Add text semantic matching for taskflow #3003
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
linjieccc
reviewed
Aug 10, 2022
docs/model_zoo/taskflow.md
Outdated
| @@ -1324,6 +1325,32 @@ from paddlenlp import Taskflow | |||
| * `output_scores`：是否要输出解码得分，请默认为False。 | |||
| </div></details> | |||
|
|
|||
| ### 文本语义相似度 | |||
There was a problem hiding this comment.
这里是否可以和已有的文本相似度任务合并，通过Taskflow("text_similarity", model="XXX")选择不同的backbone
paddlenlp/taskflow/taskflow.py
Outdated
| "models": { | ||
| "rocketqa-zh-dureader-cross-encoder": { | ||
| "task_class": SemanticMatchingTask, | ||
| "task_flag": 'semantic_matching-cross-encoder', |
There was a problem hiding this comment.
task_flag的模型名称建议和model对齐
linjieccc
reviewed
Aug 18, 2022
paddlenlp/taskflow/taskflow.py
Outdated
| "rocketqa-zh-dureader-cross-encoder": { | ||
| "task_class": TextSimilarityTask, | ||
| "task_flag": 'rocketqa-zh-dureader-cross-encoder', | ||
| }, | ||
| }, | ||
| "default": { | ||
| "model": "simbert-base-chinese" |
There was a problem hiding this comment.
默认模型这里可以改为rocketqa-zh-dureader-cross-encoder
paddlenlp/taskflow/taskflow.py
Outdated
| @@ -192,6 +192,10 @@ | |||
| "task_class": TextSimilarityTask, | |||
| "task_flag": "text_similarity-simbert-base-chinese" | |||
| }, | |||
| "rocketqa-zh-dureader-cross-encoder": { | |||
| "task_class": TextSimilarityTask, | |||
| "task_flag": 'rocketqa-zh-dureader-cross-encoder', | |||
There was a problem hiding this comment.
'rocketqa-zh-dureader-cross-encoder' -> 'text_similarity-rocketqa-zh-dureader-cross-encoder'
linjieccc
reviewed
Aug 18, 2022
docs/model_zoo/taskflow.md
Outdated
|
|
||
| #### 单条输入 | ||
|
|
||
| ```python | ||
| >>> from paddlenlp import Taskflow | ||
| >>> similarity = Taskflow("text_similarity") | ||
| >>> similarity = Taskflow("text_similarity",model="rocketqa-zh-dureader-cross-encoder") |
There was a problem hiding this comment.
建议默认调用不加model参数进行简化，直接similarity = Taskflow("text_similarity")，然后参考UIE提供一个模型选择的表格
tianxin1860
reviewed
Aug 19, 2022
Comment on lines
68
to
72
| if ('rocketqa' not in model): | ||
| self._check_task_files() | ||
| self._get_inference_model() | ||
| else: | ||
| self._construct_model(model) |
There was a problem hiding this comment.
为什么 RocketQA cross encoder 模型不支持走动转静之后的高性能预测？
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
PR changes
Description