Related papers: End-to-End Autoregressive Retrieval via Bootstrapp…

Previous methods for audio-image matching generally fall into one of two categories: pipeline models or End-to-End models. Pipeline models first transcribe speech and then encode the resulting text; End-to-End models encode speech directly.…

Non-autoregressive (NAR) models simultaneously generate multiple outputs in a sequence, which significantly reduces the inference speed at the cost of accuracy drop compared to autoregressive baselines. Showing great potential for real-time…

Generative retrieval uses differentiable search indexes to directly generate relevant document identifiers in response to a query. Recent studies have highlighted the potential of a strong generative retrieval model, trained with carefully…

Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…

Pre-training and fine-tuning have achieved remarkable success in many downstream natural language processing (NLP) tasks. Recently, pre-training methods tailored for information retrieval (IR) have also been explored, and the latest success…

Reply suggestion models help users process emails and chats faster. Previous work only studies English reply suggestion. Instead, we present MRS, a multilingual reply suggestion dataset with ten languages. MRS can be used to compare two…

In many real-world settings, machine learning models and interactive systems have access to both structured knowledge, e.g., knowledge graphs or tables, and unstructured content, e.g., natural language documents. Yet, most rely on either.…

We study textual autocomplete---the task of predicting a full sentence from a partial sentence---as a human-machine communication game. Specifically, we consider three competing goals for effective communication: use as few tokens as…

This paper addresses the gap between general-purpose text embeddings and the specific demands of item retrieval tasks. We demonstrate the shortcomings of existing models in capturing the nuances necessary for zero-shot performance on item…

Evaluating retrieval-augmented generation (RAG) presents challenges, particularly for retrieval models within these systems. Traditional end-to-end evaluation methods are computationally expensive. Furthermore, evaluation of the retrieval…

Respondent-Driven Sampling (RDS) is a form of link-tracing sampling, a sampling technique used for `hard-to-reach' populations that aims to leverage individuals' social relationships to reach potential participants. While the methodological…

Dialogue systems can benefit from being able to search through a corpus of text to find information relevant to user requests, especially when encountering a request for which no manually curated response is available. The state-of-the-art…

Open domain neural dialogue models, despite their successes, are known to produce responses that lack relevance, diversity, and in many cases coherence. These shortcomings stem from the limited ability of common training objectives to…

Task-oriented dialog (TOD) systems often require interaction with an external knowledge base to retrieve necessary entity (e.g., restaurant) information to support the response generation. Most current end-to-end TOD systems either retrieve…

Understanding fine-grained links between documents is crucial for many applications, yet progress is limited by the lack of efficient methods for data curation. To address this limitation, we introduce a domain-agnostic framework for…

Conversational recommender systems have attracted immense attention recently. The most recent approaches rely on neural models trained on recorded dialogs between humans, implementing an end-to-end learning process. These systems are…

With the advancement of speech synthesis technology, users have higher expectations for the naturalness and expressiveness of synthesized speech. But previous research ignores the importance of prompt selection. This study proposes a…

Retrieval-augmented generation methods often neglect the quality of content retrieved from external knowledge bases, resulting in irrelevant information or potential misinformation that negatively affects the generation results of large…

Multi-hop question answering (QA) requires systems to iteratively retrieve evidence and reason across multiple hops. While recent RAG and agentic methods report strong results, the underlying retrieval--reasoning \emph{process} is often…

Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…