Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and cons. Despite the natural idea of an ensemble model of the two, existing ensemble methods only focused on leveraging one approach to enhance another, we argue however that they can be further mutually enhanced with a proper training strategy. In this paper, we propose ensembleGAN, an adversarial learning framework for enhancing a retrieval-generation ensemble model in open-domain conversation scenario. It consists of a language-model-like generator, a ranker generator, and one ranker discriminator. Aiming at generating responses that approximate the ground-truth and receive high ranking scores from the discriminator, the two generators learn to generate improved highly relevant responses and competitive unobserved candidates respectively, while the discriminative ranker is trained to identify true responses from adversarial ones, thus featuring the merits of both generator counterparts. The experimental results on a large short-text conversation data demonstrate the effectiveness of the ensembleGAN by the amelioration on both human and automatic evaluation metrics.
iFLYTEK Research（科大讯飞研究院）；Harbin Institute of Technology（哈尔滨工业大学）；iFLYTEK AI Research (Hebei)（科大讯飞人工智能研究院（河北））
Human conversations contain many types of information, e.g., knowledge, common sense, and language habits. In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversation pairs $ \left\langle{post, reply} \right\rangle$ to learn word embedding. Different from previous works, PR-Embedding uses the vectors from two different semantic spaces to represent the words in post and reply. To catch the information among the pair, we first introduce the word alignment model from statistical machine translation to generate the cross-sentence window, the…
MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
Independent Researcher（独立研究者）；Hanoi University of Science and Technology（河内科学技术大学）；VNU University of Engineering and Technology（VNU工程大学）；Monash University（墨尔本大学）
Finding semantically rich and computer-understandable representations for textual dialogues, utterances and words is crucial for dialogue systems (or conversational agents), as their performance mostly depends on understanding the context of conversations. Recent research aims at finding distributed vector representations (embeddings) for words, such that semantically similar words are relatively close within the vector-space. Encoding the "meaning" of text into vectors is a current trend, and text can range from words, phrases and documents to actual human-to-human conversations. In recent re…
This paper describes the Tartan conversational agent built for the 2018 Alexa Prize Competition. Tartan is a non-goal-oriented socialbot focused around providing users with an engaging and fluent casual conversation. Tartan's key features include an emphasis on structured conversation based on flexible finite-state models and an approach focused on understanding and using conversational acts. To provide engaging conversations, Tartan blends script-like yet dynamic responses with data-based generative and retrieval models. Unique to Tartan is that our dialog manager is modeled as a dynamic Fini…
Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation
The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；The Hong Kong University of Science and Technology（香港科学与技术大学）；National University of Singapore（新加坡国立大学）
iFLYTEK Research, Hefei（科大讯飞研究院（合肥））；Department of Electrical and Computer Engineering, Queen’s University（女王大学电气与计算机工程系）
We present our work on Track 2 in the Dialog System Technology Challenges 7 (DSTC7). The DSTC7-Track 2 aims to evaluate the response generation of fully data-driven conversation models in knowledge-grounded settings, which provides the contextual-relevant factual texts. The Sequenceto-Sequence models have been widely used for end-to-end generative conversation modelling and achieved impressive results. However, they tend to output dull and repeated responses in previous studies. Our work aims to promote the diversity for end-to-end conversation response generation, which follows a two-stage pi…
S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modeling
College of Computer Science, Inner Mongolia University（内蒙古大学计算机学院）；University of Electronic Science and Technology of China, Shenzhen Campus（电子科技大学深圳校区）
Alibaba-NTU Singapore Joint Research Institute, Nanyang Technological University (NTU), Singapore（阿里巴巴-南洋理工大学新加坡联合研究院，南洋理工大学）；Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly, NTU, Singapore（南洋理工大学-不列颠哥伦比亚大学积极老龄化卓越联合研究中心，南洋理工大学）；Alibaba Group, China（阿里巴巴集团）
We study the problem of imposing conversational goals/keywords on open-domain conversational agents, where the agent is required to lead the conversation to a target keyword smoothly and fast. Solving this problem enables the application of conversational agents in many real-world scenarios, e.g., recommendation and psychotherapy. The dominant paradigm for tackling this problem is to 1) train a next-turn keyword classifier, and 2) train a keyword-augmented response retrieval model. However, existing approaches in this paradigm have two limitations: 1) the training and evaluation datasets for n…
Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. This paper describes a 3-step procedure to develop a conversational model that satisfies these criteria and can efficiently scale to rank a large set of response candidates. First, we provide a simple algorithm to semi-automatically create a high-coverage template set from historic conversations without any annotation. Second, we propose a neural architecture that encodes the dialogue context and applicable business con…
Prior studies addressing target-oriented conversational tasks lack a crucial notion that has been intensively studied in the context of goal-oriented artificial intelligence agents, namely, planning. In this study, we propose the task of Target-Guided Open-Domain Conversation Planning (TGCP) task to evaluate whether neural conversational agents have goal-oriented conversation planning abilities. Using the TGCP task, we investigate the conversation planning abilities of existing retrieval models and recent strong generative models. The experimental results reveal the challenges facing current t…
Human computer conversation is regarded as one of the most difficult problems in artificial intelligence. In this paper, we address one of its key sub-problems, referred to as short text conversation, in which given a message from human, the computer returns a reasonable response to the message. We leverage the vast amount of short conversation data available on social media to study the issue. We propose formalizing short text conversation as a search problem at the first step, and employing state-of-the-art information retrieval (IR) techniques to carry out the task. We investigate the signi…
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Huawei Poisson Lab（华为泊松实验室）；Waseda University（早稻田大学）
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Carnegie Mellon University（卡内基梅隆大学）；Alibaba Group（阿里巴巴集团）；Microsoft Research Redmond（微软雷德蒙德研究院）；Tencent AI Lab（腾讯人工智能实验室）
Intelligent personal assistant systems that are able to have multi-turn conversations with human users are becoming increasingly popular. Most previous research has been focused on using either retrieval-based or generation-based methods to develop such systems. Retrieval-based methods have the advantage of returning fluent and informative responses with great diversity. However, the performance of the methods is limited by the size of the response repository. On the other hand, generation-based methods can produce highly coherent responses on any topics. But the generated responses are often …
Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model
Beijing University of Posts and Telecommunications（北京邮电大学）；SenseTime（商汤科技）；Beijing Key Laboratory of Network System and Network Culture（网络系统与网络文化北京市重点实验室）
UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval
The Chinese University of Hong Kong（香港中文大学）；Nankai University（南开大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
University of Washington（华盛顿大学）；Google Research（谷歌研究院）；Allen Institute for AI（艾伦人工智能研究所）
Compared to standard retrieval tasks, passage retrieval for conversational question answering (CQA) poses new challenges in understanding the current user question, as each question needs to be interpreted within the dialogue context. Moreover, it can be expensive to re-train well-established retrievers such as search engines that are originally developed for non-conversational queries. To facilitate their use, we develop a query rewriting model CONQRR that rewrites a conversational question in the context into a standalone question. It is trained with a novel reward function to directly optim…
University of Amsterdam（阿姆斯特丹大学）；Università della Svizzera italiana (USI)（意大利语区瑞士大学）
With the improvements in speech recognition and voice generation technologies over the last years, a lot of companies have sought to develop conversation understanding systems that run on mobile phones or smart home devices through natural language interfaces. Conversational assistants, such as Google Assistant and Microsoft Cortana, can help users to complete various types of tasks. This requires an accurate understanding of the user's information need as the conversation evolves into multiple turns. Finding relevant context in a conversation's history is challenging because of the complexity…
Retrieval-based conversation systems generally tend to highly rank responses that are semantically similar or even identical to the given conversation context. While the system's goal is to find the most appropriate response, rather than the most semantically similar one, this tendency results in low-quality responses. We refer to this challenge as the echoing problem. To mitigate this problem, we utilize a hard negative mining approach at the training stage. The evaluation shows that the resulting model reduces echoing and achieves better results in terms of Average Precision and Recall@N met…
Beyond Static: Related Questions Retrieval Through Conversations in Community Question Answering
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；School of Management Science and Engineering, Southwestern University of Finance and Economics（西南财经大学管理科学与工程学院）
