相关论文: A Document-grounded Matching Network for Response …

Multi-document grounded dialogue systems (DGDS) belong to a class of conversational agents that answer users' requests by finding supporting knowledge from a collection of documents. Most previous studies aim to improve the knowledge…

Panoramic Narrative Grounding (PNG) is an emerging visual grounding task that aims to segment visual objects in images based on dense narrative captions. The current state-of-the-art methods first refine the representation of phrase by…

How decisions are being made is of utmost importance within organizations. The explicit representation of business logic facilitates identifying and adopting the criteria needed to make a particular decision and drives initiatives to…

Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue…

Document-grounded dialogue (DGD) uses documents as external knowledge for dialogue generation. Correctly understanding the dialogue context is crucial for selecting knowledge from the document and generating proper responses. In this paper,…

Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representation and ignore…

Conversational grounding is a collaborative mechanism for establishing mutual knowledge among participants engaged in a dialogue. This experimental study analyzes information-seeking conversations to investigate the capabilities of large…

Image-text matching has received growing interest since it bridges vision and language. The key challenge lies in how to learn correspondence between image and text. Existing works learn coarse correspondence based on object co-occurrence…

Knowledge models are fundamental to dialogue systems for enabling conversational interactions, which require handling domain-specific knowledge. Ensuring effective communication in information-providing conversations entails aligning user…

We consider incorporating topic information into message-response matching to boost responses with rich content in retrieval-based chatbots. To this end, we propose a topic-aware convolutional neural tensor network (TACNTN). In TACNTN,…

Text response generation for multimodal task-oriented dialog systems, which aims to generate the proper text response given the multimodal context, is an essential yet challenging task. Although existing efforts have achieved compelling…

Large language models (LLMs) such as ChatGPT can produce coherent, cohesive, relevant, and fluent answers for various natural language processing (NLP) tasks. Taking document-level machine translation (MT) as a testbed, this paper provides…

Recent advances in reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text. However, complex Question Answering (QA) typically requires multi-hop…

Compared to sentence-level systems, document-level neural machine translation (NMT) models produce a more consistent output across a document and are able to better resolve ambiguities within the input. There are many works on…

We investigate response selection for multi-turn conversation in retrieval-based chatbots. Existing studies pay more attention to the matching between utterances and responses by calculating the matching score based on learned features,…

Models such as latent semantic analysis and those based on neural embeddings learn distributed representations of text, and match the query against the document in the latent semantic space. In traditional information retrieval models, on…

Retrieval-augmented generation (RAG) systems have been widely adopted in contemporary large language models (LLMs) due to their ability to improve generation quality while reducing the required input context length. In this work, we focus…

Large language models (LLMs) have an impressive ability to draw on novel information supplied in their context. Yet the mechanisms underlying this contextual grounding remain unknown, especially in situations where contextual information…

Semantic matching, which aims to determine the matching degree between two texts, is a fundamental problem for many NLP applications. Recently, deep learning approach has been applied to this problem and significant improvements have been…

Intelligent personal assistant systems with either text-based or voice-based conversational interfaces are becoming increasingly popular around the world. Retrieval-based conversation models have the advantages of returning fluent and…