Spaces:
Running
Running
title: PyTerrier SPLADE | |
emoji: π | |
colorFrom: green | |
colorTo: green | |
sdk: gradio | |
sdk_version: 3.7 | |
app_file: app.py | |
pinned: false | |
<style> | |
.transformer { | |
display: inline-block; | |
background: #8facdb; | |
position: relative; | |
height: 60px; | |
line-height: 60px; | |
padding: 0 24px; | |
margin: 0 18px; | |
color: #333; | |
cursor: help; | |
} | |
.transformer::before { | |
content: ""; | |
position: absolute; | |
bottom: 0; | |
top: 0; | |
left: -15px; | |
border-top: 30px solid #8facdb; | |
border-bottom: 30px solid #8facdb; | |
border-left: 15px solid transparent; | |
} | |
.transformer::after { | |
content: ""; | |
position: absolute; | |
bottom: 0; | |
top: 0; | |
right: -15px; | |
border-top: 30px solid transparent; | |
border-bottom: 30px solid transparent; | |
border-left: 15px solid #8facdb; | |
} | |
.transformer.boring { | |
background: #ddd; | |
} | |
.transformer.boring::before { | |
border-top-color: #ddd; | |
border-bottom-color: #ddd; | |
} | |
.transformer.boring::after { | |
border-left-color: #ddd; | |
} | |
.df { | |
width: 24px; | |
line-height: 24px; | |
text-align: center; | |
border: 3px double #888; | |
background-color: #eee; | |
color: #333; | |
border-radius: 4px; | |
display: inline-block; | |
box-sizing: content-box; | |
cursor: help; | |
margin: 0 -25px; | |
opacity: 0.5; | |
z-index: 1; | |
position: relative; | |
} | |
.df:hover { | |
opacity: 1; | |
} | |
.pipeline { | |
text-align: center; | |
} | |
</style> | |
This is a demonstration of [PyTerrier's SPLADE package](https://github.com/cmacdonald/pyt_splade). The SPLADE model encodes queries and documents | |
into sparse representations, which can then be used for indexing and retrieval. | |
### Query Encoding | |
Let's start by exploring SPLADE's query encoder. The query encoder is a `QβQ` (query rewriting, query-to-query) transformer, and can be used in pipelines accordingly. | |
It maps a query string into [MatchOp](https://terrier-core.readthedocs.io/en/latest/querylanguage.html#matching-op-query-language) query with terms from the | |
query re-weighted and weighted expansion terms added. | |
<div class="pipeline"> | |
<div class="df" title="Query Frame">Q</div> | |
<div class="transformer" title="SPLADE Query Transformer">SPLADE</div> | |
<div class="df" title="Query Frame">Q</div> | |
</div> | |