Related papers: Retrieve and Refine: Improved Sequence Generation …

Retrieval-augmented generation (RAG) for language models significantly improves language understanding systems. The basic retrieval-then-read pipeline of response generation has evolved into a more extended process due to the integration of…

Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address these issues by identifying and penalizing undesirable…

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…

Maintaining a consistent personality in conversations is quite natural for human beings, but is still a non-trivial task for machines. The persona-based dialogue generation task is thus introduced to tackle the personality-inconsistent…

Evaluating generative models, such as large language models (LLMs), commonly involves question-answering tasks where the final answer is selected based on probability of answer choices. On the other hand, for models requiring reasoning, the…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training gap where…

This work combines information about the dialogue history encoded by pre-trained model with a meaning representation of the current system utterance to realize contextual language generation in task-oriented dialogues. We utilize the…

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…

Neural generative models have become popular and achieved promising performance on short-text conversation tasks. They are generally trained to build a 1-to-1 mapping from the input post to its output response. However, a given post is…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

Responses in task-oriented dialogue systems often realize multiple propositions whose ultimate form depends on the use of sentence planning and discourse structuring operations. For example a recommendation may consist of an explicitly…

Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively…

A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative…

In this paper, we focus on methods to reduce the size and improve the quality of the prompt context required for question-answering systems. Attempts to increase the number of retrieved chunked documents and thereby enlarge the context…

Using neural networks to generate replies in human-computer dialogue systems is attracting increasing attention over the past few years. However, the performance is not satisfactory: the neural network tends to generate safe, universally…

Many text generation systems benefit from using a retriever to retrieve passages from a textual knowledge corpus (e.g., Wikipedia) which are then provided as additional context to the generator. For open-ended generation tasks (like…

Recently, utilizing deep neural networks to build the opendomain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to…

Current approaches for controlling dialogue response generation are primarily focused on high-level attributes like style, sentiment, or topic. In this work, we focus on constrained long-term dialogue generation, which involves more…

We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single…

Constructing responses in task-oriented dialogue systems typically relies on information sources such the current dialogue state or external databases. This paper presents a novel approach to knowledge-grounded response generation that…