中文
相关论文

相关论文: Improving Conversational Passage Re-ranking with V…

200 篇论文

In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme. Existing solutions to passage reranking focus on enriching the interaction between query and each passage…

信息检索 · 计算机科学 2023-12-25 Zongmeng Zhang , Wengang Zhou , Jiaxin Shi , Houqiang Li

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

信息检索 · 计算机科学 2021-11-30 Sheng-Chieh Lin , Jheng-Hong Yang , Jimmy Lin

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

计算与语言 · 计算机科学 2025-01-28 Ziwei Liu , Qi Zhang , Lifu Gao

Conversational recommendation (ConvRec) systems must understand rich and diverse natural language (NL) expressions of user preferences and intents, often communicated in an indirect manner (e.g., "I'm watching my weight"). Such complex…

计算与语言 · 计算机科学 2024-06-04 Sara Kemper , Justin Cui , Kai Dicarlantonio , Kathy Lin , Danjie Tang , Anton Korikov , Scott Sanner

Recent developments of dense retrieval rely on quality representations of queries and contexts from pre-trained query and context encoders. In this paper, we introduce TOUR (Test-Time Optimization of Query Representations), which further…

计算与语言 · 计算机科学 2023-05-30 Mujeen Sung , Jungsoo Park , Jaewoo Kang , Danqi Chen , Jinhyuk Lee

Conversational search is a difficult task as it aims at retrieving documents based not only on the current user query but also on the full conversation history. Most of the previous methods have focused on a multi-stage ranking approach…

信息检索 · 计算机科学 2024-07-08 Nam Le Hai , Thomas Gerald , Thibault Formal , Jian-Yun Nie , Benjamin Piwowarski , Laure Soulier

Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad-hoc information retrieval (IR) systems due to the coreference and omission…

计算与语言 · 计算机科学 2021-03-12 Sheng-Chieh Lin , Jheng-Hong Yang , Rodrigo Nogueira , Ming-Feng Tsai , Chuan-Ju Wang , Jimmy Lin

In this work, we focus on improving the captions generated by image-caption generation systems. We propose a novel re-ranking approach that leverages visual-semantic measures to identify the ideal caption that maximally captures the visual…

计算机视觉与模式识别 · 计算机科学 2022-09-20 Ahmed Sabir , Francesc Moreno-Noguer , Pranava Madhyastha , Lluís Padró

This paper describes the participation of UvA.ILPS group at the TREC CAsT 2020 track. Our passage retrieval pipeline consists of (i) an initial retrieval module that uses BM25, and (ii) a re-ranking module that combines the score of a BERT…

信息检索 · 计算机科学 2021-02-18 Svitlana Vakulenko , Nikos Voskarides , Zhucheng Tu , Shayne Longpre

Information retrieval systems have traditionally relied on exact term match methods such as BM25 for first-stage retrieval. However, recent advancements in neural network-based techniques have introduced a new method called dense retrieval.…

信息检索 · 计算机科学 2025-03-25 Ahmed H. Salamah , Pierre McWhannel , Nicole Yan

Recently, much progress in natural language processing has been driven by deep contextualized representations pretrained on large corpora. Typically, the fine-tuning on these pretrained models for a specific downstream task is based on…

信息检索 · 计算机科学 2022-08-11 Jia-Huei Ju , Jheng-Hong Yang , Chuan-Ju Wang

Conversational search allows a user to interact with a search system in multiple turns. A query is strongly dependent on the conversation context. An effective way to improve retrieval effectiveness is to expand the current query with…

信息检索 · 计算机科学 2023-06-06 Fengran Mo , Jian-Yun Nie , Kaiyu Huang , Kelong Mao , Yutao Zhu , Peng Li , Yang Liu

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retrieved passages with a zero-shot question generation model, which uses a pre-trained language model…

计算与语言 · 计算机科学 2023-04-04 Devendra Singh Sachan , Mike Lewis , Mandar Joshi , Armen Aghajanyan , Wen-tau Yih , Joelle Pineau , Luke Zettlemoyer

State of the art approaches for (embedding based) unsupervised semantic search exploits either compositional similarity (of a query and a passage) or pair-wise word (or term) similarity (from the query and the passage). By design, word…

计算与语言 · 计算机科学 2019-03-14 Md Faisal Mahbub Chowdhury , Vijil Chenthamarakshan , Rishav Chakravarti , Alfio M. Gliozzo

Reranker models aim to re-rank the passages based on the semantics similarity between the given query and passages, which have recently received more attention due to the wide application of the Retrieval-Augmented Generation. Most previous…

计算与语言 · 计算机科学 2025-01-14 Junlong Liu , Yue Ma , Ruihui Zhao , Junhao Zheng , Qianli Ma , Yangyang Kang

Recent studies have demonstrated the effectiveness of using large language language models (LLMs) in passage ranking. The listwise approaches, such as RankGPT, have become new state-of-the-art in this task. However, the efficiency of…

计算与语言 · 计算机科学 2025-01-29 Qi Liu , Bo Wang , Nan Wang , Jiaxin Mao

Neural information retrieval systems typically use a cascading pipeline, in which a first-stage model retrieves a candidate set of documents and one or more subsequent stages re-rank this set using contextualized language models such as…

信息检索 · 计算机科学 2021-04-27 Antonio Mallia , Omar Khattab , Nicola Tonellotto , Torsten Suel

We propose reCSE, a self supervised contrastive learning sentence representation framework based on feature reshaping. This framework is different from the current advanced models that use discrete data augmentation methods, but instead…

计算与语言 · 计算机科学 2024-08-27 Fufangchen Zhao , Jian Gao , Danfeng Yan

Retrieve-and-rerank is a popular retrieval pipeline because of its ability to make slow but effective rerankers efficient enough at query time by reducing the number of comparisons. Recent works in neural rerankers take advantage of large…

信息检索 · 计算机科学 2025-05-21 Eugene Yang , Andrew Yates , Kathryn Ricci , Orion Weller , Vivek Chari , Benjamin Van Durme , Dawn Lawrie

Large Language Model (LLM)-based passage expansion has shown promise for enhancing first-stage retrieval, but often underperforms with dense retrievers due to semantic drift and misalignment with their pretrained semantic space. Beyond…

信息检索 · 计算机科学 2025-08-26 Huanwei Xu , Lin Xu , Liang Yuan
‹ 上一页 1 2 3 10 下一页 ›