Related papers: Gated Group Self-Attention for Answer Selection
Memory units have been widely used to enrich the capabilities of deep networks on capturing long-term dependencies in reasoning and prediction tasks, but little investigation exists on deep generative models (DGMs) which are good at…
The recent advance in neural network architecture and training algorithms have shown the effectiveness of representation learning. The neural network-based models generate better representation than the traditional ones. They have the…
Several deep learning models have been proposed for question answering. However, due to their single-pass nature, they have no way to recover from local maxima corresponding to incorrect answers. To address this problem, we introduce the…
Session-based recommendation is a challenging problem in the real-world scenes, e.g., ecommerce, short video platforms, and music platforms, which aims to predict the next click action based on the anonymous session. Recently, graph neural…
Automatic question generation is an important technique that can improve the training of question answering, help chatbots to start or continue a conversation with humans, and provide assessment materials for educational purposes. Existing…
Retrieval augmented generation has revolutionized large language model (LLM) outputs by providing factual supports. Nevertheless, it struggles to capture all the necessary knowledge for complex reasoning questions. Existing retrieval…
We introduce a novel task, Video Question Generation (Video QG). A Video QG model automatically generates questions given a video clip and its corresponding dialogues. Video QG requires a range of skills -- sentence comprehension, temporal…
Transformers excel across a large variety of tasks but remain susceptible to corrupted inputs, since standard self-attention treats all query-key interactions uniformly. Inspired by lateral inhibition in biological neural circuits and…
We implement a method for re-ranking top-10 results of a state-of-the-art question answering (QA) system. The goal of our re-ranking approach is to improve the answer selection given the user question and the top-10 candidates. We focus on…
This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending…
Question Generation is the task of automatically creating questions from textual input. In this work we present a new Attentional Encoder--Decoder Recurrent Neural Network model for automatic question generation. Our model incorporates…
In multi-turn dialogue generation, response is usually related with only a few contexts. Therefore, an ideal model should be able to detect these relevant contexts and produce a suitable response accordingly. However, the widely used…
The RepEval 2017 Shared Task aims to evaluate natural language understanding models for sentence representation, in which a sentence is represented as a fixed-length vector with neural networks and the quality of the representation is…
Knowledge selection is the key in knowledge-grounded dialogues (KGD), which aims to select an appropriate knowledge snippet to be used in the utterance based on dialogue history. Previous studies mainly employ the classification approach to…
Interactive search can provide a better experience by incorporating interaction feedback from the users. This can significantly improve search accuracy as it helps avoid irrelevant information and captures the users' search intents.…
Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, summary-centric questions and length-constrained,…
Scene text recognition has been a hot topic in computer vision. Recent methods adopt the attention mechanism for sequence prediction which achieve convincing results. However, we argue that the existing attention mechanism faces the problem…
Goal-driven selective attention (GDSA) is a remarkable function that allows the complex dynamical networks of the brain to support coherent perception and cognition. Part I of this two-part paper proposes a new control-theoretic framework,…
Attention modules connecting encoder and decoders have been widely applied in the field of object recognition, image captioning, visual question answering and neural machine translation, and significantly improves the performance. In this…
The open-ended Visual Question Answering (VQA) task requires AI models to jointly reason over visual and natural language inputs using world knowledge. Recently, pre-trained Language Models (PLM) such as GPT-3 have been applied to the task…