zhangmozhi / retrofit_clwe
Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries (ACL 2020)
☆8Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for retrofit_clwe
- Code and data accompanying our ACL 2020 paper, "Unsupervised Domain Clusters in Pretrained Language Models".☆59Updated 4 years ago
- ☆11Updated 4 years ago
- Various utility scripts useful for natural language processing, machine translation, etc.☆47Updated 2 years ago
- Code for Repl4NLP paper "A Cross-Task Analysis of Text Span Representations"☆21Updated 2 years ago
- PyTorch source code of NAACL 2021 paper "Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Tran…☆17Updated 2 years ago
- ☆27Updated last year
- Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework☆52Updated 4 years ago
- ☆57Updated last year
- Code for the paper "Factorising Meaning and Form for Intent-Preserving Paraphrasing", Tom Hosking & Mirella Lapata (ACL 2021)☆27Updated last year
- The official tool for creating proceedings for conferences of the Association for Computational Linguistics (ACL).☆41Updated 3 years ago
- Lexically constrained decoding for sequence generation using Grid Beam Search☆93Updated 6 years ago
- EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints☆29Updated 2 years ago
- ☆23Updated 4 years ago
- Implementation of the paper: Specializing pretrained word embeddings (for parsing) by IB☆52Updated 2 years ago
- UDapter is a multilingual dependency parser that uses "contextual" adapters together with language-typology features for language-specifi…☆30Updated last year
- Code and resources for evaluating cross-lingual embedding spaces☆28Updated 4 years ago
- Semantic parsers based on encoder-decoder framework☆90Updated last year
- Official code of our NAACL 2019 paper on Zero-Shot Cross-Lingual Transfer with Order Differences☆18Updated 5 years ago
- ☆11Updated 2 years ago
- Code for EMNLP2021 paper "Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training"☆20Updated 3 years ago
- Data and code for "A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization" (ACL 2020)☆47Updated last year
- Python code for training models in the ACL paper, "Beyond BLEU:Training Neural Machine Translation with Semantic Similarity".☆52Updated 4 years ago
- [EMNLP 2020] Collective HumAn OpinionS on Natural Language Inference Data☆33Updated 2 years ago
- Code for the paper "Balancing Training for Multilingual Neural Machine Translation, ACL 2020"☆23Updated 3 years ago
- PyTorch implementation of the RCSLS cross-lingual word embedding alignment method☆12Updated 5 years ago
- ☆17Updated 3 years ago
- Code base for paper "Zero-Shot Cross-Lingual Transfer with Meta Learning"☆33Updated 2 weeks ago
- SP-10K is a large-scale human-annotated selectional preference set. Five selectional preference relations are included.☆10Updated 4 years ago
- ☆20Updated 3 years ago
- ☆42Updated 3 years ago