相关论文: Bridging the Gap: From Ad-hoc to Proactive Search …
Real-world dialogue usually unfolds as an infinite stream. It thus requires bounded-state memory mechanisms to operate within an infinite horizon. However, existing read-then-think memory is fundamentally misaligned with this setting, as it…
Large Language Model (LLM)-driven conversational search is shifting information retrieval from reactive keyword matching to proactive, open-ended dialogues. In this context, Conversation Starters are widely deployed to provide personalized…
The development of largely human-annotated benchmarks has driven the success of deep neural networks in various NLP tasks. To enhance the effectiveness of existing benchmarks, collecting new additional input-output pairs is often too costly…
Recent research has shown that mixed-initiative conversational search, based on the interaction between users and computers to clarify and improve a query, provides enormous advantages. Nonetheless, incorporating additional information…
Conversational search provides a natural interface for information retrieval (IR). Recent approaches have demonstrated promising results in applying dense retrieval to conversational IR. However, training dense retrievers requires large…
Conversational text-to-speech (TTS) aims to synthesize speech with proper prosody of reply based on the historical conversation. However, it is still a challenge to comprehensively model the conversation, and a majority of conversational…
Long-horizon personalization requires dialogue assistants to retrieve user-specific facts from extended interaction histories. In practice, many relevant facts often have low semanticsimilarity to the query under dense retrieval. Standard…
Conversational search systems require effective handling of context-dependent queries that often contain ambiguity, omission, and coreference. Conversational Query Reformulation (CQR) addresses this challenge by transforming these queries…
Recent years have witnessed an increasing amount of dialogue/conversation on the web especially on social media. That inspires the development of dialogue-based retrieval, in which retrieving videos based on dialogue is of increasing…
How can we better understand the mechanisms behind multi-turn information seeking dialogues? How can we use these insights to design a dialogue system that does not require explicit query formulation upfront as in question answering? To…
This work presents a text-to-audio-retrieval system based on pre-trained text and spectrogram transformers. Our method projects recordings and textual descriptions into a shared audio-caption space in which related examples from different…
Rotary Position Embedding (RoPE) is an efficient position encoding approach and is widely utilized in numerous large language models (LLMs). Recently, a lot of methods have been put forward to further expand the context window based on…
Automatic speech quality assessment has raised more attention as an alternative or support to traditional perceptual clinical evaluation. However, most research so far only gains good results on simple tasks such as binary classification,…
In conversational AI, personalizing dialogues with persona profiles and contextual understanding is essential. Despite large language models' (LLMs) improved response coherence, effective persona integration remains a challenge. In this…
Large Language Models cannot reliably acquire new knowledge post-deployment -- even when relevant text resources exist, models fail to transform them into actionable knowledge without retraining. Retrieval-Augmented Generation attempts to…
In this paper, we study a novel spatial crowdsourcing system where the workers' time availabilities and their spatial locations are known a priori. Consequently, the tasks assignment to workers is performed not only based on the current…
This paper proposes a voice conversion (VC) method using sequence-to-sequence (seq2seq or S2S) learning, which flexibly converts not only the voice characteristics but also the pitch contour and duration of input speech. The proposed…
Proactive dialogue systems, related to a wide range of real-world conversational applications, equip the conversational agent with the capability of leading the conversation direction towards achieving pre-defined targets or fulfilling…
Multimodal scene search of conversations is essential for unlocking valuable insights into social dynamics and enhancing our communication. While experts in conversational analysis have their own knowledge and skills to find key scenes, a…
The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generator formulates the answer based on the documents retrieved by the retriever. Incorporating Large…