Related papers: Dynamic Multi-Level Multi-Task Learning for Senten…

Sentence embedding is an effective feature representation for most deep learning-based NLP tasks. One prevailing line of methods is using recursive latent tree-structured networks to embed sentences with task-specific structures. However,…

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial…

Text simplification is the process of splitting and rephrasing a sentence to a sequence of sentences making it easier to read and understand while preserving the content and approximating the original meaning. Text simplification has been…

Multi-task learning has recently become a very active field in deep learning research. In contrast to learning a single task in isolation, multiple tasks are learned at the same time, thereby utilizing the training signal of related tasks…

We present a novel and effective technique for performing text coherence tasks while facilitating deeper insights into the data. Despite obtaining ever-increasing task performance, modern deep-learning approaches to NLP tasks often only…

Much effort has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) down-stream applications. However, there is still a lack of…

The Split and Rephrase (SPRP) task, which consists in splitting complex sentences into a sequence of shorter grammatical sentences, while preserving the original meaning, can facilitate the processing of complex texts for humans and…

We consider problems in sequential decision making with natural multi-level structure, where sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure has remained a…

Sentence Split and Rephrase aims to break down a complex sentence into several simple sentences with its meaning preserved. Previous studies tend to address the issue by seq2seq learning from parallel sentence pairs, which takes a complex…

Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain. Current approaches directly adapt a pre-trained language model (LM) on in-domain text before…

Recent work has explored the syntactic abilities of RNNs using the subject-verb agreement task, which diagnoses sensitivity to sentence structure. RNNs performed this task well in common cases, but faltered in complex sentences (Linzen et…

Similarity is a comparative-subjective measure that varies with the domain within which it is considered. In several NLP applications such as document classification, pattern recognition, chatbot question-answering, sentiment analysis,…

Language is highly structured, with syntactic and semantic structures, to some extent, agreed upon by speakers of the same language. With implicit or explicit awareness of such structures, humans can learn and use language efficiently and…

Multimedia applications often require concurrent solutions to multiple tasks. These tasks hold clues to each-others solutions, however as these relations can be complex this remains a rarely utilized property. When task relations are…

For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given sentences. By substituting complex words with simple…

In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the…

This work improves monolingual sentence alignment for text simplification, specifically for text in standard and simple Wikipedia. We introduce a convolutional neural network structure to model similarity between two sentences. Due to the…

We present an approach for recursively splitting and rephrasing complex English sentences into a novel semantic hierarchy of simplified sentences, with each of them presenting a more regular structure that may facilitate a wide variety of…

Purpose: Surgery scene understanding with tool-tissue interaction recognition and automatic report generation can play an important role in intra-operative guidance, decision-making and postoperative analysis in robotic surgery. However,…

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…