ivulic

ivulic's Stars

• facebookresearch/MUSE

  A library for Multilingual Unsupervised or Supervised word Embeddings

  Language:Python3.2k98171552

• state-spaces/s4

  Structured state space sequence models

  Language:Jupyter Notebook2.4k52135293

• AkariAsai/self-rag

  This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

  Language:Python1.8k1782167

• JustGlowing/minisom

  :red_circle: MiniSom is a minimalistic implementation of the Self Organizing Maps

  Language:Python1.4k31141421

• PolyAI-LDN/conversational-datasets

  Large datasets for conversational AI

  Language:Python1.3k7430167

• babylonhealth/fastText_multilingual

  Multilingual word vectors in 78 languages

  Language:Jupyter Notebook1.2k550121

• princeton-nlp/LM-BFF

  [ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723

  Language:Python7162949131

• globalwordnet/english-wordnet

  The Open English WordNet

  Language:Python4692459457

• PolyAI-LDN/pheme

  Language:Python251111923

• PolyAI-LDN/task-specific-datasets

  A collection of task-specific NLU datasets

  Language:Python14512647

• ZhangXInFD/soundstorm-speechtokenizer

  Implementation of SoundStorm built upon SpeechTokenizer.

  Language:Python10361013

• cambridgeltl/xcopa

  XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning

  988112

• cambridgeltl/composable-sft

  A library for parameter-efficient and composable transfer learning for NLP with sparse fine-tunings.

  Language:Python68859

• nmrksic/attract-repel

  The Attract-Repel algorithm presented in (Mrkšić et al., TACL 2017), with accompanying resources.

  Language:Python649617

• nmrksic/LEAR

  Specialising Word Vectors for Lexical Entailment

  Language:Python28618

• ndaheim/faithful-dialogue

  23304

• ducdauge/sft-llm

  Scaling Sparse Fine-Tuning to Large Language Models

  Language:Python17231

• codogogo/towerparse

  Tower Parse: Low-Resource Dependency Parsing via Hierarchical Source Selection

  Language:Python15121

• cambridgeltl/multi3woz

  The official repository for Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems (TACL 2023)

  Language:Python14702

• cambridgeltl/e2e_tod_toolkit

  A codebase for e2e ToD toolkit.

  Language:Python11601

• ivulic/panlex-bli

  Bilingual lexicon induction (BLI) training and test sets extracted from PanLex - used in the work of Vulić et al. (EMNLP 2019)

  9100

• codogogo/instamap

  Instance-Based Mapping for Induction of Cross-Lingual Word Embedding Spaces

  Language:Python8200

• cambridgeltl/COD

  671

• ivulic/hyperlex

  HyperLex: a gold standard resource for measuring and evaluating how well semantic models capture graded or soft lexical entailment

  3100