Yujie Lin, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Jun Ma, and I published “Explainable Fashion Recommendation with Joint Outfit Matching and Comment Generation” on arXiv. Most previous work on fashion recommendation focuses on designing visual features to enhance recommendations. Existing work neglects user comments of fashion items, which have been proved effective in generating explanations along with better recommendation results. We propose a novel neural network framework, neural fashion recommendation (NFR), that simultaneously provides fashion recommendations and generates abstractive comments. NFR consists of two parts: outfit matching and comment generation. For outfit matching, we propose a convolutional neural network with a mutual attention mechanism to extract visual features of outfits. The visual features are then decoded into a rating score for the matching prediction. For abstractive comment generation, we propose a gated recurrent neural network with a cross-modality attention mechanism to transform visual features into a concise sentence. The two parts are jointly trained based on a multi-task learning framework in an end-to-end back-propagation paradigm. Extensive experiments conducted on an existing dataset and a collected real-world dataset show NFR achieves significant improvements over state-of-the-art baselines for fashion recommendation. Meanwhile, our generated comments achieve impressive ROUGE and BLEU scores in comparison to human-written comments. The generated comments can be regarded as explanations for the recommendation results. We release the dataset and code to facilitate future research. You can find the paper here.
We just opened five more vacancies for PhD students. The general area is AI for Retail, and the positions are part of the new AIRLab. Areas range from recommendation to federated search and conversational search to replenishment. Deadline: July 16, 2018. Please visit this page for all the details.
We’ve just put three more papers on arXiv.
Earlier in June, Sapna Negi, Paul Buitelaar, and I put “Open Domain Suggestion Mining: Problem Definition and Datasets” on arXiv. In the paper we propose a formal definition for the task of suggestion mining in the context of a wide range of open domain applications. Human perception of the term suggestion is subjective and this effects the preparation of hand labeled datasets for the task of suggestion mining. Existing work either lacks a formal problem definition and annotation procedure, or provides domain and application specific definitions. Moreover, many previously used manually labeled datasets remain proprietary. We first present an annotation study, and based on our observations propose a formal task definition and annotation procedure for creating benchmark datasets for suggestion mining. With this study, we also provide publicly available labeled datasets for suggestion mining in multiple domains. You can find the paper here.
Then, in mid June, Branislav Kveton, Chang Li, Tor Lattimore, Ilya Markov, Csaba Szepesvari, Masrour Zoghi, and I put “BubbleRank: Safe Online Learning to Rerank” on arXiv. We study the problem of online learning to re-rank, where users provide feedback to improve the quality of displayed lists. Learning to rank has been traditionally studied in two settings. In the offline setting, rankers are typically learned from relevance labels of judges. These approaches have become the industry standard. However, they lack exploration, and thus are limited by the information content of offline data. In the online setting, an algorithm can propose a list and learn from the feedback on it in a sequential fashion. Bandit algorithms developed for this setting actively experiment, and in this way overcome the biases of offline data. But they also tend to ignore offline data, which results in a high initial cost of exploration. We propose BubbleRank, a bandit algorithm for re-ranking that combines the strengths of both settings. The algorithm starts with an initial base list and improves it gradually by swapping higher-ranked less attractive items for lower-ranked more attractive items. We prove an upper bound on the n-step regret of BubbleRank that degrades gracefully with the quality of the initial base list. Our theoretical findings are supported by extensive numerical experiments on a large real-world click dataset. The paper can be found here.
And, third, Svitlana Vakulenko, Michael Cochez, Vadim Savenkov, Axel Polleres, and I put “Measuring Semantic Coherence of a Conversation” on arXiv. Conversational systems have become increasingly popular as a way for humans to interact with computers. To be able to provide intelligent responses, conversational systems must correctly model the structure and semantics of a conversation. We introduce the task of measuring semantic (in)coherence in a conversation with respect to background knowledge, which relies on the identification of semantic relations between concepts introduced during a conversation. We propose and evaluate graph-based and machine learning-based approaches for measuring semantic coherence using knowledge graphs, their vector space embeddings and word embedding models, as sources of background knowledge. We demonstrate how these approaches are able to uncover different coherence patterns in conversations on the Ubuntu Dialogue Corpus. The paper can be found here.
We just opened another vacancy, for a PhD student to work on dataset search. Come and join us to work in the area of AI & IR, together with great colleagues at Elsevier, VU Amsterdam and KNAW. See https://t.co/um5ldIQAZg for more details.