Aleksandr Chuklin Jeff Dalton Julia Kiseleva Alexey Borisov Mikhail Burtsev October 2018

Brussels, Belgium

Association for Computational Linguistics http://www.aclweb.org/anthology/W18-57 book SCAI:2018 IgorShalyminov OndřejDušek OliverLemon Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 1–8 http://www.aclweb.org/anthology/W18-5701 The overall objective of 'social' dialogue systems is to support engaging, entertaining, and lengthy conversations on a wide variety of topics, including social chit-chat. inproceedings shalyminov-duek-lemon:2018:SCAI Giovanni YokoKristianto HuiwenZhang BinTong MakotoIwayama YoshiyukiKobayashi Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 9–16 http://www.aclweb.org/anthology/W18-5702 Solving composites tasks, which consist of several inherent sub-tasks, remains a challenge in the research area of dialogue. Current studies have tackled this issue by manually decomposing the composite tasks into several sub-domains. However, much human effort is inevitable. This paper proposes a dialogue framework that autonomously models meaningful sub-domains and learns the policy over them. Our experiments show that our framework outperforms the baseline without sub-domains by 11% in terms of success rate, and is competitive with that with manually defined sub-domains. inproceedings kristianto-EtAl:2018:SCAI BorisGalitsky DmitryIlvovsky Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 17–23 http://www.aclweb.org/anthology/W18-5703 In this section we propose a reasoning-based approach to a dialogue management for a customer support chat bot. To build a dialogue scenario, we analyze the discourse tree (DT) of an initial query of a customer support dialogue that is frequently complex and multi-sentence. We then enforce rhetorical agreement between DT of the initial query and that of the answers, requests and responses. The chat bot finds answers, which are not only relevant by topic but also suitable for a given step of a conversation and match the question by style, communication means, experience level and other domain-independent attributes. We evaluate a performance of proposed algorithm in car repair domain and observe a 5 to 10% improvement for sin-gle and three-step dialogues respectively, in comparison with baseline approaches to dialogue management. inproceedings galitsky-ilvovsky:2018:SCAI MarcoGuerini SaraFalcone BernardoMagnini Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 24–32 http://www.aclweb.org/anthology/W18-5704 In task-oriented conversational agents, more attention has been usually devoted to assessing task effectiveness (i.e. quality of service), rather than to how the task is achieved (i.e. quality of experience). inproceedings guerini-falcone-magnini:2018:SCAI WafaAissa LaureSoulier LudovicDenoyer Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 33–39 http://www.aclweb.org/anthology/W18-5705 Search-oriented conversational systems rely on information needs expressed in natural language (NL). We focus here on the understanding of NL expressions for building keyword-based queries. We propose a reinforcement-learning-driven translation model framework able to 1) learn the translation from NL expressions to queries in a supervised way, and, 2) to overcome the lack of large-scale dataset by framing the translation model as a word selection approach and injecting relevance feedback as a reward in the learning process. Experiments are carried out on two TREC datasets. We outline the effectiveness of our approach in a retrieval task. inproceedings aissa-soulier-denoyer:2018:SCAI NutLimsopatham OlegRokhlenko DavidCarmel Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 40–45 http://www.aclweb.org/anthology/W18-5706 Recent advances in automatic speech recognition lead toward enabling a voice conversation between a human user and an intelligent virtual assistant. This provides a potential foundation for developing artificial personal shoppers for e-commerce websites, such as Alibaba, Amazon, and eBay. Personal shoppers are valuable to the on-line shops as they enhance user engagement and trust by promptly dealing with customers' questions and concerns. Developing an artificial personal shopper requires the agent to leverage knowledge about the customer and products, while interacting with the customer in a human-like conversation. In this position paper, we motivate and describe the artificial personal shopper task, and then address a research agenda for this task by adapting and advancing existing information retrieval and natural language processing technologies. inproceedings limsopatham-rokhlenko-carmel:2018:SCAI AtsushiSaito Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 46–51 http://www.aclweb.org/anthology/W18-5707 