Lexical simplification (LS) aims at replacing words considered complex in a sentence by simpler equivalents. In this paper, we present the first automatic LS service for French, FrenLys, which offers different techniques to generate, select and rank
substitutes. The paper describes the different methods proposed by our tool, which includes both classical approaches (e.g. generation of candidates from lexical resources, frequency filter, etc.) and more innovative approaches such as the exploitation of CamemBERT, a model for French based on the RoBERTa architecture. To evaluate the different methods, a new evaluation dataset for French is introduced.
Natural language inference is a method of finding inferences in language texts. Understanding the meaning of a sentence and its inference is essential in many language processing applications. In this context, we consider the inference problem for a
Dravidian language, Malayalam. Siamese networks train the text hypothesis pairs with word embeddings and language agnostic embeddings, and the results are evaluated against classification metrics for binary classification into entailment and contradiction classes. XLM-R embeddings based Siamese architecture using gated recurrent units and bidirectional long short term memory networks provide promising results for this classification problem.
In our work, we chose to follow semantic transfer based approach. Our approach consists of two main phases. The first phase, Natural Language Analysis phase, aims to analyze the text and extract the required knowledge from it. In addition to the synt
actic analysis results, one of the main outputs for this phase is a concept map which summarize the concepts of the related domain and the relationships between these concepts.
