https://github.com/NTMC-Community/awesome-neural-models-for-semantic-match

A curated list of papers dedicated to neural text (semantic) matching.
https://github.com/NTMC-Community/awesome-neural-models-for-semantic-match

List: awesome-neural-models-for-semantic-match

deep-learning information-retrieval neu-ir question-answering semantic-matching text-similarity

Last synced: about 2 months ago
JSON representation

A curated list of papers dedicated to neural text (semantic) matching.

• Host: GitHub
• URL: https://github.com/NTMC-Community/awesome-neural-models-for-semantic-match
• Owner: NTMC-Community
• License: mit
• Created: 2018-06-18T14:36:33.000Z (over 6 years ago)
• Default Branch: gh-pages
• Last Pushed: 2023-12-08T09:08:01.000Z (10 months ago)
• Last Synced: 2024-05-21T12:18:25.479Z (4 months ago)
• Topics: deep-learning, information-retrieval, neu-ir, question-answering, semantic-matching, text-similarity
• Language: HTML
• Homepage:
• Size: 158 KB
• Stars: 771
• Watchers: 53
• Forks: 125
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-Paper-List - Text Matching - NTMC_Community-be8abf)  (Natural Language Processing)
• awesome-document-similarity - Awesome Neural Models for Semantic Match

README

        


    

    



    
Awesome Neural Models for Semantic Match








    A collection of papers maintained by MatchZoo Team.

    


    Checkout our open source toolkit MatchZoo for more information!






Text matching is a core component in many natural language processing tasks, where many task can be viewed as a matching between two texts input.



    



Where **s** and **t** are source text input and target text input, respectively. The **psi** and **phi** are representation function for input **s** and **t**, respectively. The **f** is the interaction function, and **g** is the aggregation function. More detailed explaination about this formula can be found on [A Deep Look into Neural Ranking Models for Information Retrieval](https://arxiv.org/abs/1903.06902). The representative matching tasks are as follows:

|                                          **Tasks**                                           | **Source Text** |     **Target Text**      |

| :------------------------------------------------------------------------------------------: | :-------------: | :----------------------: |

| [Ad-hoc Information Retrieval](Ad-hoc-Information-Retrieval/Ad-hoc-Information-Retrieval.md) |      query      | document (title/content) |

| [Community Question Answering](Community-Question-Answering/Community-Question-Answering.md) |    question     |     question/answer      |

|     [Paraphrase Identification](Paraphrase-Identification/Paraphrase-Identification.md)     |     string1     |         string2          |

|    [Natural Language Inference](Natural-Language-Inference/Natural-Language-Inference.md)    |     premise     |        hypothesis        |

|                [Response Retrieval](Response-Retrieval/Response-Retrieval.md)                |    context/utterances     |         response         |

|                [Long Form Question Answering](LFQA/LFQA.md)                |    question+document    |         answer         |

### Healthcheck

```python

pip3 install -r requirements.txt

python3 healthcheck.py

```