ng-j-p / rouge-we
ROUGE summarization evaluation metric, enhanced with use of Word Embeddings
☆22Updated 6 years ago
Related projects ⓘ
Alternatives and complementary repositories for rouge-we
- Frame-Semantic and PropBank Semantic Role Labeling with Syntactic Scaffolding.☆50Updated 3 years ago
- Uncovering divergent linguistic information in word embeddings with lessons for intrinsic and extrinsic evaluation☆63Updated 6 years ago
- Diverse Natural Language Inference Collection - NLI dataset that can used to evaluate how well models perform distinct types of reasoning…☆36Updated 3 years ago
- Code to compute topic coherence for several topic cardinalities and aggregate scores across them☆22Updated last year
- Large scale sentential paraphrases collection and annotation☆47Updated last year
- Code for the paper "Extreme Adaptation for Personalized Neural Machine Translation"☆43Updated 2 years ago
- data and scripts for the shared task "Task 1: Paraphrase and Semantic Similarity in Twitter (PIT)" at SemEval 2015☆44Updated 3 years ago
- Zero-Shot Open Entity Typing as Type-Compatible Grounding, EMNLP'18.☆43Updated 4 years ago
- MT/IE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models☆22Updated 6 years ago
- Datasets for Question Answering by Search and Reading☆70Updated 6 years ago
- ☆44Updated 6 years ago
- Summarization datasets from the New York Times Annotated Corpus☆47Updated 4 years ago
- Modified BLEU score. Uses word2vec similarity instead of one to one similarity.☆7Updated 6 years ago
- pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference☆61Updated last year
- Preprocessing scripts to read definitions and other information from dictionaries☆22Updated 7 years ago
- COLING 2018 Tutorial on Multilingual FrameNet: Automatic semantic role labeling for FrameNet☆25Updated 6 years ago
- ☆27Updated 6 years ago
- ☆10Updated 7 years ago
- This repository contains the code for the Form-Context Model and its Attentive Mimicking variant.☆31Updated 4 years ago
- Code and data related to "Efficient, Compositional, Order-Sensitive n-gram Embeddings" (EACL 2017)☆14Updated 7 years ago
- Twpipe is a pipeline toolkit that parses raw tweets into universal dependencies.☆28Updated 5 years ago
- AMR-to-Text Generator with Side Information☆24Updated 3 years ago
- Word Sense Induction with neural Bi-language Models and symmetric patterns☆12Updated 6 years ago
- Text generation with entities as context☆31Updated 6 years ago
- TextGraphs-13 Shared Task on Multi-Hop Inference Explanation Regeneration☆44Updated 4 years ago
- Parser for Abstract Meaning Representation☆45Updated 4 years ago
- Auxiliary GAN for WE post-specialisation☆23Updated 5 years ago
- ☆25Updated last year
- Code for bidirectional sequence generation (BiSon) for generating from BERT pre-trained models.☆52Updated 4 years ago