We aim to overcome the lack of diversity in responses of current dialogue systems and to develop a dialogue system that is engaging as a conversational partner. We propose a generator-evaluator model that evaluates multiple responses generated by a response generator and selects the best response by an evaluator. By generating multiple responses, we obtain diverse responses. We conduct human evaluations to compare the output of the proposed system with that of a baseline system. The results of the human evaluations showed that the proposed system's responses were often judged to be better than the baseline system's, and indicated the effectiveness of the proposed method.
相關內容
Regression modeling is the workhorse of statistics and there is a vast literature on estimation of the regression function. It is realized in recent years that in regression analysis the ultimate aim may be the estimation of a level set of the regression function, instead of the estimation of the regression function itself. The published work on estimation of the level set has thus far focused mainly on nonparametric regression, especially on point estimation. In this paper, the construction of confidence sets for the level set of linear regression is considered. In particular, $1-\alpha$ level upper, lower and two-sided confidence sets are constructed for the normal-error linear regression. It is shown that these confidence sets can be easily constructed from the corresponding $1-\alpha$ level simultaneous confidence bands. It is also pointed out that the construction method is readily applicable to other parametric regression models where the mean response depends on a linear predictor through a monotonic link function, which include generalized linear models, linear mixed models and generalized linear mixed models. Therefore the method proposed in this paper is widely applicable. Examples are given to illustrate the method.
Unit testing is one of the most established quality-assurance techniques for software development. One major advantage of unit testing is the adjustable trade-off between efficiency (i.e., testing effort) and effectiveness (i.e., fault-detection probability). To this end, various strategies have been proposed to exploit this trade-off. In particular, test-suite reduction (TSR) reduces the number of (presumably redundant) test cases while testing a single program version. Regression-test selection (RTS) selects test cases for testing consecutive program revisions. However, both TSR and RTS may influence -- or even obstruct -- each others' performance when used in combination. For instance, test cases discarded during TSR for a particular program version may become relevant again for RTS. However, finding a combination of both strategies leading to a reasonable trade-off throughout the version history of a program is an open question. The goal of this paper is to gain a better understanding of the interactions between TSR and RTS with respect to efficiency and effectiveness. To this end, we present a configurable framework called RegreTS for automated unit-testing of C programs. The framework comprises different strategies for TSR and RTS and possible combinations thereof. We apply this framework to a collection of subject systems, delivering several crucial insights. First, TSR has almost always a negative impact on the effectiveness of RTS, yet a positive impact on efficiency. Second, test cases revealing to testers the effect of program modifications between consecutive program versions are far more effective than test cases simply covering modified code parts, yet causing much more testing effort.
The field of neural style transfer has experienced a surge of research exploring different avenues ranging from optimization-based approaches and feed-forward models to meta-learning methods. The developed techniques have not just progressed the field of style transfer, but also led to breakthroughs in other areas of computer vision, such as all of visual synthesis. However, whereas quantitative evaluation and benchmarking have become pillars of computer vision research, the reproducible, quantitative assessment of style transfer models is still lacking. Even in comparison to other fields of visual synthesis, where widely used metrics exist, the quantitative evaluation of style transfer is still lagging behind. To support the automatic comparison of different style transfer approaches and to study their respective strengths and weaknesses, the field would greatly benefit from a quantitative measurement of stylization performance. Therefore, we propose a method to complement the currently mostly qualitative evaluation schemes. We provide extensive evaluations and a large-scale user study to show that the proposed metric strongly coincides with human judgment.
Though chatbots based on large neural models can often produce fluent responses in open domain conversations, one salient error type is contradiction or inconsistency with the preceding conversation turns. Previous work has treated contradiction detection in bot responses as a task similar to natural language inference, e.g., detect the contradiction between a pair of bot utterances. However, utterances in conversations may contain co-references or ellipsis, and using these utterances as is may not always be sufficient for identifying contradictions. This work aims to improve the contradiction detection via rewriting all bot utterances to restore antecedents and ellipsis. We curated a new dataset for utterance rewriting and built a rewriting model on it. We empirically demonstrate that this model can produce satisfactory rewrites to make bot utterances more complete. Furthermore, using rewritten utterances improves contradiction detection performance significantly, e.g., the AUPR and joint accuracy scores (detecting contradiction along with evidence) increase by 6.5% and 4.5% (absolute increase), respectively.
