Related papers: Neural-based Natural Language Generation in Dialog…
Retrieval-Augmented Generation (RAG) aims to generate more reliable and accurate responses, by augmenting large language models (LLMs) with the external vast and dynamic knowledge. Most previous work focuses on using RAG for single-round…
Automatic question generation aims to generate questions from a text passage where the generated questions can be answered by certain sub-spans of the given passage. Traditional methods mainly use rigid heuristic rules to transform a…
We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts, and we use it to directly compare…
Large language models (LLMs) have achieved strong empirical performance in various fields, benefiting from their huge amount of parameters that store knowledge. However, LLMs still suffer from several key issues, such as hallucination…
Retrieval-Augmented Generation (RAG) is widely used to augment the input to Large Language Models (LLMs) with external information, such as recent or domain-specific knowledge. Nonetheless, current models still produce closed-domain…
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge. Recently, some works have incorporated iterative knowledge accumulation processes into RAG models to progressively accumulate…
This paper investigates a new task named Conversational Question Generation (CQG) which is to generate a question based on a passage and a conversation history (i.e., previous turns of question-answer pairs). CQG is a crucial task for…
In this paper, we focus on the personalized response generation for conversational systems. Based on the sequence to sequence learning, especially the encoder-decoder framework, we propose a two-phase approach, namely initialization then…
In this thesis, we explore the use of deep neural networks for generation of natural language. Specifically, we implement two sequence-to-sequence neural variational models - variational autoencoders (VAE) and variational encoder-decoders…
Understanding, predicting, and generating object motions and transformations is a core problem in artificial intelligence. Modeling sequences of evolving images may provide better representations and models of motion and may ultimately be…
Incorporating prior knowledge like lexical constraints into the model's output to generate meaningful and coherent sentences has many applications in dialogue system, machine translation, image captioning, etc. However, existing RNN-based…
The recent application of RNN encoder-decoder models has resulted in substantial progress in fully data-driven dialogue systems, but evaluation remains a challenge. An adversarial loss could be a way to directly evaluate the extent to which…
The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integration of retrieved information. This paper proposes to bridge…
We present a framework for generating natural language description from structured data such as tables; the problem comes under the category of data-to-text natural language generation (NLG). Modern data-to-text NLG systems typically employ…
Large language models (LLMs) have exhibited remarkable few-shot learning capabilities and unified the paradigm of NLP tasks through the in-context learning (ICL) technique. Despite the success of ICL, the quality of the exemplar…
Pre-trained language models have been successfully used in response generation for open-domain dialogue. Four main frameworks have been proposed: (1) Transformer-ED using Transformer encoder and decoder separately for source and target…
Recurrent neural network grammars (RNNG) are generative models of language which jointly model syntax and surface structure by incrementally generating a syntax tree and sentence in a top-down, left-to-right order. Supervised RNNGs achieve…
State-of-the-art encoder-decoder models (e.g. for machine translation (MT) or automatic speech recognition (ASR)) are constructed and trained end-to-end as an atomic unit. No component of the model can be (re-)used without the others,…
We propose an online, end-to-end, neural generative conversational model for open-domain dialogue. It is trained using a unique combination of offline two-phase supervised learning and online human-in-the-loop active learning. While most…
Recurrent neural network grammars (RNNGs) are generative models of (tree,string) pairs that rely on neural networks to evaluate derivational choices. Parsing with them using beam search yields a variety of incremental complexity metrics…