Exploring Dense Retrieval for Dialogue Response Selection

• URL: http://arxiv.org/abs/2110.06612v1
• Date: Wed, 13 Oct 2021 10:10:32 GMT
• Title: Exploring Dense Retrieval for Dialogue Response Selection
• Authors: Tian Lan, Deng Cai, Yan Wang, Yixuan Su, Xian-Ling Mao, Heyan Huang
• Abstract summary: We present a solution to directly select proper responses from a large corpus or even a nonparallel corpus, using a dense retrieval model. For re-rank setting, the superiority is quite surprising given its simplicity. For full-rank setting, we can emphasize that we are the first to do such evaluation.
• Score: 42.89426092886912
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent research on dialogue response selection has been mainly focused on selecting a proper response from a pre-defined small set of candidates using sophisticated neural models. Due to their heavy computational overhead, they are unable to select responses from a large candidate pool. In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using a dense retrieval model. We extensively test our proposed approach under two experiment settings: (i) re-rank experiment that aims to rank a small set of pre-defined candidates; (ii) full-rank experiment where the target is to directly select proper responses from a full candidate pool that may contain millions of candidates. For re-rank setting, the superiority is quite surprising given its simplicity. For full-rank setting, we can emphasize that we are the first to do such evaluation. Moreover, human evaluation results show that increasing the size of nonparallel corpus leads to further improvement of our model performance\footnote{All our source codes, models and other related resources are publically available at \url{https://github.com/gmftbyGMFTBY/SimpleReDial-v1}.

Related papers

• Aligning Large Language Models by On-Policy Self-Judgment [49.31895979525054]
  Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. We present a novel alignment framework, SELF-JUDGE, that does on-policy learning and is parameter efficient. We show that the rejecting sampling by itself can improve performance further without an additional evaluator.
  arXiv  Detail & Related papers  (2024-02-17T11:25:26Z)
• Generative Judge for Evaluating Alignment [84.09815387884753]
  We propose a generative judge with 13B parameters, Auto-J, designed to address these challenges. Our model is trained on user queries and LLM-generated responses under massive real-world scenarios. Experimentally, Auto-J outperforms a series of strong competitors, including both open-source and closed-source models.
  arXiv  Detail & Related papers  (2023-10-09T07:27:15Z)
• Model-Based Simulation for Optimising Smart Reply [3.615981646205045]
  Smart Reply (SR) systems present a user with a set of replies, of which one can be selected in place of having to type out a response. Previous work has focused largely on post-hoc diversification, rather than explicitly learning to predict sets of responses. We present a novel method SimSR, that employs model-based simulation to discover high-value response sets.
  arXiv  Detail & Related papers  (2023-05-26T12:04:33Z)
• Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder [45.60134971181856]
  Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods pre-compute image embeddings over the entire corpus and compare these to a reference image embedding modified by the query text at test time. We propose to combine the merits of both schemes using a two-stage model.
  arXiv  Detail & Related papers  (2023-05-25T17:56:24Z)
• SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation [54.66399120084227]
  Language models trained on large-scale corpora can generate remarkably fluent results in open-domain dialogue. For the persona-based dialogue generation task, consistency and coherence are great challenges for language models. A two-stage SimOAP strategy is proposed, i.e., over-sampling and post-evaluation.
  arXiv  Detail & Related papers  (2023-05-18T17:23:00Z)
• Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task [27.513992470527427]
  In retrieval-based dialogue systems, a response selection model acts as a ranker to select the most appropriate response among several candidates. Recent studies have shown that leveraging adversarial responses as negative training samples is useful for improving the discriminating power of the selection model. This paper proposes a simple but efficient method for generating adversarial negative responses leveraging a large-scale language model.
  arXiv  Detail & Related papers  (2022-10-31T11:49:49Z)
• A Systematic Evaluation of Response Selection for Open Domain Dialogue [36.88551817451512]
  We curated a dataset where responses from multiple response generators produced for the same dialog context are manually annotated as appropriate (positive) and inappropriate (negative) We conduct a systematic evaluation of state-of-the-art methods for response selection, and demonstrate that both strategies of using multiple positive candidates and using manually verified hard negative candidates can bring in significant performance improvement in comparison to using the adversarial training data, e.g., increase of 3% and 13% in Recall@1 score, respectively.
  arXiv  Detail & Related papers  (2022-08-08T19:33:30Z)
• Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues [11.726528038065764]
  We focus on the more realistic task of full-rank retrieval of responses, where $n$ can be up to millions of responses. Our findings based on three different information-seeking dialogue datasets reveal that a learned response expansion technique is a solid baseline for sparse retrieval. We find the best performing method overall to be dense retrieval with intermediate training, followed by fine-tuning on the target conversational data.
  arXiv  Detail & Related papers  (2022-04-22T08:15:15Z)
• In Situ Answer Sentence Selection at Web-scale [120.69820139008138]
  Passage-based Extracting Answer Sentence In-place (PEASI) is a novel design for AS2 optimized for Web-scale setting. We train PEASI in a multi-task learning framework that encourages feature sharing between the components: passage reranker and passage-based answer sentence extractor. Experiments show PEASI effectively outperforms the current state-of-the-art setting for AS2, i.e., a point-wise model for ranking sentences independently, by 6.51% in accuracy.
  arXiv  Detail & Related papers  (2022-01-16T06:36:00Z)
• Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting [84.9716460244444]
  We consider utilizing the underlying correlation in the data resource itself to derive different kinds of supervision signals. We conduct extensive experiments in two public datasets and obtain significant improvement in both datasets.
  arXiv  Detail & Related papers  (2020-02-18T06:29:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.