Add text similarity task for Taskflow #1345
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ZeyuChen
reviewed
Nov 22, 2021
docs/model_zoo/taskflow.md
Outdated
| @@ -174,6 +176,20 @@ senta("作为老的四星酒店，房间依然很整洁，相当不错。机场 | |||
| >>> [{'text': '作为老的四星酒店，房间依然很整洁，相当不错。机场接机服务很好，可以在车上办理入住手续，节省时间。', 'label': 'positive', 'score': 0.984320878982544}] | |||
| ``` | |||
|
|
|||
| ### 文本匹配 | |||
docs/model_zoo/taskflow.md
Outdated
| @@ -11,6 +11,7 @@ | |||
| - [文本纠错](#文本纠错) | |||
| - [句法分析](#句法分析) | |||
| - [情感分析](#情感分析) | |||
| - [文本匹配](#文本匹配) | |||
paddlenlp/taskflow/text_matching.py
Outdated
|
|
||
| usage = r""" | ||
| from paddlenlp import Taskflow | ||
|
|
There was a problem hiding this comment.
taskname改为text similarity会不会更为表意？
linjieccc
changed the title
ZeyuChen
reviewed
Nov 22, 2021
docs/model_zoo/taskflow.md
Outdated
|
|
||
| similarity = Taskflow("text_similarity") | ||
| similarity([["世界上什么东西最小", "世界上什么东西最小？"]]) | ||
| >>> [{'query': '世界上什么东西最小', 'title': '世界上什么东西最小？', 'similarity': 0.992725}] |
There was a problem hiding this comment.
输入的key可能采用text1，text2 更加准确。如果用query和title会被倾向于认为是短文本与长文本匹配
ZeyuChen
reviewed
Nov 23, 2021
| [{'text1': '世界上什么东西最小', 'text2': '世界上什么东西最小？', 'similarity': 0.992725}] | ||
| ''' | ||
|
|
||
| similarity = Taskflow("text_similarity", batch_size=2) |
There was a problem hiding this comment.
batch_size这地方需要手动配置吗？是否可以根据输入的size自动获得呢？
There was a problem hiding this comment.
是说batch_size=1的话，不能同时输入两条？还是说这个batch size是作为predictor的关键参数
There was a problem hiding this comment.
batch_size目前是手动配置的，默认值是1，考虑是让用户结合机器本身情况配置
batch_size是predictor的关键参数
ZeyuChen
reviewed
Nov 24, 2021
| self.input_handles[1].copy_from_cpu(t_segment_ids) | ||
| self.predictor.run() | ||
| vecs_title = self.output_handle[1].copy_to_cpu() | ||
|
|
ZeyuChen
reviewed
Nov 26, 2021
docs/model_zoo/taskflow.md
Outdated
| similarity([["世界上什么东西最小", "世界上什么东西最小？"]]) | ||
| >>> [{'text1': '世界上什么东西最小', 'text2': '世界上什么东西最小？', 'similarity': 0.992725}] | ||
|
|
||
| similarity = Taskflow("text_similarity", batch_size=2) |
There was a problem hiding this comment.
还是得告诉开发者，为什么这个batch_size=2有什么用。
There was a problem hiding this comment.
其他examples都得同步增强下这里的API参数描述。不然这里会误解，必须要设置batch size=2，才能传入两条样本
There was a problem hiding this comment.
已修改，这里修改了代码示例，新增可配置参数说明
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR types
New features
PR changes
APIs
Description
1.Add text similarity task for Taskflow