Semanlink - Adam Roberts sur Twitter : "New preprint: How Much Knowledge Can You Pack into the Parameters of a Language Model?..."

Adam Roberts sur Twitter : "New preprint: How Much Knowledge Can You Pack into the Parameters of a Language Model?..."

Tags:

Au sujet de ce document

sl:bookmarkOf : https://twitter.com/ada_rob/status/1227062195671822336
sl:creationDate : 2020-02-11
sl:creationTime : 2020-02-11T12:24:21Z
sl:relatedDoc : http://www.semanlink.net/doc/2020/02/how_much_knowledge_can_you_pack

Infos sur le fichier

Bookmark of: https://twitter.com/ada_rob/status/1227062195671822336

Documents with similar tags (experimental)

How Much Knowledge Can You Pack Into the Parameters of a Language Model?

Tags:

> It has recently been observed that neural language
models trained on unstructured text can
implicitly store and retrieve knowledge using
natural language queries.

indeed, cf. Facebook's paper [Language Models as Knowledge Bases?](/doc/2019/09/_1909_01066_language_models_as)

> In this short paper,
we measure the practical utility of this
approach by fine-tuning pre-trained models to
answer questions without access to any external
context or knowledge.

> we show that a large language
model pre-trained on unstructured text can
attain competitive results on open-domain question
answering benchmarks without any access
to external knowledge

BUT:

>1. state-of-the-art results only with the largest model
which had 11 billion parameters.
>1. “open-book” models
typically provide some indication of what information
they accessed when answering a question
that provides a useful form of interpretability.
In contrast, our model distributes knowledge
in its parameters in an inexplicable way, which
precludes this form of interpretability.
>1. **the maximum-likelihood objective provides no guarantees as to whether
a model will learn a fact or not.**

So, what's the point? To be compared with this [IBM's paper](/doc/2019/09/_1909_04120_span_selection_pre): "a new pre-training task inspired by reading comprehension and an effort to avoid encoding general knowledge in the transformer network itself"

2020-02-11 A propos