From e68946965df578860ec3f5e58938f199440bb07a Mon Sep 17 00:00:00 2001
From: Branden Chan <33759007+brandenchan@users.noreply.github.com>
Date: Tue, 5 Oct 2021 14:38:15 +0200
Subject: [PATCH] Update Reader language options
---
docs/latest/guides/languages.mdx | 47 ++++++++++++++++++++++++++++----
1 file changed, 41 insertions(+), 6 deletions(-)
diff --git a/docs/latest/guides/languages.mdx b/docs/latest/guides/languages.mdx
index bb415c821..bc904ffbe 100644
--- a/docs/latest/guides/languages.mdx
+++ b/docs/latest/guides/languages.mdx
@@ -89,6 +89,17 @@ there are a couple QA models that are directly usable in Haystack.
),
},
+ {
+ title: "French",
+ content: (
+
+ from haystack.reader import FARMReader
+
+ reader = FARMReader("etalab-ia/camembert-base-squadFR-fquad-piaf")
+
+
+ ),
+ },
{
title: "Italian",
content: (
@@ -137,13 +148,24 @@ there are a couple QA models that are directly usable in Haystack.
content: (
+ from haystack.reader import TransformersReader
+
+ reader = TransformersReader("deepset/gelectra-large-germanquad")
+
+
+ ),
+ },
{
title: "French",
content: (
from haystack.reader import TransformersReader
- reader = TransformersReader("illuin/camembert-base-fquad")
+ reader = TransformersReader("etalab-ia/camembert-base-squadFR-fquad-piaf")
),
@@ -154,8 +176,22 @@ there are a couple QA models that are directly usable in Haystack.
from haystack.reader import TransformersReader
- reader =
- TransformersReader("mrm8488/bert-italian-finedtuned-squadv1-it-alfa")
+ reader = TransformersReader("mrm8488/bert-italian-finedtuned-squadv1-it-alfa")
+
+
+ ),
+ },
+ {
+ title: "Chinese",
+ content: (
+
+ from haystack.reader import TransformersReader
+
+ reader = TransformersReader("uer/roberta-base-chinese-extractive-qa")
+
+ # or
+
+ reader = TransformersReader("wptoux/albert-chinese-large-qa")
),
@@ -166,8 +202,7 @@ there are a couple QA models that are directly usable in Haystack.
from haystack.reader import TransformersReader
- reader =
- TransformersReader("deepset/xlm-roberta-large-squad2")
+ reader = TransformersReader("deepset/xlm-roberta-large-squad2")
),
@@ -185,7 +220,7 @@ We are the creators of the **German** model and you can find out more about it [
The **French**, **Italian**, **Spanish**, **Portuguese** and **Chinese** models are monolingual language models trained on versions of the SQuAD dataset in their respective languages
and their authors report decent results in their model cards
-(e.g. [here](https://huggingface.co/illuin/camembert-base-fquad) and [here](https://huggingface.co/mrm8488/bert-italian-finedtuned-squadv1-it-alfa)).
+(e.g. [here](https://huggingface.co/etalab-ia/camembert-base-squadFR-fquad-piaf) and [here](https://huggingface.co/mrm8488/bert-italian-finedtuned-squadv1-it-alfa)).
There also exist Korean QA models on the model hub but their performance is not reported.
The **zero-shot model** that is shown above is a **multilingual XLM-RoBERTa Large** that is trained on English SQuAD.