Related papers: Neural Syntactic Preordering for Controlled Paraph…

Prediction without justification has limited applicability. As a remedy, we learn to extract pieces of input text as justifications -- rationales -- that are tailored to be short and coherent, yet sufficient for making the same prediction.…

We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation. Existing approaches to this problem use recurrent structures, which not only suffer from the long-term dependency problem…

Many implicit inferences exist in text depending on how it is structured that can critically impact the text's interpretation and meaning. One such structural aspect present in text with chronology is the order of its presentation. For…

While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear what aspects of…

In this article we present a multivariate model for determining the different syntactic, semantic, and form (surface-structure) processes underlying the comprehension of simple phrases. This model is applied to EEG signals recorded during a…

While a considerable amount of semantic parsing approaches have employed RNN architectures for code generation tasks, there have been only few attempts to investigate the applicability of Transformers for this task. Including hierarchical…

Recent language models, especially those based on recurrent neural networks (RNNs), make it possible to generate natural language from a learned probability. Language generation has wide applications including machine translation,…

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the…

Current state-of-the-art models for sentiment analysis make use of word order either explicitly by pre-training on a language modeling objective or implicitly by using recurrent neural networks (RNNs) or convolutional networks (CNNs). This…

To achieve deep natural language understanding, syntactic constituent parsing plays a crucial role and is widely required by many artificial intelligence systems for processing both text and speech. A recent approach involves using standard…

This paper presents a semantic parsing approach for unrestricted texts. Semantic parsing is one of the major bottlenecks of Natural Language Understanding (NLU) systems and usually requires building expensive resources not easily portable…

Text generation is a fundamental building block in natural language processing tasks. Existing sequential models performs autoregression directly over the text sequence and have difficulty generating long sentences of complex structures.…

In recent years, neural paraphrase generation based on Seq2Seq has achieved superior performance, however, the generated paraphrase still has the problem of lack of diversity. In this paper, we focus on improving the diversity between the…

Writers, poets, singers usually do not create their compositions in just one breath. Text is revisited, adjusted, modified, rephrased, even multiple times, in order to better convey meanings, emotions and feelings that the author wants to…

We present the first sentence simplification model that learns explicit edit operations (ADD, DELETE, and KEEP) via a neural programmer-interpreter approach. Most current neural sentence simplification systems are variants of…

We inspect the multi-head self-attention in Transformer NMT encoders for three source languages, looking for patterns that could have a syntactic interpretation. In many of the attention heads, we frequently find sequences of consecutive…

Natural Language Processing (NLP) systems commonly leverage bag-of-words co-occurrence techniques to capture semantic and syntactic word relationships. The resulting word-level distributed representations often ignore morphological…

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to…

Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of…