Related papers: Multimodal Attention Branch Network for Perspectiv…

This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the embedding, with each row of the matrix attending on a…

Multimedia or spoken content presents more attractive information than plain text content, but the former is more difficult to display on a screen and be selected by a user. As a result, accessing large collections of the former is much…

Introducing attentional mechanism in neural network is a powerful concept, and has achieved impressive results in many natural language processing tasks. However, most of the existing models impose attentional distribution on a flat…

We present BERTGEN, a novel generative, decoder-only model which extends BERT by fusing multimodal and multilingual pretrained models VL-BERT and M-BERT, respectively. BERTGEN is auto-regressively trained for language generation tasks,…

Aspect-based sentiment classification is a crucial problem in fine-grained sentiment analysis, which aims to predict the sentiment polarity of the given aspect according to its context. Previous works have made remarkable progress in…

We present an approach that exploits hierarchical Recurrent Neural Networks (RNNs) to tackle the video captioning problem, i.e., generating one or multiple sentences to describe a realistic video. Our hierarchical framework contains a…

A major obstacle in reinforcement learning-based sentence generation is the large action space whose size is equal to the vocabulary size of the target-side language. To improve the efficiency of reinforcement learning, we present a novel…

Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation. Despite the success in modeling intra-sentence coherence, existing generation models…

Distributed representation plays an important role in deep learning based natural language processing. However, the representation of a sentence often varies in different tasks, which is usually learned from scratch and suffers from the…

The task of Natural Language Inference (NLI) is widely modeled as supervised sentence pair classification. While there has been a lot of work recently on generating explanations of the predictions of classifiers on a single piece of text,…

This paper details the implementation of an algorithm for automatically generating a high-level knowledge network to perform commonsense reasoning, specifically with the application of robotic task repair. The network is represented using a…

A natural image usually conveys rich semantic content and can be viewed from different angles. Existing image description methods are largely restricted by small sets of biased visual paragraph annotations, and fail to cover rich underlying…

This paper presents a framework towards prompting multi-robot teams with high-level tasks using natural language expressions. Our objective is to use the reasoning capabilities demonstrated by recent language models in understanding and…

This paper explores the task of answer-aware questions generation. Based on the attention-based pointer generator model, we propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical…

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly…

This paper demonstrates a task to finetune a BART model so it can construct a sentence from an arbitrary set of words, which used to be a difficult NLP task. The training task is making sentences with four words, but the trained model can…

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.…

The self-attention mechanism has significantly advanced the field of natural language processing, facilitating the development of advanced language-learning machines. Although its utility is widely acknowledged, the precise mechanisms of…

In reading comprehension, generating sentence-level distractors is a significant task, which requires a deep understanding of the article and question. The traditional entity-centered methods can only generate word-level or phrase-level…

Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions cannot be explained as those of decision trees. In many…