[HN Gopher] Enhancing Frame Detection with Retrieval Augmented G...
___________________________________________________________________
Enhancing Frame Detection with Retrieval Augmented Generation
Author : PaulHoule
Score : 34 points
Date : 2025-02-28 17:25 UTC (4 days ago)
(HTM) web link (arxiv.org)
(TXT) w3m dump (arxiv.org)
| tsunego wrote:
| Cool paper but unsurprising results since anything benefits from
| RAG
| 0xdeadbeefbabe wrote:
| Also, grep is really exciting with lots of data.
| visarga wrote:
| I usually annotate my chunks with title, summary, keywords and
| multiple levels of hierarchical topics. More recently I thought
| about annotating intent, user values and tactics, especially for
| debate related text and LLM chats. So I would annotate state (the
| summary of the content itself), values (intent and values) and
| policy (tactics), taking inspiration from RL.
|
| The idea of detecting frames and using them to tease out the
| implicit meaning from text is quite nice. It seems there is a lot
| more to discover about using LLMs prior to RAG. Text is like
| code, you can't know what it does untill you run it, and in this
| case, until you annotate it. For example "10+10" won't embed
| close to "20". And "The fifth letter in this string" won't
| retrieve "f" by emmbedding similarity.
| nthingtohide wrote:
| I have this very stupid question and I haven't seen it answered
| anywhere.
|
| Let's say LLM while training is ingesting a very long book.
|
| The name of the author of the book would appear at the very
| beginning.
|
| While inference, how does the llm determine that the last
| chapter of the book is written by so and so author and hence
| that chunk should be near that author's style.
| visarga wrote:
| The information is probably lost, training on very long
| inputs is expensive, we usually train on short inputs and
| only send longer ones at the end. So the author name would
| not appear together with all the chunks unless it appears on
| every page in the header, assuming the headers are not
| stripped out first.
| andrewmutz wrote:
| From the paper:
|
| > Frames ... are conceptual structures that capture the semantic
| and syntactic relationships underlying language. They are helpful
| in providing a structured semantic context for understanding
| relationships between entities, enabling tasks like Machine
| Reading Comprehension and Information Extraction to be more
| accurate and contextually aware.
| simonw wrote:
| I had to learn what a "frame" is to understand this.
| https://framenet.icsi.berkeley.edu/ is useful (FrameNet is the
| collection of 1,000 frames used in the paper).
|
| An example of a frame is an "Event" -
| https://framenet.icsi.berkeley.edu/fnReports/data/frameIndex... -
| where:
|
| > An Event takes place at a Place and Time.
|
| So if you're extracting frames from a piece of text, that's one
| of the concepts you might be trying to identify - along with what
| the place and time are.
| sitkack wrote:
| https://en.wikipedia.org/wiki/Frame_(artificial_intelligence...
|
| > Frames are an artificial intelligence data structure used to
| divide knowledge into substructures by representing
| "stereotyped situations".
|
| They are highly related to ontology systems and knowledge
| engineering.
| kridsdale1 wrote:
| Seems like a viable name for this data structure could have
| been "Thing".
___________________________________________________________________
(page generated 2025-03-04 23:01 UTC)