WING-NUS/Kairos

Stars
18
Rank 1,208,065 (Top 24 %)
Language
Java
License
Apache License 2.0
Created about 14 years ago
Updated almost 14 years ago

WING-NUS/Kairos

WING-NUS

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Kairos, combines a focused crawler and an information extraction engine, to convert a list of conference websites into a index filled with fields of metadata that correspond to individual papers. Using event date metadata extracted from the conference website, Kairos proactively harvests metadata about the individual papers soon after they are made public. We use a Maximum Entropy classifier to classify uniform resource locators (URLs) as scientific conference websites and use Conditional Random Fields (CRF) to extract individual paper metadata from such websites. The crawler is built on top of the popular open-source crawler Nutch.

scisumm-corpus

Scientific Document Summarization Corpus and Annotations from the WING NUS group.

sequicity

Source code for the ACL 2018 paper entitled "Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures" by Wenqiang Lei et al.

JD2Skills-BERT-XMLC

Code and Dataset for the Bhola et al. (2020) Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework

SWING

The Summarizer from the Web IR / NLP Group (WING), hence SWING, is a modular, state-of-the-art automatic extractive text summarization system. It is used as the basis for summarization research at the National University of Singapore. It performs as one of the leading automatic summarization systems in the international TAC competition, getting high marks for the ROUGE evaluation measure

cs6101

The Web IR / NLP Group (WING)'s public reading group at the National University of Singapore.

slsql

Code for the EMNLP 2020 paper "Re-examining the Role of Schema Linking in Text-to-SQL".

SciAssist

SSID

Student Submission Integrity Diagnosis

Prastava

100% Pure Ruby Recommendation System (CF/CBF/Hybrid)

ELCo

The Dataset and Official Implementation for <The ELCo Dataset: Bridging Emoji and Lexical Composition> @ LREC-COLING 2024

JavaRAP

JavaRAP is an implementation of the classic Resolution of Anaphora Procedure (RAP) given by Lappin and Leass (1994) . It resolves third person pronouns, lexical anaphors, and identifies pleonastic pronouns. The original purpose of the implementation is to provide anaphora resolution result to our TREC 2003 Q&A system.

ResearchTrends

Source code for the COLING 2018 paper entitled "Identifying Emergent Research Trends by Key Authors and Phrases" by Shenhao Jiang et al.

RelatedWorkSummarizationDataset

Dataset for the paper: Cong Duy Vu Hoang and Min-Yen Kan (2010) Towards Automated Related Work Summarization. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), Beijing, China. pp. 427-435.

RAZ

Robust Argumentative Zoning - This is the home page for the argumentative zoning for raw text project, a collaboration between NUS and the University of Cambridge. This work follows Teufel's thesis to zone (label) sentences with six different rhetorical functions for scholarly discoure. The download comes with Teufel's original analysis and markup of 80 cmp-lg articles.

ChairVisE

ir-seminar

The Web IR / NLP Group (WING)'s IR Seminar at the National University of Singapore.

discoling

Source code for the AAAI 2018 paper entitled "Linguistic Properties Matter for Implicit Discourse Relation Recognition: Combining Semantic Interaction, Topic Continuity and Attribution" by Wenqiang Lei et al.

texWordCount

A perl script to help count words in LaTeX. LPGL.

SciSWING

Scientific Document Summarizer from the Web IR / NLP Group (WING), NUS

chatongpt

Chat on GPT public event - 18 April 2023

PyTorchCRF

A work-in-progress repository to develop a stand-alone lightweight CRF Layer in Pytorch

nlp-seminar

The Web IR / NLP Group (WING)'s NLP Seminar at the National University of Singapore.

RSScrawler-1

WING-LDA

LDA group project

FCKeyphrase

SciVerse Application for document keyphrase extraction

Word-News-Android

Word News Android client

WordNews

WordNews Chinese/English Language Learning system with Chrome Extension and Android backends.

search-engine-wrapper

This package provides a Java wrapper framework for unifying programmatic access to search engines. A convenience class is also included for downloading the files at the URLs in the search engine results. This package contains an API as well as a command-line application.

cubit

Google Scholar Analytics Package (Server backend and embeddable Javascript)

SSNLP-2019

Static Jekyll Website for the Singapore Symposium on Natural Language Processing.

ACL-Anthology-Codebase

Script and code for running the older version of the ACL Anthology

PDTB-scorer

domadapter

Elsevier-KP

Keyphrase Extraction (Base version for Elsevier; Elsevier-KP). Link below not working yet.

NeuralQuestionGeneration

WING-NUS (Pan Liangming's) Re-implementation of Serban et al's. 2016 ACL work "Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus"

DICOMER

DIscourse COherence Model for Evaluating Readability. DICOMER is a package for evaluating the coherence of text using discourse matrix representation, augmented with discourse hierarchy structure. Part of the deliverables from Lin et al.'s 2012 ACL paper entitled "Combining Coherence Models and Machine Translation Evaluation Metrics for Summarization Evaluation".

TESLA-S

TESLA-S: Evaluating Summary Content. Adaptation of the popular TESLA evaluation metric for summarization content evaluation. Part of the deliverables from Lin et al.'s 2012 ACL paper entitled "Combining Coherence Models and Machine Translation Evaluation Metrics for Summarization Evaluation".

ETD-Parsing

Repository for shared project for electronic theses and dissertation parsing collaboration between Virginia Tech, Old Dominion University and National University of Singapore.