cl-tohoku/PheMT

Stars
13
Rank 1,512,713 (Top 30 %)
Language
Python
Created about 4 years ago
Updated almost 4 years ago

cl-tohoku/PheMT

cl-tohoku

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

A phenomenon-wise evaluation dataset for Japanese-English machine translation robustness. The dataset is based on the MTNT dataset, with additional annotations of four linguistic phenomena; Proper Noun, Abbreviated Noun, Colloquial Expression, and Variant. COLING 2020.

bert-japanese

BERT models for Japanese text.

ILYS-aoba-chatbot

keigo_transfer_task

敬語変換タスクにおける評価用データセット

JAQKET_baseline

AIO2_DPR_baseline

https://www.nlp.ecei.tohoku.ac.jp/projects/aio/

phsic

Compute co-occurrence strength between sentences with short learning time

eval-via-selection

showcase

A PyTorch implementation of the Japanese Predicate-Argument Structure (PAS) analyser presented in the paper of Matsubayashi & Inui (2018) with some improvements.

elmo-japanese

BPersona-chat

waiting for update

Multi-VidSum

xbe

Cross-stitch bi-encoder for distantly supervised relation extraction (EMNLP 2022)

TYPIC

J-UniMorph

Dataset of UniMorph in Japanese

JAOJ

Japanese Argument Omission Judgement

AIO3_FiD_baseline

A baseline QA system for AIO3 competition utilizing Dense Passage Retrieval (DPR) and Fusion-in-Decoder (FiD)

AIO3_BPR_baseline

A baseline QA system for AIO3 competition utilizing Binary Passage Retriever (BPR)

CORD-19_phrase_embeddings

Phrase embeddings trained on the CORD-19 collection of COVID-19 research papers

aio4-bpr-baseline

AIO4_GPT_baseline

aio4-fid-baseline

第4回AI王早押し解答部門 Fusion-in-Decoder(FiD)ベースライン

LPAttack

LPAttack: A Feasible Annotation Scheme for Capturing Logic Pattern of Attacks in Arguments

trace-manipulate

scientific-paper-pros-cons

IRAC_2022

A knowledge base of domain-specific implicit reasonings in arguments via causality

quiz-datasets

QA datasets created from Japanese quiz questions.

hagi-bot