More Like this

1. Asking Clarifying Questions Based on Negative Feedback in Conversational Search

   https://doi.org/10.1145/3471158.3472232  

   Ai, Q. ; Bi, K. ; Croft, W. B. ( July 2021 , Proceedings of the 7th ACM International Conference on the Theory of Information Retrieval (ICTIR 2021))

   Users often need to look through multiple search result pages or reformulate queries when they have complex information-seeking needs. Conversational search systems make it possible to improve user satisfaction by asking questions to clarify users’ search intents. This, however, can take significant effort to answer a series of questions starting with “what/why/how”. To quickly identify user intent and reduce effort during interactions, we propose an intent clarification task based on yes/no questions where the system needs to ask the correct question about intents within the fewest conversation turns. In this task, it is essential to use negative feedback about themore »previous questions in the conversation history. To this end, we propose a Maximum-Marginal-Relevance (MMR) based BERT model (MMR-BERT) to leverage negative feedback based on the MMR principle for the next clarifying question selection. Experiments on the Qulac dataset show that MMR-BERT outperforms state-of-the-art baselines significantly on the intent identification task and the selected questions also achieve significantly better performance in the associated document retrieval tasks.« less
2. IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems

   https://doi.org/10.1145/3366423.3380011  

   Yang, L. ( April 2020 , Proceedings of The Web Conference 2020 (WWW 2020))

   Personal assistant systems, such as Apple Siri, Google Now, Amazon Alexa, and Microsoft Cortana, are becoming ever more widely used. Understanding user intent such as clarification questions, potential answers and user feedback in information-seeking conversations is critical for retrieving good responses. In this paper, we analyze user intent patterns in information-seeking conversations and propose an intent-aware neural response ranking model ``IART'', which refers to ``Intent-Aware Ranking with Transformers''. IART is built on top of the integration of user intent modeling and language representation learning with the Transformer architecture, which relies entirely on a self-attention mechanism instead of recurrent nets. Itmore »incorporates intent-aware utterance attention to derive an importance weighting scheme of utterances in conversation context with the aim of better conversation history understanding. We conduct extensive experiments with three information-seeking conversation data sets including both standard benchmarks and commercial data. Our proposed model outperforms all baseline methods with respect to a variety of metrics. We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results. Our research findings provide insights on intent-aware neural ranking models based on Transformers for response selection, and have implications for the design of the next generation of information-seeking conversation systems.« less
3. Entertaining and opinionated but too controlling: a large-scale user study of an open domain Alexa prize system

   Bowden, Kevin K. ; Wu, Jiaqi ; Cui, Wen ; Juraska, Juraj ; Harrison, Vrindavan ; Schwarzmann, Brian ; Santer, Nicholas ; Whittaker, Steve ; Walker, Marilyn ( August 2019 , Proceedings of the 1st International Conference on Conversational User Interfaces)

   Conversational systems typically focus on functional tasks such as scheduling appointments or creating todo lists. Instead we design and evaluate SlugBot (SB), one of 8 semifinalists in the 2018 AlexaPrize, whose goal is to support casual open-domain social inter-action. This novel application requires both broad topic coverage and engaging interactive skills. We developed a new technical approach to meet this demanding situation by crowd-sourcing novel content and introducing playful conversational strategies based on storytelling and games. We collected over 10,000 conversations during August 2018 as part of the Alexa Prize competition. We also conducted an in-lab follow-up qualitative evaluation. Over-allmore »users found SB moderately engaging; conversations averaged 3.6 minutes and involved 26 user turns. However, users reacted very differently to different conversation subtypes. Storytelling and games were evaluated positively; these were seen as entertaining with predictable interactive structure. They also led users to impute personality and intelligence to SB. In contrast, search and general Chit-Chat induced coverage problems; here users found it hard to infer what topics SB could understand, with these conversations seen as being too system-driven. Theoretical and design implications suggest a move away from conversational systems that simply provide factual information. Future systems should be designed to have their own opinions with personal stories to share, and SB provides an example of how we might achieve this.« less
4. Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search

   https://doi.org/10.1145/3397271.3401061  

   Hashemi, Helia ; Zamani, Hamed ; Croft, W. Bruce ( July 2020 , Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR2020))

   Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, in particular, conversational search systems with limited bandwidth interfaces. Analyzing and generating clarifying question have been recently studied in the literature. However, accurate utilization of user responses to clarifying questions has been relatively less explored. In this paper, we propose a neural network model based on a novel attention mechanism, called multi source attention network. Our model learns a representation for a user-system conversation that includes clarifying questions. In more detail, with the help of multiple information sources,more »our model weights each term in the conversation. In our experiments, we use two separate external sources, including the top retrieved documents and a set of different possible clarifying questions for the query. We implement the proposed representation learning model for two downstream tasks in conversational search; document retrieval and next clarifying question selection. We evaluate our models using a public dataset for search clarification. Our experiments demonstrate significant improvements compared to competitive baselines.« less
5. Weakly-Supervised Open-Retrieval Conversational Question Answering

   https://doi.org/10.1007/978-3-030-72113-8_35  

   Qu, C. ; Yang, L. ; Chen, C. ; Croft, W. B. ; Krishna, K. ; Iyyer, M. ( March 2021 , Proceedings of the 43rd European Conference on Information Retrieval (ECIR 2021))

   Recent work on Question Answering (QA) and Conversational QA (ConvQA) emphasizes the role of retrieval: a system first retrieves evidence from a large collection and then extracts answers. This open-retrieval setting typically assumes that each question is answerable by a single span of text within a particular passage (a span answer). The supervision signal is thus derived from whether or not the system can recover an exact match of this ground-truth answer span from the retrieved passages. This method is referred to as span-match weak supervision. However, information-seeking conversations are challenging for this span-match method since long answers, especially freeformmore »answers, are not necessarily strict spans of any passage. Therefore, we introduce a learned weak supervision approach that can identify a paraphrased span of the known answer in a passage. Our experiments on QuAC and CoQA datasets show that although a span-match weak supervisor can handle conversations with span answers, it is not sufficient for freeform answers generated by people. We further demonstrate that our method is more flexible since it can handle both span answers and freeform answers. In particular, our method outperforms the span-match method on conversations with freeform answers, and it can be more powerful when combined with the span-match method. We also conduct in-depth analyses to show more insights on open-retrieval ConvQA under a weak supervision setting.« less