Question rewriting for conversational search based on unsupervised and supervised methods.
Project description
This is an official source code repository of the paper: Mele et al., Adaptive Utterance Rewriting for Conversational Search, IP&M, 2021.
Authors: Ida Mele, Cristina Ioana Muntean, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto, Ophir Frieder.
Code: https://github.com/hpclab/adaptive-utterance-rewriting-conversational-search
Data
- Datasets: CAsT 2019 dataset divided into training and test sets as specified in the paper.
Query resolution
The query resolution module uses both supervised and unsupervised methods for rewriting queries.
For the supervised classification based rewriting run either of the following rewriting strategies "Standard", "Enriched", "LastSE", "First_and_Last_SE", "First_or_Last_SE":
from convrewriting.supervised.pipeline_classification import rewrite_strategy
rewrite_strategy("Standard")
For the unsupervised based rewriting strategy run either of the following:
from convrewriting.unsupervised.pipeline_nlp import rewrite_context, rewrite_first_topic, rewrite_topic_shift
rewrite_context()
rewrite_first_topic()
rewrite_topic_shift()
Citation Licence
This source code is subject to the following citation license:
By downloading and using the source code stored in this GitHub repository, you agree to cite at the undernoted paper in any kind of material you produce where this code has been used to conduct search or experimentation, whether be it a research paper, dissertation, article, poster, presentation, or documentation. By using this software, you have agreed to the citation licence.
@article{mele2021adaptive,
title = {Adaptive Utterance Rewriting for Conversational Search},
journal = {Information Processing \& Management},
volume = {58},
number = {6},
pages = {102682},
year = {2021},
issn = {0306-4573},
doi = {https://doi.org/10.1016/j.ipm.2021.102682},
url = {https://www.sciencedirect.com/science/article/pii/S0306457321001679},
author = {Ida Mele and Cristina Ioana Muntean and Franco Maria Nardini and Raffaele Perego and Nicola Tonellotto and Ophir Frieder},
}
Contact Us
For any other question/comment, write us an email: {cristina.muntean@isti.cnr.it}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for convrewriting-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 32fab77f58fa0d3a332ef5fa7bf2590822502956b6862a5389f0c89fe6fa62d8 |
|
MD5 | 64fdd506581e36e0114467cc2baa3979 |
|
BLAKE2b-256 | ab4558cb90082ab7b16380ac7a0220f47ff613cb2b9e286ed974121792af43c7 |