Code Monkey home page Code Monkey logo

argument_tagger's Introduction

Summarize

Model F1(Claim) F1(Premise) Accuracy
CRF 0.37 0.32 0.59
LSTM 0.15 0.16 0.60
BiLSTM 0.17 0.17 0.63
BiLSTM-CRF 0.23 0.13 0.41
Wangchanberta 0.51 0.39 0.65
Model F1(B-c) F1(B-p) F1(I-c) F1(I-p) Accuracy
CRF 0.66 0.56 0.50 0.72 0.59
LSTM 0.32 0.59 0.54 0.69 0.60
BiLSTM 0.76 0 .58 0.59 0.67 0.63
BiLSTM-CRF 0.41 0.34 0.32 0.48 0.41
Wangchanberta 0.75 0.64 0.65 0.72 0.65


Bar Plot

sentence word



CRF

Accuracy 0.59
Precision Recall F1 support
B-c 0.74 0.59 0.66 176
B-p 0.65 0.56 0.56 176
I-c 0.52 0.50 0.50 1910
I-p 0.71 0.73 0.72 5083
micor avg 0.66 0.66 0.66 7336
macro avg 0.65 0.57 0.61 7336
weighted avg 0.66 0.66 0.66 7336
Precision Recall F1 support
C 0.41 0.33 0.37 176
P 0.38 0.28 0.32 176
micor avg 0.40 0.31 0.35 352
macro avg 0.40 0.31 0.35 352
weighted avg 0.40 0.31 0.35 352

LSTM

Accuracy 0.60
Precision Recall F1 support
B-c 0.82 0.20 0.32 157
B-p 0.75 0.48 0.59 158
I-c 0.58 0.51 0.54 1735
I-p 0.60 0.81 0.69 3727
micor avg 0.60 0.70 0.64 5777
macro avg 0.69 0.50 0.53 5777
weighted avg 0.60 0.70 0.63 5777
Precision Recall F1 support
C 0.13 0.17 0.15 157
P 0.11 0.25 0.16 158
micor avg 0.12 0.21 0.15 315
macro avg 0.12 0.21 0.15 315
weighted avg 0.12 0.21 0.15 315

BiLSTM

Accuracy 0.63
Precision Recall F1 support
B-c 0.84 0.70 0.76 157
B-p 0.77 0.47 0.58 158
I-c 0.75 0.48 0.59 1735
I-p 0.65 0.68 0.67 3727
micor avg 0.68 0.62 0.65 5777
macro avg 0.75 0.58 0.65 5777
weighted avg 0.69 0.62 0.64 5777
Precision Recall F1 support
C 0.15 0.20 0.17 157
P 0.12 0.27 0.17 158
micor avg 0.14 0.23 0.17 315
macro avg 0.14 0.23 0.17 315
weighted avg 0.14 0.23 0.17 315

BiLSTM-CRF

Accuracy 0.41
Precision Recall F1 support
B-c 0.38 0.45 0.41 161
B-p 0.29 0.40 0.34 170
I-c 0.32 0.31 0.32 1845
I-p 0.34 0.78 0.48 3518
micor avg 0.34 0.60 0.43 5694
macro avg 0.33 0.48 0.38 5694
weighted avg 0.34 0.60 0.42 5694
Precision Recall F1 support
C 0.21 0.25 0.23 161
P 0.11 0.16 0.13 170
micor avg 0.15 0.21 0.18 331
macro avg 0.16 0.21 0.18 331
weighted avg 0.16 0.212 0.18 331

Wangchanberta

Accuracy 0.65
Precision Recall F1 support
B-c 0.73 0.77 0.75 154
B-p 0.50 0.70 0.64 155
I-c 0.70 0.61 0.65 1675
I-p 0.65 0.81 0.72 3637
micor avg 0.66 0.75 0.70 5621
macro avg 0.67 0.72 0.69 56221
weighted avg 0.67 0.75 0.70 5621
Precision Recall F1 support
C 0.45 0.59 0.51 154
P 0.31 0.54 0.39 155
micor avg 0.37 0.56 0.44 309
macro avg 0.38 0.56 0.45 309
weighted avg 0.38 0.56 0.45 309

argument_tagger's People

Contributors

pitiwatmike avatar

Stargazers

avatar

Watchers

avatar

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.