Repositories list

• Induct-Learn

  Public
  Jupyter Notebook

  •0•0•0•0•Updated Oct 2, 2024Oct 2, 2024

• ConvLogRecaller-dataset

  Public
  ConvLogRecaller-dataset

  0•0•0•0•Updated Apr 12, 2024Apr 12, 2024

• Self-ICL

  Public
  Python

  •1•2•1•0•Updated Dec 3, 2023Dec 3, 2023

• FECS

  Public
  Python

  •0•6•0•0•Updated Nov 28, 2023Nov 28, 2023

• ZARA

  Public
  0•1•1•0•Updated Nov 5, 2023Nov 5, 2023

• contrastive-debate-representation

  Public
  Contrastively learning participant representations per round in thread-based debates.

  Python

  •0•2•0•0•Updated Oct 25, 2023Oct 25, 2023

• ContributionSum

  Public
  The ContributionSum Dataset

  GNU General Public License v3.0

  •0•1•0•0•Updated Aug 14, 2023Aug 14, 2023

• Citation-Intent-Classification-Evidence-Extraction-

  Public
  Citation Intent Classification and Its Supporting Evidence Extraction for Citation Graph Construction

  0•1•1•0•Updated Aug 13, 2023Aug 13, 2023

• AMDRD

  Public
  Analysis Model of Discourse Relations within a Document(AMDRD)

  Python

  •

  GNU General Public License v3.0

  •1•2•0•0•Updated Aug 11, 2023Aug 11, 2023

• LifeEventDialog

  Public
  Life Event Dialog contains fine-grained personal life event annotations on DailyDialog.

  0•8•0•0•Updated May 2, 2023May 2, 2023

• NTUNLP-ImageGallery

  Public
  提供台大AI中心共享平台圖片。

  Apache License 2.0

  •0•0•0•0•Updated Apr 29, 2023Apr 29, 2023

• traditional-chinese-alpaca

  Public
  A Traditional-Chinese instruction-following model with datasets based on Alpaca.

  Python

  •

  Apache License 2.0

  •18•133•2•0•Updated Mar 28, 2023Mar 28, 2023

• C2RC2

  Public
  Categorizing Citation Relations in Scientific Papers Based on the Contributions of Cited Papers

  MIT License

  •0•2•0•0•Updated Nov 21, 2022Nov 21, 2022

• Lifelog-SentiLiveKB-Dataset

  Public
  0•0•0•0•Updated Nov 14, 2022Nov 14, 2022

• Lifelog-FPImgCapHRC

  Public
  0•0•0•0•Updated Nov 3, 2022Nov 3, 2022

• tw-eH

  Public
  Learning to Generate Explanation from e-Hospital Services for Medical Suggestion

  Python

  •

  MIT License

  •0•3•0•0•Updated Nov 3, 2022Nov 3, 2022

• Lifelog-PKBQAC2.0-Dataset

  Public
  0•0•0•0•Updated Oct 17, 2022Oct 17, 2022

• ICDA

  Public
  Interactive Clinical Diagnostic Assistant for Medical Interview

  Python

  •0•2•0•0•Updated Sep 7, 2022Sep 7, 2022

• SEEN

  Public
  SEEN: Structured Event Enhancement Network for Explainable Need Detection of Information Recall Assistance

  natural-language-processinglanguage-modelpersonal-knowledge-base+ 3lifeloggraph-neural-networksinformation-recall

  Python

  •

  MIT License

  •0•3•0•0•Updated Aug 21, 2022Aug 21, 2022

• PRRCA

  Public
  Peer Review and Rebuttal Counter-Arguments Dataset

  0•1•0•0•Updated Aug 13, 2022Aug 13, 2022

• NTUSD

  Public
  Sentiment words are employed to compute the tendency of a sentence, and then a document. To detect sentiment words in Chinese documents, a Chinese sentiment dictionary is indispensable. However, a small dictionary may suffer from the problem of coverage. A method to learn sentiment words and their strengths from multiple resources is developed i…

  MIT License

  •2•7•0•0•Updated Jun 20, 2022Jun 20, 2022

• Dialogue-MPDD

  Public
  A dialogue dataset is an indispensable resource for building a dialogue system. Additional information like emotions and interpersonal relationships labeled on conversations enables the system to capture the emotion flow of the participants in the dialogue. However, there is no publicly available Chinese dialogue dataset with emotion and relatio…

  0•4•0•0•Updated Jun 1, 2022Jun 1, 2022

• WSD-MSD-1030

  Public
  A word similarity dataset with high proportion of multi-sense words that is designed to facilitate more reliable evaluations of sense embeddings.

  0•2•0•0•Updated Jun 1, 2022Jun 1, 2022

• Finance-FinNum

  Public
  Numeral is the crucial part of financial documents. In order to understand the detail of opinions in financial documents, we should not only analyze the text, but also need to assay the numeric information in depth. Because of the informal writing style, analyzing social media data is more challenging than analyzing news and official documents. …

  1•3•0•0•Updated Jun 1, 2022Jun 1, 2022

• Finance-FinProLex

  Public
  FinProLex provides 5,162 tokens in professional analysts' reports and the financial social media platform posts with expert-like scores. The expert-like scores are calculated based on the pointwise mutual information (PMI).

  1•4•0•0•Updated Jun 1, 2022Jun 1, 2022

• Finance-Numeracy-600K

  Public
  Numeral is the crucial part of in narrative, especially in financial documents. We should not only analyze the text, but also need to assay the numeric information in depth. Numeracy-600K is a dataset for testing the numeracy of machines.

  1•3•0•0•Updated Jun 1, 2022Jun 1, 2022

• Finance-NTUSD-Fin

  Public
  NTUSD-Fin provides various scoring methods including frequency, CFIDF, chi-squared value, market sentiment score and word vector for the tokens. Only the tokens appeared at least ten times and shown significantly difference between expected and observed frequency with chi-squared test are remained in our dictionary. The predetermined significanc…

  2•4•1•0•Updated Jun 1, 2022Jun 1, 2022

• NTU-English-Tense-Predictor

  Public
  A rule-based English tense predictor based on the output of the dependency parser like Stanford CoreNLP.

  Python

  •0•2•0•0•Updated Jun 1, 2022Jun 1, 2022

• Chinese-Word-Ordering-Errors-Detection-and-Correction-Corpus

  Public
  Word Ordering Errors (WOEs) are the most frequent type of grammatical errors at sentence level for non-native Chinese language learners. Learners taking Chinese as a foreign language often place character(s) in the wrong places in sentences, and that results in wrong word(s) or ungrammatical sentences. Besides, there are no clear word boundaries…

  0•4•0•0•Updated Jun 1, 2022Jun 1, 2022

• NTU-Irony-Corpus

  Public
  The NTU Irony Corpus consists of more than 1,000 microblog messages collected from the Plurk website. All the messages in the corpus are in Traditional Chinese and have been confirmed to be ironic. They are marked with three types of labels: (1) ironic word/phrase , (2) context, and (3) rhetoric element.

  0•4•0•0•Updated Jun 1, 2022Jun 1, 2022