Related papers: Continuous Decomposition of Granularity for Neural…

In this paper, we propose Neural Phrase-to-Phrase Machine Translation (NP$^2$MT). Our model uses a phrase attention mechanism to discover relevant input (source) segments that are used by a decoder to generate output (target) phrases. We…

Neural architectures are the foundation for improving performance of deep neural networks (DNNs). This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs. The proposed…

Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification. However, challenges still exist in adapting GCN on learning discriminative…

Domain-general semantic parsing is a long-standing goal in natural language processing, where the semantic parser is capable of robustly parsing sentences from domains outside of which it was trained. Current approaches largely rely on…

Compositional generalization is a basic mechanism in human language learning, but current neural networks lack such ability. In this paper, we conduct fundamental research for encoding compositionality in neural networks. Conventional…

Paraphrase generation is a long-standing task in natural language processing (NLP). Supervised paraphrase generation models, which rely on human-annotated paraphrase pairs, are cost-inefficient and hard to scale up. On the other hand,…

The Knowledge Graph-to-Text Generation task aims to convert structured knowledge graphs into coherent and human-readable natural language text. Recent efforts in this field have focused on enhancing pre-trained language models (PLMs) by…

Two crucial issues for text summarization to generate faithful summaries are to make use of knowledge beyond text and to make use of cross-sentence relations in text. Intuitive ways for the two issues are Knowledge Graph (KG) and Graph…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We propose an end-to-end…

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neural network as an encoder to map an input sentence into a…

Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…

Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents…

Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages. Inspired by the notion of working memory, we propose a new Transformer variant named RegularGPT. With its novel combination of…

Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…

Recent years have seen a proliferation of attention mechanisms and the rise of Transformers in Natural Language Generation (NLG). Previously, state-of-the-art NLG architectures such as RNN and LSTM ran into vanishing gradient problems; as…

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…

Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall…

Graph Neural Networks (GNNs) are gaining extensive attention for their application in graph data. However, the black-box nature of GNNs prevents users from understanding and trusting the models, thus hampering their applicability. Whereas…

Neural Processes (NPs) are a rapidly evolving class of models designed to directly model the posterior predictive distribution of stochastic processes. Originally developed as a scalable alternative to Gaussian Processes (GPs), which are…