Explore @UKPLab Open Source projects

Easy to use, state-of-the-art Neural Machine Translation for 100+ languages

13,862

EasyNMT

BiLSTM-CNN-CRF architecture for sequence tagging

1,073

emnlp2017-bilstm-cnn-crf

Hands-on tutorial on deep learning with a special focus on Natural Language Processing (NLP)

820

deeplearning4nlp-tutorial

BiLSTM-CNN-CRF architecture for sequence tagging using ELMo representations.

628

elmo-bilstm-cnn-crf

Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577

389

gpl

Context-Aware Representations for Knowledge Base Relation Extraction

310

emnlp2017-relation-extraction

Concatenated Power Mean Embeddings as Universal Cross-Lingual Sentence Representations

287

arxiv2018-xling-sentence-embeddings

Accompanying code for our COLING 2018 paper "Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering"

185

coling2018-graph-neural-networks-question-answering

Investigating Pretrained Language Models for Graph-to-Text Generation

171

plms-graph2text

MMT-Retrieval

kg2text

Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs (authors' implementation for the TACL20 paper)

acl2019-BERT-argument-classification-and-clustering

The Argument Reasoning Comprehension Task: Source codes & Datasets

argument-reasoning-comprehension-task

Pytorch-version BERT-flow: One can apply BERT-flow to any PLM within Pytorch framework.

pytorch-bertflow

Code for paper "End-to-End Non-Factoid Question Answering with an Interactive Visualization of Neural Attention Weights"

acl2017-non-factoid-qa

Accompanying code for our ACL-2017 publication on Neural End-to-End Learning for Computational Argumentation Mining

acl2017-neural_end2end_am

Accompanying code for our *SEM 2018 @ NAACL 2018 paper "Mixing Context Granularities for Improved Entity Linking on Question Answering Data across Entity Categories"

starsem2018-entity-linking

fever-2018-team-athene

Automatically detect errors in annotated corpora.

nessie

Multi-dataset stance detection and robustness experiments

mdl-stance-robustness

Code for the paper "Multi-Task Learning for Argumentation Mining in Low-Resource Settings"

naacl18-multitask_argument_mining

Code for keyphrase classification systems submitted to the SemEval 2017 shared task ScienceIE.

semeval2017-scienceie

starsem18-multimodalKB

acl2020-interactive-entity-linking

Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning

on-emergence

Heterogenous, Task- and Domain-Specific Benchmark for Unsupervised Sentence Embeddings used in the TSDAE paper: https://arxiv.org/abs/2104.06979.

useb

Accompanying code for our EMNLP 2017 publication "GraphDocExplore: A Framework for the Experimental Comparison of Graph-based Document Exploration Techniques"

emnlp2017-graphdocexplore

Structural Adapters in Pretrained Language Models for AMR-to-Text Generation (EMNLP 2021)

StructAdapt

coling2018_fake-news-challenge

Repository for the IWCS 2017 paper "Representation Learning for Answer Selection with LSTM-Based Importance Weighting"

iwcs2017-answer-selection

Controlling Argument Generation via topic, stance, and aspect

controlled-argument-generation

Code and data for ACL2016 article "Which argument is more convincing? Analyzing and predicting convincingness of Web arguments using bidirectional LSTM" by Ivan Habernal and Iryna Gurevych"

acl2016-convincing-arguments

refresh2018-predicting-trends-from-arxiv

Source code and data for Like a Good Nearest Neighbor

emnlp2018-activation-functions

Shell

lagonn

emnlp2020-debiasing-unknown

arxiv2018-bayesian-ensembles

naacl2019-does-my-rebuttal-matter

Ruby

naacl2019-like-humans-visual-attacks

A general framework for Interactive Multi-Document Summarization

acl2017-interactive_summarizer

adaptable-adapters

acl2020-confidence-regularization

E2E NLG Challenge submission

e2e-nlg-challenge-2017

Enhancing AMR-to-Text Generation with Dual Graph Representations (implementation for the EMNLP-IJCNLP-2019 paper)

emnlp2019-dualgraph

linspector

MetaQA: Combining Expert Agents for Multi-Skill Question Answering

MetaQA

aaai2019-coala-cqa-answer-selection

arxiv2023-dapr

Files for Event Nugget Detection systems submitted to TAC 2015 shared task on Event Nugget Detection

tac2015-event-detection

Event Time Extraction with a Decision Tree of Neural Classifiers

tacl2017-event-time-extraction

Implementation of a simple frame identification approach (SimpleFrameId) described in the paper "Out-of-domain FrameNet Semantic Role Labeling"

