Freda Shi's Projects
High-accuracy NLP parser with models for 11 languages.
A python tool for evaluating the quality of sentence embeddings.
Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)
An open-source implementation of the paper ``A Structured Self-Attentive Sentence Embedding'' (Lin et al., ICLR 2017).
[ACL 2021 Findings] Subtree/subsequence substitution as data augmentation
NAACL 2021: Are NLP Models really able to Solve Simple Math Word Problems?
An efficient toolkit for syntactic evaluation (Marvin and Linzen, EMNLP 2018; Gulordava et al., NAACL 2018).
Text-to-LogicForm is a simple code for leveraging a syntactic graph for semantic parsing using a nov
[EMNLP 2018] On Tree-Based Neural Sentence Modeling.
Code implementation of our paper in LREC 2018, Constructing High Quality Sense-specific Corpus and Word Embedding via Unsupervised Elimination of Pseudo Multi-sense
A framework to learn cross-lingual word embedding mappings
[ACL 2019] Visually Grounded Neural Syntax Acquisition
[COLING 2018] Learning Visually-Grounded Semantics from Contrastive Adversarial Samples.