Diverse Natural Language Inference Collection - NLI dataset that can used to evaluate how well models perform distinct types of reasoning (EMNLP 2018)

Organized inventory of research using the Abstract Meaning Representation

A neural-symbolic joint reasoning approach for Natural Language Inference (NLI). Modeling NLI as inference path planning through a search engine. Sequence chunking and neural paraphrase detection for syntactic variation. SOTA result on SICK and MED.

Universal Dependency polarization for monotonicity based natural language inference

Study on stereotype transfer accross Multilingual Language Models for English, Spanish, French, Greek and Croatian. The emotion profiles for different social groups are obtained from pre-trained XLM-RoBERTa and fine-tuned versions of it.

Modeling plurals, mass terms of fragment of English in Haskell

Linguistic-knowledge-aware Neuro-symbolic Model for Entity State Tracking

Computational Semantics and Pragmatics

Sense clusterings of FinnWordNet

Evaluation (and some implementations/adaptations) of WSD systems for Finnish

A new evaluation mechanism and a learning strategy for de-biased and interpretable NLI models. Models co-learn sentence classification and evidence retrieval for the classification.

Implementation of different Sentence Encoders trained on Natural Language Inference and evaluated on unseen tasks through Meta's SentEval framework.