Unstructured documents serving as external knowledge of the dialogues help to generate more informative responses. Previous research focused on knowledge selection (KS) in the document with dialogue. However, dialogue history that is not related to the current dialogue may introduce noise in the KS processing. In this paper, we propose a Compare Aggregate Transformer (CAT) to jointly denoise the dialogue context and aggregate the document information for response generation. We designed two different comparison mechanisms to reduce noise (before and during decoding). In addition, we propose two metrics for evaluating document utilization efficiency based on word overlap. Experimental results on the CMUDoG dataset show that the proposed CAT model outperforms the state-of-the-art approach and strong baselines.
The heavy traffic congestion problem has always been a concern for modern cities. To alleviate traffic congestion, researchers use reinforcement learning (RL) to develop better traffic signal control (TSC) algorithms in recent years. However, most RL models are trained and tested in the same traffic flow environment, which results in a serious overfitting problem. Since the traffic flow environment in the real world keeps varying, these models can hardly be applied due to the lack of generalization ability. Besides, the limited number of accessible traffic flow data brings extra difficulty in testing the generalization ability of the models. In this paper, we design a novel traffic flow generator based on Wasserstein generative adversarial network to generate sufficient diverse and quality traffic flows and use them to build proper training and testing environments. Then we propose a meta-RL TSC framework GeneraLight to improve the generalization ability of TSC models. GeneraLight boosts the generalization performance by combining the idea of flow clustering and model-agnostic meta-learning. We conduct extensive experiments on multiple real-world datasets to show the superior performance of GeneraLight on generalizing to different traffic flows.
With the rapid development in online education, knowledge tracing (KT) has become a fundamental problem which traces students' knowledge status and predicts their performance on new questions. Questions are often numerous in online education systems, and are always associated with much fewer skills. However, the previous literature fails to involve question information together with high-order question-skill correlations, which is mostly limited by data sparsity and multi-skill problems. From the model perspective, previous models can hardly capture the long-term dependency of student exercise history, and cannot model the interactions between student-questions, and student-skills in a consistent way. In this paper, we propose a Graph-based Interaction model for Knowledge Tracing (GIKT) to tackle the above probems. More specifically, GIKT utilizes graph convolutional network (GCN) to substantially incorporate question-skill correlations via embedding propagation. Besides, considering that relevant questions are usually scattered throughout the exercise history, and that question and skill are just different instantiations of knowledge, GIKT generalizes the degree of students' master of the question to the interactions between the student's current state, the student's history related exercises, the target question, and related skills. Experiments on three datasets demonstrate that GIKT achieves the new state-of-the-art performance, with at least 1% absolute AUC improvement.
To drive purchase in online advertising, it is of the advertiser's great interest to optimize the sequential advertising strategy whose performance and interpretability are both important. The lack of interpretability in existing deep reinforcement learning methods makes it not easy to understand, diagnose and further optimize the strategy. In this paper, we propose our Deep Intents Sequential Advertising (DISA) method to address these issues. The key part of interpretability is to understand a consumer's purchase intent which is, however, unobservable (called hidden states). In this paper, we model this intention as a latent variable and formulate the problem as a Partially Observable Markov Decision Process (POMDP) where the underlying intents are inferred based on the observable behaviors. Large-scale industrial offline and online experiments demonstrate our method's superior performance over several baselines. The inferred hidden states are analyzed, and the results prove the rationality of our inference.
Non-autoregressive neural machine translation achieves remarkable inference acceleration compared to autoregressive models. However, current non-autoregressive models still fall behind their autoregressive counterparts in prediction accuracy. We attribute the accuracy gaps to two disadvantages of non-autoregressive models: a) learning simultaneous generation under the overly strong conditional independence assumption; b) lacking explicit target language modeling. In this paper, we propose Glancing Transformer (GLAT) to address the above disadvantages, which reduces the difficulty of learning simultaneous generation and introduces explicit target language modeling in the non-autoregressive setting at the same time. Experiments on several benchmarks demonstrate that our approach significantly improves the accuracy of non-autoregressive models without sacrificing any inference efficiency. In particular, GLAT achieves 30.91 BLEU on WMT 2014 German-English, which narrows the gap between autoregressive models and non-autoregressive models to less than 0.5 BLEU score.
