Megagon Labs

All

63 repositories

ambignlg
Public
🐶 Data for AmbigNLG: Addressing Task Ambiguity in Instruction for NLG (Ayana Niwa and Hayate Iso; EMNLP 2024)
nlp dataset nlg ambiguity llm
Python
•
Other
•0•2•0•0•Updated Oct 23, 2024Oct 23, 2024
Hallucination_MDS
Public
2•4•1•0•Updated Oct 17, 2024Oct 17, 2024
holobench
Public
🫧 Code for Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data (Maekawa*, Iso* et al.; Oct 2024)
nlp database reasoning llm long-context-modeling
Python
•
BSD 3-Clause "New" or "Revised" License
•0•4•0•0•Updated Oct 17, 2024Oct 17, 2024
Megatron-LM
Public
Ongoing research training transformer models at scale
Python
•
Other
•2.4k•0•0•0•Updated Sep 27, 2024Sep 27, 2024
TensorRT-LLM
Public
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
C++
•
Apache License 2.0
•995•0•0•0•Updated Sep 1, 2024Sep 1, 2024
starmie
Public
Resources for PVLDB 2023 submission
Python
•6•23•3•0•Updated Aug 28, 2024Aug 28, 2024
opiniondigest
Public
OpinionDigest: A Simple Framework for Opinion Summarization (ACL 2020)
Python
•
Apache License 2.0
•9•56•3•3•Updated Aug 20, 2024Aug 20, 2024
napa
Public
🍷 Code for Noisy Pairing and Partial Supervision for Stylized Opinion Summarization (Iso et al; INLG 2024)
nlp summarization noisy-data opinion-summarization inlg
Python
•0•1•0•0•Updated Aug 12, 2024Aug 12, 2024
autotemplate
Public
🧩 Code for AutoTemplate: A Simple Recipe for Lexically Constrained Text Generation (Iso; INLG 2024)
nlp summarization lexical-constraints constrained-text-generation inlg
Python
•
BSD 3-Clause "New" or "Revised" License
•0•0•0•0•Updated Aug 12, 2024Aug 12, 2024
meganno-client
Public
Python
•
BSD 3-Clause "New" or "Revised" License
•0•7•2•0•Updated Aug 2, 2024Aug 2, 2024
witqa
Public
Other
•0•5•0•0•Updated Jul 22, 2024Jul 22, 2024
CMDBench
Public
Data and Code for CMDBench experiments
Python
•
Apache License 2.0
•0•4•0•0•Updated Jun 19, 2024Jun 19, 2024
watchog
Public
The code for SIGMOD 2024 paper titled "Watchog: A Light-weight Contrastive Learning based Framework for Column Annotation"
Python
•1•3•1•0•Updated Jun 17, 2024Jun 17, 2024
meganno-service
Public
Python
•
BSD 3-Clause "New" or "Revised" License
•1•0•0•0•Updated May 22, 2024May 22, 2024
meganno-ui
Public
JavaScript
•
BSD 3-Clause "New" or "Revised" License
•0•0•0•0•Updated Apr 18, 2024Apr 18, 2024
ditto
Public
Code for the paper "Deep Entity Matching with Pre-trained Language Models"
Python
•
Apache License 2.0
•89•262•18•1•Updated Apr 17, 2024Apr 17, 2024
ginza
Public
A Japanese NLP Library using spaCy as framework based on Universal Dependencies
Python
•
MIT License
•57•757•10•2•Updated Mar 30, 2024Mar 30, 2024
MCR
Public
0•1•0•0•Updated Mar 30, 2024Mar 30, 2024
bunkai
Public
Sentence boundary disambiguation tool for Japanese texts (日本語文境界判定器)
japanese sentence-tokenizer sentence-boundary-detection python
Python
•
Apache License 2.0
•11•186•2•16•Updated Mar 26, 2024Mar 26, 2024
sato
Public
Code and data for Sato https://arxiv.org/abs/1911.06311.
Python
•
Apache License 2.0
•40•108•11•11•Updated Feb 23, 2024Feb 23, 2024
llm-longeval
Public
💵 Code for Less is More for Long Document Summary Evaluation by LLMs (Wu, Iso et al; EACL 2024)
nlp evaluation-metrics gpt-4 long-document-summarization llm nlg-evaluation eacl-2024
Python
•
BSD 3-Clause "New" or "Revised" License
•0•6•2•0•Updated Feb 22, 2024Feb 22, 2024
xatu
Public
🕊️ Code and Data for XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates (Zhang et al; LREC-COLING 2024)
nlp dataset nlg text-editing gpt-4 llm lrec-coling-2024
Python
•
BSD 3-Clause "New" or "Revised" License
•0•5•0•0•Updated Feb 20, 2024Feb 20, 2024
zett
Public
🙈 Code for Zero-shot Triplet Extraction by Template Infilling (Kim et al; IJCNLP-AACL 2023)
nlp information-extraction zero-shot-learning zero-shot-triplet-extraction ijcnlp-aacl-2023
Python
•
BSD 3-Clause "New" or "Revised" License
•0•16•2•1•Updated Feb 17, 2024Feb 17, 2024
asdc
Public
Accommodation Search Dialog Corpus (宿泊施設探索対話コーパス)
dialog corpus japanese-language
Python
•
Creative Commons Attribution 4.0 International
•2•23•0•12•Updated Jan 19, 2024Jan 19, 2024
SubjQA
Public
A question-answering dataset with a focus on subjective information
14•43•3•2•Updated Jan 8, 2024Jan 8, 2024
magneton
Public
Repository of the Magneton framework for authoring interaction-aware and customizable widgets.
TypeScript
•
Apache License 2.0
•0•4•0•0•Updated Jan 4, 2024Jan 4, 2024
pilota
Public
✈ SCUD generator (解釈文生成器)
python japanese sentence-generator
Python
•
Apache License 2.0
•0•1•0•16•Updated Nov 6, 2023Nov 6, 2023
rjdb
Public
0•0•0•0•Updated Nov 6, 2023Nov 6, 2023
vecscan
Public
Python
•
MIT License
•2•50•0•1•Updated Sep 11, 2023Sep 11, 2023
cocosum
Public
🥥 Code & Data for Comparative Opinion Summarization via Collaborative Decoding (Iso et al; Findings of ACL 2022)
text-generation natural-language-generation pretrained-language-model pytorch-lightning opinion-summarization co-decoding comparative-opinion-summarization
Python
•
Apache License 2.0
•2•21•2•0•Updated Jul 25, 2023Jul 25, 2023