aetting / compeval-generation-system
Sentence generation system for evaluating composition, described in Ettinger et al. (2018) "Assessing Composition in Sentence Vector Representations". Probing task datasets and classifier code available at
☆16Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for compeval-generation-system
- Diverse Natural Language Inference Collection - NLI dataset that can used to evaluate how well models perform distinct types of reasoning…☆36Updated 3 years ago
- Assessing syntactic abilities of BERT☆150Updated 5 years ago
- NAACL 2019 paper: Density Matching for Bilingual Word Embedding (Zhou et al., 2019)☆64Updated last year
- Code and data corresponding to "Hypothesis Only Baselines in Natural Language Inference" (StarSem 2018)☆27Updated last year
- Frame-Semantic and PropBank Semantic Role Labeling with Syntactic Scaffolding.☆50Updated 3 years ago
- pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference☆61Updated last year
- Parser for Abstract Meaning Representation☆45Updated 4 years ago
- Large scale sentential paraphrases collection and annotation☆47Updated last year
- Datasets for Question Answering by Search and Reading☆70Updated 6 years ago
- structured attention encoder☆13Updated 6 years ago
- Code for the paper "Extreme Adaptation for Personalized Neural Machine Translation"☆43Updated 2 years ago
- ☆44Updated 6 years ago
- Preprocessing scripts to read definitions and other information from dictionaries☆22Updated 7 years ago
- Pre-training character n-gram embeddings☆23Updated last year
- Uncovering divergent linguistic information in word embeddings with lessons for intrinsic and extrinsic evaluation☆63Updated 6 years ago
- ☆60Updated 6 years ago
- The Attract-Repel algorithm presented in (Mrkšić et al., TACL 2017), with accompanying resources.☆64Updated 7 years ago
- Code for bidirectional sequence generation (BiSon) for generating from BERT pre-trained models.☆52Updated 4 years ago
- An updated version of the Parser-v1 repo, used for Stanford's submission in the CoNLL17 shared task.☆47Updated 6 years ago
- Code for the paper "Improving Robustness of Machine Translation with Synthetic Noise"☆21Updated 4 years ago
- Companion site for "Analysis Methods in Neural Language Processing: A Survey"☆67Updated 4 years ago
- Twpipe is a pipeline toolkit that parses raw tweets into universal dependencies.☆28Updated 5 years ago
- Data and code for Kang et al., EMNLP 2019's paper titled "(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Ann…☆29Updated 4 years ago
- scripts and data for ACL 16 paper☆14Updated 8 years ago
- Text generation with entities as context☆31Updated 6 years ago
- This repository makes the integral Let's Go dataset publicly available.☆45Updated last year
- ☆28Updated 6 years ago
- NLI test set with lexical inferences☆48Updated 6 years ago
- Transition-based UCCA Parser☆72Updated 3 years ago