coling2018-xling_argument_mining

Erlang

eacl2017-oodFrameNetSRL

acl2020-dialogue-coherence-assessment

MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale

emnlp2020-multicqa

CARE

Project CARE

Vue

lrec2018-live-blog-corpus

EACL21-personalized-conversational-system

Source code repository for our EMNLP paper on cross-domain claim identification

emnlp2017-claim-identification

Accompanying code for our EMNLP 2018 Demo paper "Interactive Instance-based Evaluation of Knowledge Base Question Answering"

emnlp2018-question-answering-interface

Code and data for EMNLP2016 article "What makes a convincing argument? Empirical analysis and detecting attributes of convincingness in Web argumentation" by Ivan Habernal and Iryna Gurevych

emnlp2016-empirical-convincingness

Sentence Embeddings used in the GermEval-2017 Submission

germeval2017-sentiment-detection

emnlp2018-april

Code and data for NAACL 2018 article "Before Name-calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation" by Habernal et al.

naacl2018-before-name-calling-habernal-et-al

Experimental code for the paper 'Finding Convincing Arguments Using Scalable Bayesian Preference Learning'

tacl2018-preference-convincing

TeX

emnlp2017-cmapsum-corpus

Accompanying code for our EMNLP 2017 publication "Bringing Structure into Summaries: Crowdsourcing a Benchmark Corpus of Concept Maps"

TWEAC-qa-agent-selection

acl2019-GPPL-humour-metaphor

Code for "Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking" (https://arxiv.org/abs/2210.10695).

incorporating-relevance

An adaptation of MarMot morphological tagger for generic sequence-to-sequence tasks

coling2016-pcrf-seq2seq

SciGen

Files for the system submitted to the LSDSem2017 Workshop Story Cloze Test Challenge

lsdsem2017-story-cloze

Argotario: a multi-lingual serious game to tackle fallacious argumentation

acl2022-impli

argotario

Annotate text with FrameNet frames and arguments.

framenet-tools

A general framework for Multi-Document Summarization based on Genetic Algorithm and Swarm Intelligence

coling2016-genetic-swarm-MDS

emnlp2021-prompt-ft-heuristics

This repository is for the paper Metaphor Generation with Conceptual Mappings (ACL 2021).

acl2021-metaphor-generation-conceptual

Repository for the IJCNLP 2017 paper "Concept-Map-Based Multi-Document Summarization using Concept Co-Reference Resolution and Global Importance Optimization"

ijcnlp2017-cmaps

Source code, data, and supplementary materials for our ACL 2016 article

acl2016-supersense-embeddings

This repository contains the code for the EMNLP'23 paper "AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification"

AdaSent

A software for manually creating multi-document summarization corpora and a platform for developing complex annotation tasks spanning multiple steps.

mdswriter

Code associated with NLPeer: A unified resource for the study of peer review

nlpeer

Code for our optimizer which takes scored sentences and extract the best summary according to the ROUGE approximation.

acl2016-optimizing-rouge

emnlp2021-hypercoref-cdcr

📄🕸️ Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora

cdcr-beyond-corpus-tailored

Asking Clarification Questions for Code Generation in General-Purpose Programming Language

codeclarqa

thesis2018-tk_mtl_sequence_tagging

Annotations and code for the EMNLP 2018 paper 'Weeding out Conventionalized Metaphors: A Corpus of Novel Metaphor Annotations'

emnlp2018-novel-metaphors

Accompanying code for our paper "Frame- and Entity-Based Knowledge for Common-Sense Argumentative Reasoning" at the 5th Workshop on Argument Mining @ EMNLP 2018.

emnlp2018-argmin-commonsense-knowledge

acl2020-empowering-active-learning

Supplementary data for the Unshared Task at the 3rd Argument Mining workshop, ACL 2016

argmin2016-unshared-task

f1000rd

Discourse Graph Annotation Tool (DiGAT)

argmin2015-DiGAT

A general-purpose library for cross-document NLP modelling and analysis

intertext-graph

Source code and data of our paper "Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation" (https://arxiv.org/abs/2210.13865, to appear at EMNLP 2022).

emnlp2022-missing-counter-evidence

This repository includes the code for integrating contextual information for supervised text classification tasks using a dual-encoder approach and information exchange via cross-attention. You can find the paper here: https://arxiv.org/abs/2211.01874

arxiv2022-context-injection-stance

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs. arXiv 2024

arxiv2024-conditional-reasoning-llms

This repository contains code and model for EACL2023 Transformers with Learnable Activation Functions

2022-RAFT

CNN- and LSTM-based Claim Classification in Online User Comments

100

coling2016-claim-classification