Recently, neural techniques have been used to generate source code automatically. While promising for declarative languages, these approaches achieve much poorer performance on datasets for imperative languages. Since a declarative language is typically embedded in an imperative language (i.e., the turducken-style programming) in real-world software development, the promising results on declarative languages can hardly lead to significant reduction of manual software development efforts. In this paper, we define a new code generation task: given a natural language comment, this task aims to generate a program in a base imperative language with an embedded declarative language. To our knowledge, this is the first turducken-style code generation task. For this task, we present Lyra: a dataset in Python with embedded SQL. This dataset contains 2,000 carefully annotated database manipulation programs from real-world projects. Each program is paired with both a Chinese comment and an English comment. In our experiment, we adopted Transformer, BERT-style, and GPT-style models as baselines. In the best setting, the generation performance of GPT-style models is better than others, where the AST exact matching accuracy is 24% and 25.5% when using Chinese and English comments, respectively. Therefore, we believe that Lyra provides a new challenge for code generation. Yet, overcoming this challenge may significantly boost the applicability of code generation techniques for real-world software development.
Citations in science are being studied from several perspectives. On the one hand, there are approaches such as scientometrics and the science of science, which take a more quantitative perspective. In this chapter I briefly review some of the literature on citations, citation distributions and models of citations. These citations feature prominently in another part of the literature which is dealing with research evaluation and the role of metrics and indicators in that process. Here I briefly review part of the discussion in research evaluation. This also touches on the subject of how citations relate to peer review. Finally, I try to integrate the two literatures with the aim of clarifying what I believe the two can learn from each other. The fundamental problem in research evaluation is that research quality is unobservable. This has consequences for conclusions that we can draw from quantitative studies of citations and citation models. The term "indicators" is a relevant concept in this context, which I try to clarify. Causality is important for properly understanding indicators, especially when indicators are used in practice: when we act on indicators, we enter causal territory. Even when an indicator might have been valid, through its very use, the consequences of its use may invalidate it. By combining citation models with proper causal reasoning and acknowledging the fundamental problem about unobservable research quality, we may hope to make progress.
In multi-turn dialog, utterances do not always take the full form of sentences \cite{Carbonell1983DiscoursePA}, which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog context to generate a reasonable response. Hence, in this paper, we propose to improve the response generation performance by examining the model's ability to answer a reading comprehension question, where the question is focused on the omitted information in the dialog. Enlightened by the multi-task learning scheme, we propose a joint framework that unifies these two tasks, sharing the same encoder to extract the common and task-invariant features with different decoders to learn task-specific features. To better fusing information from the question and the dialog history in the encoding part, we propose to augment the Transformer architecture with a memory updater, which is designed to selectively store and update the history dialog information so as to support downstream tasks. For the experiment, we employ human annotators to write and examine a large-scale dialog reading comprehension dataset. Extensive experiments are conducted on this dataset, and the results show that the proposed model brings substantial improvements over several strong baselines on both tasks. In this way, we demonstrate that reasoning can indeed help better response generation and vice versa. We release our large-scale dataset for further research.
User engagement is a critical metric for evaluating the quality of open-domain dialogue systems. Prior work has focused on conversation-level engagement by using heuristically constructed features such as the number of turns and the total time of the conversation. In this paper, we investigate the possibility and efficacy of estimating utterance-level engagement and define a novel metric, {\em predictive engagement}, for automatic evaluation of open-domain dialogue systems. Our experiments demonstrate that (1) human annotators have high agreement on assessing utterance-level engagement scores; (2) conversation-level engagement scores can be predicted from properly aggregated utterance-level engagement scores. Furthermore, we show that the utterance-level engagement scores can be learned from data. These scores can improve automatic evaluation metrics for open-domain dialogue systems, as shown by correlation with human judgements. This suggests that predictive engagement can be used as a real-time feedback for training better dialogue models.
Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce. In this work, we address the problem of generating coherent multi-sentence texts from the output of an information extraction system, and in particular a knowledge graph. Graphical knowledge representations are ubiquitous in computing, but pose a significant challenge for text generation techniques due to their non-hierarchical nature, collapsing of long-distance dependencies, and structural variety. We introduce a novel graph transforming encoder which can leverage the relational structure of such knowledge graphs without imposing linearization or hierarchical constraints. Incorporated into an encoder-decoder setup, we provide an end-to-end trainable system for graph-to-text generation that we apply to the domain of scientific text. Automatic and human evaluations show that our technique produces more informative texts which exhibit better document structure than competitive encoder-decoder methods.
Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations. In this work, we address both problems by proposing a novel deep person image generation model for synthesizing realistic person images conditional on pose. The model is based on a generative adversarial network (GAN) and used specifically for pose normalization in re-id, thus termed pose-normalization GAN (PN-GAN). With the synthesized images, we can learn a new type of deep re-id feature free of the influence of pose variations. We show that this feature is strong on its own and highly complementary to features learned with the original images. Importantly, we now have a model that generalizes to any new re-id dataset without the need for collecting any training data for model fine-tuning, thus making a deep re-id model truly scalable. Extensive experiments on five benchmarks show that our model outperforms the state-of-the-art models, often significantly. In particular, the features learned on Market-1501 can achieve a Rank-1 accuracy of 68.67% on VIPeR without any model fine-tuning, beating almost all existing models fine-tuned on the dataset.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191