Git Product home page Git Product logo

zmsp's Introduction

the Mingled Structured Predictor (zmsp)

Hi, here is a probably useful repo for Structured Prediction tasks.


Related works:

(* The following ones are using the current version of zmsp-vX.)

  • "Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training": details

(* The following ones are using the older version of zmsp-v2.)

  • "A Survey of Active Learning for Natural Language Processing": details

  • "Transfer Learning from Semantic Role Labeling to Event Argument Extraction with Template-based Slot Querying": details

  • "On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling": details

  • "Comparing Span Extraction Methods for Semantic Role Labeling": details


(* The following ones are using the older version of zmsp-v1.)

  • "An Empirical Exploration of Local Ordering Pre-training for Structured Prediction": details

  • "A Two-Step Approach for Implicit Event Argument Detection": details

  • Some other parsers for interested readers: details

  • "An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing": details

  • "On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing": details

zmsp's People

Contributors

zzsfornlp avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

zmsp's Issues

How to initiate the project?

Hi! Thank you for your code! I was trying to replicate your work in "An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing". But after I prepared my own data, and made a running script as you suggested in "v1/docs/emp_graph.md", the program seemed unable to find the module "msp".
I also noticed that "v1/docs/run.md" says "the main dir zmsp should be in sys.path", but I can't figure out what that means.
Here's my script to run the project, and the error reported.

#!/usr/bin/env bash
# =====
# base options
base_opt="conf_output:_conf partype:graph init_from_pretrain:1 lrate.val:0.001 drop_embed:0.33 dropmd_embed:0.33 singleton_thr:2 fix_drop:1 max_epochs:300"
global_unproj_m="dec_algorithm:unproj output_normalizing:global"
# possible losses
prob_loss="loss_function:prob margin.init_val:0."

# =====
# specify paths
SRC_DIR=../v1/
method=${global_unproj_m}
loss=${prob_loss}
# further specify `train/dev/test/embed` paths
DATA_TRAIN="data/2.7UD_English-EWT/en_ewt-ud-train.conllu"
DATA_DEV="data/2.7UD_English-EWT/en_ewt-ud-dev.conllu"
DATA_TEST="data/2.7UD_English-EWT/en_ewt-ud-test.conllu"
DATA_EMBED="data/wiki.en.vec"
# =====
# running
# on GPU 0
CUDA_VISIBLE_DEVICES=0 PYTHONPATH=${SRC_DIR} python3 v1/tasks/cmd.py zdpar.main.train train:${DATA_TRAIN} dev:${DATA_DEV} test:${DATA_TEST} pretrain_file:${DATA_EMBED} device:0 ${base_opt} ${method} ${loss}

image
Could do tell me how to fix this? Thanks!

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.