Learning from sparse and delayed reward inproceedings saito:2018:SCAI WenchaoDu AlanBlack Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 52–58 http://www.aclweb.org/anthology/W18-5708 Data augmentation seeks to manipulate the available data for training to improve the generalization ability of models. We investigate two data augmentation proxies, permutation and flipping, for neural dialog response selection task on various models over multiple datasets, including both Chinese and English languages. Different from standard data augmentation techniques, our method combines the original and synthesized data for prediction. Empirical results show that our approach can gain 1 to 3 recall-at-1 points over baseline models in both full-scale and small-scale settings. inproceedings du-black:2018:SCAI ShubhamAgarwal OndřejDušek IoannisKonstas VerenaRieser Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 59–66 http://www.aclweb.org/anthology/W18-5709 Multimodal search-based dialogue is a challenging new task: It extends visually inproceedings agarwal-EtAl:2018:SCAI BojanPetrovski IgnacioAguado AndreeaHossmann MichaelBaeriswyl ClaudiuMusat Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 67–73 http://www.aclweb.org/anthology/W18-5710 Most of the world's data is stored in relational databases. Accessing these requires specialized knowledge of the Structured Query Language (SQL), putting them out of the reach of many people. A recent research thread in Natural Language Processing (NLP) aims to alleviate this problem, by automatically translating natural language questions into SQL queries. While the proposed solutions are a great start, they lack robustness and do not easily generalize: the methods require high quality descriptions of the database table columns, and the most widely used training dataset, WikiSQL, is heavily biased towards using those descriptions as part of the questions. inproceedings petrovski-EtAl:2018:SCAI SamuelLouvan BernardoMagnini Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 74–80 http://www.aclweb.org/anthology/W18-5711 Slot filling is a crucial task in the Natural Language Understanding (NLU) component of a dialogue system. Most approaches for this task rely solely on the domain-specific datasets for training. We propose a joint model of slot filling and Named Entity Recognition (NER) in a multi-task learning (MTL) setup. Our experiments on three slot filling datasets show that using NER as an auxiliary task improves slot filling performance and achieve competitive performance compared with state-of-the-art. In particular, NER is effective when supervised at the lower layer of the model. For low-resource scenarios, we found that MTL is effective for one dataset. inproceedings louvan-magnini:2018:SCAI ShaojieJiang Maartende Rijke Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 81–86 http://www.aclweb.org/anthology/W18-5712 Diversity is a long-studied topic in information retrieval that usually refers to the requirement that retrieved results should be non-repetitive and cover different aspects. In a conversational setting, an additional dimension of diversity matters: an engaging response generation system should be able to output responses that are diverse and interesting. Sequence-to-sequence (Seq2Seq) models have been shown to be very effective for response generation. However, dialogue responses generated by Seq2Seq models tend to have low diversity. In this paper, we review known sources and existing approaches to this low-diversity problem. We also identify a source of low diversity that has been little studied so far, namely model over-confidence. We sketch several directions for tackling model over-confidence and, hence, the low-diversity problem, including confidence penalties and label smoothing. inproceedings jiang-derijke:2018:SCAI JasonWeston EmilyDinan AlexanderMiller Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI October 2018

Brussels, Belgium

Association for Computational Linguistics 87–92 http://www.aclweb.org/anthology/W18-5713 Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging. Retrieval models on the other hand can surface interesting responses, but are restricted to the given retrieval set leading to erroneous replies that cannot be tuned to the specific context. In this work we develop a model that combines the two approaches to avoid both their deficiencies: first retrieve a response and then refine it – the final sequence generator treating the retrieval as additional context. We show on the recent ConvAI2 challenge task our approach produces responses superior to both standard retrieval and generation models in human evaluations. inproceedings weston-dinan-miller:2018:SCAI