Skip to content
Branch: master
Find file Copy path
140 lines (85 sloc) 5.07 KB


A repository for the available models for AllenNLP. While we highlight a particular model for each task on we often have other trained models that might work better for a particular application.

Machine Comprehension

bidaf-model-2017.09.15-charpad.tar.gz (44 MB)

Based on BiDAF (Seo et al, 2017)

$ docker run allennlp/allennlp:v0.7.0 \
    evaluate \ \

start_acc: 0.642
  end_acc: 0.671
 span_acc: 0.552
       em: 0.683
       f1: 0.778

Textual Entailment

decomposable-attention-elmo-2018.02.19.tar.gz (665 MB)

Based on Parikh et al, 2017

$ docker run allennlp/allennlp:v0.7.0 \
    evaluate \ \

accuracy: 0.864

Semantic Role Labeling

srl-model-2018.05.25.tar.gz (697 MB)

Based on He et al, 2017

f1: 0.849

Coreference Resolution

coref-model-2018.02.05.tar.gz (56 MB)

Based on End-to-End Coreference Resolution (Lee et al, 2017)

f1: 0.630

Named Entity Recognition

ner-model-2018.04.26.tar.gz (678.9 MB)

Based on Deep contextualized word representations

f1: 0.925

fine-grained-ner-model-elmo-2018.08.31.tar.gz (691 MB)

Constituency Parsing

elmo-constituency-parser-2018.03.14.tar.gz (678 MB)

Based on Minimal Span Based Constituency Parser (Stern et al, 2017) but with ELMo embeddings

Dependency Parsing

Biaffine Parser

Based on Dozat and Manning, 2017

f1: 0.941

Semantic Parsing


wikitables-model-2018.09.14.tar.gz (5 MB)

Caveat: that this is trained on only part of the data and not officially evaluated.


Based on Event2Mind: Commonsense Inference on Events, Intents, and Reactions More information at:

$ allennlp evaluate \  \

Metrics (unigram recall):
xintent: 0.36
xreact: 0.41
oreact: 0.65


Based on Bilateral Multi-Perspective Matching for Natural Language Sentences


Based on Enhanced LSTM for Natural Language Inference and uses ELMo

You can’t perform that action at this time.