Response retrieval is a subset of neural ranking in which a model selects a suitable response from a set of candidates given a conversation history. Retrieval-based chat-bots are typically employed in information seeking conversational systems such as customer support agents. In order to make pairwise comparisons between a conversation history and a candidate response, two approaches are common: cross-encoders performing full self-attention over the pair and bi-encoders encoding the pair separately. The former gives better prediction quality but is too slow for practical use. In this paper, we…
Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due to high latency. On the other hand, retrieval models could return responses with much lower latency but show inferior performance to the large-scale generative models since the conversation quality is bounded by the pre-defined response set. To take advantage of both approaches, we propose a new training method called G2R (Generative-to-Retrieval distillation) that preserves the efficiency of a retrieval model while…
Despite showing increasingly human-like conversational abilities, state-of-the-art dialogue models often suffer from factual incorrectness and hallucination of knowledge (Roller et al., 2020). In this work we explore the use of neural-retrieval-in-the-loop architectures - recently shown to be effective in open-domain QA (Lewis et al., 2020b; Izacard and Grave, 2020) - for knowledge-grounded dialogue, a task that is arguably more challenging as it requires querying based on complex multi-turn dialogue context and generating conversationally coherent responses. We study various types of architec…
MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；Meituan Inc.（美团公司）；NiuTrans Research（牛译研所）；Tsinghua University（清华大学）
Chinese University of Hong Kong（香港中文大学）；Salesforce Research（Salesforce研究院）
In conversational machine reading, systems need to interpret natural language rules, answer high-level questions such as "May I qualify for VA health care benefits?", and ask follow-up clarification questions whose answer is necessary to answer the original question. However, existing works assume the rule text is provided for each user question, which neglects the essential retrieval step in real scenarios. In this work, we propose and investigate an open-retrieval setting of conversational machine reading. In the open-retrieval setting, the relevant rule texts are unknown so that a system ne…
Beijing Institute of Technology（北京理工大学）；Southeast Academy of Information Technology（东南信息技术研究院）
Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes. Machines are required to make a decision of "Yes/No/Inquire" or generate a follow-up question when the decision is "Inquire" based on retrieved rule texts, user scenario, user question, and dialogue history. Recent studies explored the methods to reduce the information gap between decision-making and question generation and thus improve the performance of generation. However, the information gap still exists because these pipeline structures are still limited in decision-m…
Conversational agents ("bots") are beginning to be widely used in conversational interfaces. To design a system that is capable of emulating human-like interactions, a conversational layer that can serve as a fabric for chat-like interaction with the agent is needed. In this paper, we introduce a model that employs Information Retrieval by utilizing convolutional deep structured semantic neural network-based features in the ranker to present human-like responses in ongoing conversation with a user. In conversations, accounting for context is critical to the retrieval model; we show that our co…
Université de Montréal（蒙特利尔大学）；Renmin University of China（中国人民大学）
Grounding human-machine conversation in a document is an effective way to improve the performance of retrieval-based chatbots. However, only a part of the document content may be relevant to help select the appropriate response at a round. It is thus crucial to select the part of document content relevant to the current conversation context. In this paper, we propose a document content selection network (CSN) to perform explicit selection of relevant document contents, and filter out the irrelevant parts. We show in experiments on two public document-grounded conversation datasets that CSN can…
PRCCF: A Persona-guided Retrieval and Causal-aware Cognitive Filtering Framework for Emotional Support Conversation
School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China（东北大学计算机科学与工程学院，沈阳，辽宁，中国）；Oracle Cloud Infrastructure, Oracle, Santa Clara, CA, United States（甲骨文云基础设施，甲骨文公司，圣克拉拉，加利福尼亚州，美国）
ASAPP, Inc.（ASAPP公司）；Massachusetts Institute of Technology（麻省理工学院）
Response suggestion is an important task for building human-computer conversation systems. Recent approaches to conversation modeling have introduced new model architectures with impressive results, but relatively little attention has been paid to whether these models would be practical in a production setting. In this paper, we describe the unique challenges of building a production retrieval-based conversation system, which selects outputs from a whitelist of candidate responses. To address these challenges, we propose a dual encoder architecture which performs rapid inference and scales wel…
