Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577
Apache License 2.0
315
stars
39
forks
source link
Should the leaning domain contain only assertion texts (like "Python is a high-level general-purpose programming language")? #30
Hi.
Should the leaning domain contain only assertion texts (like "Python is a high-level general-purpose programming language" in your example)? In your pipeline the first step is Query Generation: For a given text from our domain, we first use a T5 model that generates a possible query for the given text. E.g. when your text is “Python is a high-level general-purpose programming language”, the model might generate a query like “What is Python”. You can find various query generators on our doc2query-hub. Does that mean that texts which couldn't be converted into queries (e.g. "Investment consulting for legal entities and individuals.") cannot be used for training?
Hi. Should the leaning domain contain only assertion texts (like "Python is a high-level general-purpose programming language" in your example)? In your pipeline the first step is Query Generation: For a given text from our domain, we first use a T5 model that generates a possible query for the given text. E.g. when your text is “Python is a high-level general-purpose programming language”, the model might generate a query like “What is Python”. You can find various query generators on our doc2query-hub. Does that mean that texts which couldn't be converted into queries (e.g. "Investment consulting for legal entities and individuals.") cannot be used for training?