023 Overview Part 3In the rapidly evolving field of language model (LM) development, the role of preference modeling has become increasingly crucial. This…Jan 7Jan 7
Ayush KumarMaking LLMs “learn” from the past mistakes: EMNLP 2023 Overview Part 2The Large Language Models (LLMs) has traditionally been a statically learned models, which would often falter in their capacity to learn…Jan 7Jan 7
Ayush KumarinThe Observe.AI Tech BlogWhat questions are my customers asking?:This blog refers to our paper accepted at Interspeech 2023, Dublin.Aug 18, 2023Aug 18, 2023
Ayush KumarinThe Observe.AI Tech BlogDoes Utterance Entail Intent?:This blog refers to our technical paper accepted at Interspeech 2022, Incheon, South KoreaSep 15, 2022Sep 15, 2022
Ayush KumarinThe Observe.AI Tech BlogDoes BERT-based language model understands the nuances of spoken (ASR) transcripts?This blog refers to our technical paper accepted at BlackboxNLP@EMNLP 2021, Punta Cana.Nov 5, 2021Nov 5, 2021
Ayush KumarinThe Observe.AI Tech BlogPhoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR TranscriptHow can we develop a language model that is more robust to ASR errors and leads to better performance on downstream SLU tasks?Aug 25, 20211Aug 25, 20211
Ayush KumarinTowards Data ScienceHow to break in Machine Learning jobs? — Based on 6 years experience in MLDisclaimer: 2 yrs of academic + 4 yrs of professional experience. I don’t claim to be a mentor/coach nor do I claim myself to having an…Jan 3, 2021Jan 3, 2021
Ayush KumarTopic based textual summarizationA document can contain information regarding multiple topics viz., sports and politics. A simple summarization method would present this…Jul 12, 2018Jul 12, 2018