Giter VIP home page Giter VIP logo

spice's Introduction

Semantic Parsing for Conversational Question Answering over Knowledge Graphs

This repository contains data and code for our semantic parsing dataset SPICE. Please contact Laura Perez-Beltrachini ([email protected]) or Parag Jain ([email protected]) if you have any questions.

SPICE Dataset

The dataset is available for download from here.

The scripts for the different annotations (e.g., NER/NEL) on the dataset can be found here.

Sparql Server for SPICE Knowledge Graph

Instructions on how to set up the SPICE knowledge graph can be found here.

Baselines

BertSP

You will find code and instructions related to our BertSP baseline here.

LasagneSP

You will find code and instructions related to our LasagneSP baseline here.

Evaluation

For instructions on the evaluation scripts see here.

spice's People

Contributors

lauhaide avatar

Stargazers

Vishnudev Krishnadas avatar Saga Ekakristi avatar Beckett avatar  avatar Hwq avatar Zhanwen Chen avatar Matthis Houlès avatar  avatar Abdullah Baharoon avatar Roxanne avatar  avatar Basel Ajarmah avatar ZHANGHENGYUAN658 avatar Federico Pianzola avatar Zhuoran Jin avatar Yu Su avatar Parag Jain avatar  avatar

Watchers

Pasquale Minervini avatar Kenneth Heafield avatar Rico Sennrich avatar James Cloos avatar Barry Haddow avatar Ulrich Germann avatar Alexandra Birch avatar Parag Jain avatar Kostas Georgiou avatar  avatar

spice's Issues

Elasticsearch error in allenNLP-NER

Hi.

When I try to run below code in allenNLP-NER after run elastic_search server in localhost:9200

python nel.py  \
   -data_path "data_path/" \
  -save_path "tag_data_ner" \
  -file_path "trainlist.txt" \
  -dataset 'train' \
  -start 0  \
  -end -1 

I found the error below for every file in trainlist.txt

Failed  KGQA/SPICE/SPICE_release/train/QA_1023/QA_0.json
File KGQA/SPICE/SPICE_release/train/QA_1023/QA_42.json.tagged will be processed ... 
Traceback (most recent call last):
  File "KGQA/SPICE/dataset/ner/allennlp_ner/nel.py", line 69, in add_nel_file
    return _add_nel_file(data_file,outfile, predictor_elmo)
  File "KGQA/SPICE/dataset/ner/allennlp_ner/nel.py", line 108, in _add_nel_file
    r=elasticsearch_query(query=w, res_size=5)
  File "KGQA/SPICE/dataset/ner/allennlp_ner/nel.py", line 56, in elasticsearch_query
    res = elastic_search.search(index='csqa_wikidata', doc_type='entities',
  File "/home/anaconda3/envs/SPICE/lib/python3.9/site-packages/elasticsearch/client/utils.py", line 139, in _wrapped
    return func(*args, params=params, headers=headers, **kwargs)
  File "/home/anaconda3/envs/SPICE/lib/python3.9/site-packages/elasticsearch/client/__init__.py", line 1479, in search
    return self.transport.perform_request(
  File "/home/anaconda3/envs/SPICE/lib/python3.9/site-packages/elasticsearch/transport.py", line 345, in perform_request
    status, headers_response, data = connection.perform_request(
  File "/home/anaconda3/envs/SPICE/lib/python3.9/site-packages/elasticsearch/connection/http_urllib3.py", line 256, in perform_request
    self._raise_error(response.status, raw_data)
  File "/home/anaconda3/envs/SPICE/lib/python3.9/site-packages/elasticsearch/connection/base.py", line 287, in _raise_error
    raise HTTP_EXCEPTIONS.get(status_code, TransportError)(
elasticsearch.exceptions.RequestError: RequestError(400, 'no handler found for uri [/csqa_wikidata/entities/_search] and method [POST]', 'no handler found for uri [/csqa_wikidata/entities/_search] and method [POST]')

Is there any additional setting I missed?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.