Evaluation is crucial in the development process of task-oriented dialogue systems. As an evaluation method, user simulation allows us to tackle issues such as scalability and cost-efficiency, making it a viable choice for large-scale automatic evaluation. To help build a human-like user simulator that can measure the quality of a dialogue, we propose the following task: simulating user satisfaction for the evaluation of task-oriented dialogue systems. The purpose of the task is to increase the evaluation power of user simulations and to make the simulation more human-like. To overcome a lack of annotated data, we propose a user satisfaction annotation dataset, USS, that includes 6,800 dialogues sampled from multiple domains, spanning real-world e-commerce dialogues, task-oriented dialogues constructed through Wizard-of-Oz experiments, and movie recommendation dialogues. All user utterances in those dialogues, as well as the dialogues themselves, have been labeled based on a 5-level satisfaction scale. We also share three baseline methods for user satisfaction prediction and action prediction tasks. Experiments conducted on the USS dataset suggest that distributed representations outperform feature-based methods. A model based on hierarchical GRUs achieves the best performance in in-domain user satisfaction prediction, while a BERT-based model has better cross-domain generalization ability.
Being able to generate informative and coherent dialogue responses is crucial when designing human-like open-domain dialogue systems. Encoder-decoder-based dialogue models tend to produce generic and dull responses during the decoding step because the most predictable response is likely to be a non-informative response instead of the most suitable one. To alleviate this problem, we propose to train the generation model in a bidirectional manner by adding a backward reasoning step to the vanilla encoder-decoder training. The proposed backward reasoning step pushes the model to produce more informative and coherent content because the forward generation step's output is used to infer the dialogue context in the backward direction. The advantage of our method is that the forward generation and backward reasoning steps are trained simultaneously through the use of a latent variable to facilitate bidirectional optimization. Our method can improve response quality without introducing side information (e.g., a pre-trained topic model). The proposed bidirectional response generation method achieves state-of-the-art performance for response quality.
Conversational search is a relatively young area of research that aims at automating an information-seeking dialogue. In this paper we help to position it with respect to other research areas within conversational Artificial Intelligence (AI) by analysing the structural properties of an information-seeking dialogue. To this end, we perform a large-scale dialogue analysis of more than 150K transcripts from 15 publicly available dialogue datasets. These datasets were collected to inform different dialogue-based tasks including conversational search. We extract different patterns of mixed initiative from these dialogue transcripts and use them to compare dialogues of different types. Moreover, we contrast the patterns found in information-seeking dialogues that are being used for research purposes with the patterns found in virtual reference interviews that were conducted by professional librarians. The insights we provide (1) establish close relations between conversational search and other conversational AI tasks; and (2) uncover limitations of existing conversational datasets to inform future data collection tasks.
Existing work in counterfactual Learning to Rank (LTR) has focussed on optimizing feature-based models that predict the optimal ranking based on document features. LTR methods based on bandit algorithms often optimize tabular models that memorize the optimal ranking per query. These types of model have their own advantages and disadvantages. Feature-based models provide very robust performance across many queries, including those previously unseen, however, the available features often limit the rankings the model can predict. In contrast, tabular models can converge on any possible ranking through memorization. However, memorization is extremely prone to noise, which makes tabular models reliable only when large numbers of user interactions are available. Can we develop a robust counterfactual LTR method that pursues memorization-based optimization whenever it is safe to do? We introduce the Generalization and Specialization (GENSPEC) algorithm, a robust feature-based counterfactual LTR method that pursues per-query memorization when it is safe to do so. GENSPEC optimizes a single feature-based model for generalization: robust performance across all queries, and many tabular models for specialization: each optimized for high performance on a single query. GENSPEC uses novel relative high-confidence bounds to choose which model to deploy per query. By doing so, GENSPEC enjoys the high performance of successfully specialized tabular models with the robustness of a generalized feature-based model. Our results show that GENSPEC leads to optimal performance on queries with sufficient click data, while having robust behavior on queries with little or noisy data.
There is increasing interest in developing personalized Task-oriented Dialogue Systems (TDSs). Previous work on personalized TDSs often assumes that complete user profiles are available for most or even all users. This is unrealistic because (1) not everyone is willing to expose their profiles due to privacy concerns; and (2) rich user profiles may involve a large number of attributes (e.g., gender, age, tastes, . . .). In this paper, we study personalized TDSs without assuming that user profiles are complete. We propose a Cooperative Memory Network (CoMemNN) that has a novel mechanism to gradually enrich user profiles as dialogues progress and to simultaneously improve response selection based on the enriched profiles. CoMemNN consists of two core modules: User Profile Enrichment (UPE) and Dialogue Response Selection (DRS). The former enriches incomplete user profiles by utilizing collaborative information from neighbor users as well as current dialogues. The latter uses the enriched profiles to update the current user query so as to encode more useful information, based on which a personalized response to a user request is selected. We conduct extensive experiments on the personalized bAbI dialogue benchmark datasets. We find that CoMemNN is able to enrich user profiles effectively, which results in an improvement of 3.06% in terms of response selection accuracy compared to state-of-the-art methods. We also test the robustness of CoMemNN against incompleteness of user profiles by randomly discarding attribute values from user profiles. Even when discarding 50% of the attribute values, CoMemNN is able to match the performance of the best performing baseline without discarding user profiles, showing the robustness of CoMemNN.
Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications. However, static recommendation models are difficult to answer two important questions well due to inherent shortcomings: (a) What exactly does a user like? (b) Why does a user like an item? The shortcomings are due to the way that static models learn user preference, i.e., without explicit instructions and active feedback from users. The recent rise of conversational recommender systems (CRSs) changes this situation fundamentally. In a CRS, users and the system can dynamically communicate through natural language interactions, which provide unprecedented opportunities to explicitly obtain the exact preference of users. Considerable efforts, spread across disparate settings and applications, have been put into developing CRSs. Existing models, technologies, and evaluation methods for CRSs are far from mature. In this paper, we provide a systematic review of the techniques used in current CRSs. We summarize the key challenges of developing CRSs into five directions: (1) Question-based user preference elicitation. (2) Multi-turn conversational recommendation strategies. (3) Dialogue understanding and generation. (4) Exploitation-exploration trade-offs. (5) Evaluation and user simulation. These research directions involve multiple research fields like information retrieval (IR), natural language processing (NLP), and human-computer interaction (HCI). Based on these research directions, we discuss some future challenges and opportunities. We provide a road map for researchers from multiple communities to get started in this area. We hope this survey helps to identify and address challenges in CRSs and inspire future research.
Graph neural networks (GNNs) have shown increasing promise in real-world applications, which has caused an increased interest in understanding their predictions. However, existing methods for explaining predictions from GNNs do not provide an opportunity for recourse: given a prediction for a particular instance, we want to understand how the prediction can be changed. We propose CF-GNNExplainer: the first method for generating counterfactual explanations for GNNs, i.e., the minimal perturbations to the input graph data such that the prediction changes. Using only edge deletions, we find that we are able to generate counterfactual examples for the majority of instances across three widely used datasets for GNN explanations, while removing less than 3 edges on average, with at least 94% accuracy. This indicates that CF-GNNExplainer primarily removes edges that are crucial for the original predictions, resulting in minimal counterfactual examples.