Model-based reinforcement learning approaches leverage a forward dynamics model to support planning and decision making, which, however, may fail catastrophically if the model is inaccurate. Although there are several existing methods dedicated to combating the model error, the potential of the single forward model is still limited. In this paper, we propose to additionally construct a backward dynamics model to reduce the reliance on accuracy in forward model predictions. We develop a novel method, called Bidirectional Model-based Policy Optimization (BMPO) to utilize both the forward model and backward model to generate short branched rollouts for policy optimization. Furthermore, we theoretically derive a tighter bound of return discrepancy, which shows the superiority of BMPO against the one using merely the forward model. Extensive experiments demonstrate that BMPO outperforms state-of-the-art model-based methods in terms of sample efficiency and asymptotic performance.
Two important tasks at the intersection of knowledge graphs and natural language processing are graph-to-text (G2T) and text-to-graph (T2G) conversion. Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG dataset, which is far fewer than the millions of data for other tasks such as machine translation. Consequently, deep learning models in these two fields suffer largely from scarce training data. This work presents the first attempt to unsupervised learning of T2G and G2T via cycle training. We present CycleGT, an unsupervised training framework that can bootstrap from fully non-parallel graph and text datasets, iteratively back translate between the two forms, and use a novel pretraining strategy. Experiments on the benchmark WebNLG dataset show that, impressively, our unsupervised model trained on the same amount of data can achieve performance on par with the supervised models. This validates our framework as an effective approach to overcome the data scarcity problem in the fields of G2T and T2G.
Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution. In this paper, we eliminate this restriction by proposing multi-agent determinantal Q-learning. Our method is established on Q-DPP, an extension of determinantal point process (DPP) with partition-matroid constraint to multi-agent setting. Q-DPP promotes agents to acquire diverse behavioral models; this allows a natural factorization of the joint Q-functions with no need for \emph{a priori} structural constraints on the value function or special network architectures. We demonstrate that Q-DPP generalizes major solutions including VDN, QMIX, and QTRAN on decentralizable cooperative tasks. To efficiently draw samples from Q-DPP, we adopt an existing sample-by-projection sampler with theoretical approximation guarantee. The sampler also benefits exploration by coordinating agents to cover orthogonal directions in the state space during multi-agent training. We evaluate our algorithm on various cooperative benchmarks; its effectiveness has been demonstrated when compared with the state-of-the-art.
Learning a neural response generation model on data synthesized under the adversarial training framework helps to explore more possible responses. However, most of the data synthesized de novo are of low quality due to the vast size of the response space. In this paper, we propose a counterfactual off-policy method to learn on a better synthesis of data. It takes advantage of a real response to infer an alternative that was not taken using a structural casual model. Learning on the counterfactual responses helps to explore the high-reward area of the response space. An empirical study on the DailyDialog dataset shows that our approach significantly outperforms the HRED model as well as the conventional adversarial training approaches.
We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. The classical inverse reinforcement learning (IRL) solution involves bi-level optimization and is of high computational cost. Recent generative adversarial methods formulate the IL problem as occupancy measure matching, which, however, suffer from the notorious training instability and mode-dropping problems. Inspired by recent progress in energy-based model (EBM), in this paper, we propose a novel IL framework named Energy-Based Imitation Learning (EBIL), solving the IL problem via estimating the expert energy as the surrogate reward function through score matching. EBIL combines the idea of both EBM and occupancy measure matching, which enjoys: (1) high model flexibility for expert policy distribution estimation; (2) efficient computation that avoids the previous alternate training fashion. Though motivated by matching the policy between the expert and the agent, we surprisingly find a non-trivial connection between EBIL and the classic Max-Entropy IRL (MaxEnt IRL) approach, and further show that EBIL can be seen as a simpler and more efficient solution of MaxEnt IRL. Extensive experiments show that EBIL can always achieve comparable performance against state-of-the-art methods with less computation cost.