Related papers: CONVERSER: Few-Shot Conversational Dense Retrieval…
Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence…
Recent dense retrievers increasingly leverage the robust text understanding capabilities of Large Language Models (LLMs), encoding queries and documents into a shared embedding space for effective retrieval. However, most existing methods…
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we…
Data is stored in both structured and unstructured form. Querying both, to power natural language conversations, is a challenge. This paper introduces dIR, Discrete Information Retrieval, providing a unified interface to query both free…
Smooth and effective communication requires the ability to perform latent or explicit commonsense inference. Prior commonsense reasoning benchmarks (such as SocialIQA and CommonsenseQA) mainly focus on the discriminative task of choosing…
Composed image retrieval (CIR) is the task of retrieving a target image specified by a query image and a relative text that describes a semantic modification to the query image. Existing methods in CIR struggle to accurately represent the…
Recent studies have demonstrated that the ability of dense retrieval models to generalize to target domains with different distributions is limited, which contrasts with the results obtained with interaction-based models. Prior attempts to…
Deploying conversational voice agents with large language models faces a critical challenge: cloud-based foundation models provide deep reasoning and domain knowledge but introduce latency that disrupts natural conversation, while on-device…
A retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Retrievers have been introduced in knowledge-grounded dialog systems to…
Current neural network-based conversational models lack diversity and generate boring responses to open-ended utterances. Priors such as persona, emotion, or topic provide additional information to dialog models to aid response generation,…
Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios. Contrastive pre-training, which constructs pseudo-positive examples from unlabeled data, has shown great…
Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user's queries in natural language. From classic retrieval methods to learning-based ranking…
Information retrieval involves selecting artifacts from a corpus that are most relevant to a given search query. The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and…
A judicious combination of dictionary learning methods, block sparsity and source recovery algorithm are used in a hierarchical manner to identify the noises and the speakers from a noisy conversation between two people. Conversations are…
We extend the task of composed image retrieval, where an input query consists of an image and short textual description of how to modify the image. Existing methods have only been applied to non-complex images within narrow domains, such as…
Conversational Information Retrieval (CIR) is an emerging field of Information Retrieval (IR) at the intersection of interactive IR and dialogue systems for open domain information needs. In order to optimize these interactions and enhance…
We study learning of a matching model for response selection in retrieval-based dialogue systems. The problem is equally important with designing the architecture of a model, but is less explored in existing literature. To learn a robust…
Rapid response, namely low latency, is fundamental in search applications; it is particularly so in interactive search sessions, such as those encountered in conversational settings. An observation with a potential to reduce latency asserts…
We propose RaDeR, a set of reasoning-based dense retrieval models trained with data derived from mathematical problem solving using large language models (LLMs). Our method leverages retrieval-augmented reasoning trajectories of an LLM and…
Attention mechanisms that confer selective focus on a strict subset of input elements are nearly ubiquitous in language models today. We posit there to be downside to the use of attention: most input information is lost. In support of this…