Situated conversations, which refer to visual information as visual question answering (VQA), often contain ambiguities caused by reliance on directive information. This problem is exacerbated because some languages, such as Japanese, often omit subjective or objective terms. Such ambiguities in questions are often clarified by the contexts in conversational situations, such as joint attention with a user or user gaze information. In this study, we propose the Gaze-grounded VQA dataset (GazeVQA) that clarifies ambiguous questions using gaze information by focusing on a clarification process complemented by gaze information. We also propose a method that utilizes gaze target estimation results to improve the accuracy of GazeVQA tasks. Our experimental results showed that the proposed method improved the performance in some cases of a VQA system on GazeVQA and identified some typical problems of GazeVQA tasks that need to be improved.
Understanding expressions that refer to the physical world is crucial for such human-assisting systems in the real world, as robots that must perform actions that are expected by users. In real-world reference resolution, a system must ground the verbal information that appears in user interactions to the visual information observed in egocentric views. To this end, we propose a multimodal reference resolution task and construct a Japanese Conversation dataset for Real-world Reference Resolution (J-CRe3). Our dataset contains egocentric video and dialogue audio of real-world conversations between two people acting as a master and an assistant robot at home. The dataset is annotated with crossmodal tags between phrases in the utterances and the object bounding boxes in the video frames. These tags include indirect reference relations, such as predicate-argument structures and bridging references as well as direct reference relations. We also constructed an experimental model and clarified the challenges in multimodal reference resolution tasks.
In this paper, we propose a novel framework for evaluating style-shifting in social media conversations. Our proposed framework captures changes in an individual’s conversational style based on surprisals predicted by a personalized neural language model for individuals. Our personalized language model integrates not only the linguistic contents of conversations but also non-linguistic factors, such as social meanings, including group membership, personal attributes, and individual beliefs. We incorporate these factors directly or implicitly into our model, leveraging large, pre-trained language models and feature vectors derived from a relationship graph on social media. Compared to existing models, our personalized language model demonstrated superior performance in predicting an individual’s language in a test set. Furthermore, an analysis of style-shifting utilizing our proposed metric based on our personalized neural language model reveals a correlation between our metric and various conversation factors as well as human evaluation of style-shifting.
Narratives include a rich source of events unfolding over time and context. Automatic understanding of these events provides a summarised comprehension of the narrative for further computation (such as reasoning). In this paper, we study the Information Status (IS) of the events and propose a novel challenging task: the automatic identification of new events in a narrative. We define an event as a triplet of subject, predicate, and object. The event is categorized as new with respect to the discourse context and whether it can be inferred through commonsense reasoning. We annotated a publicly available corpus of narratives with the new events at sentence level using human annotators. We present the annotation protocol and study the quality of the annotation and the difficulty of the task. We publish the annotated dataset, annotation materials, and machine learning baseline models for the task of new event extraction for narrative understanding.
Question answering (QA) with disambiguation questions is essential for practical QA systems because user questions often do not contain information enough to find their answers. We call this task clarifying question answering, a task to find answers to ambiguous user questions by disambiguating their intents through interactions. There are two major problems in building a clarifying question answering system: data preparation of possible ambiguous questions and the generation of clarifying questions. In this paper, we tackle these problems by sentence generation methods using sentence structures. Ambiguous questions are generated by eliminating a part of a sentence considering the sentence structure. Clarifying the question generation method based on case frame dictionary and sentence structure is also proposed. Our experimental results verify that our pseudo ambiguous question generation successfully adds ambiguity to questions. Moreover, the proposed clarifying question generation recovers the performance drop by asking the user for missing information.
Human-assisting systems such as dialogue systems must take thoughtful, appropriate actions not only for clear and unambiguous user requests, but also for ambiguous user requests, even if the users themselves are not aware of their potential requirements. To construct such a dialogue agent, we collected a corpus and developed a model that classifies ambiguous user requests into corresponding system actions. In order to collect a high-quality corpus, we asked workers to input antecedent user requests whose pre-defined actions could be regarded as thoughtful. Although multiple actions could be identified as thoughtful for a single user request, annotating all combinations of user requests and system actions is impractical. For this reason, we fully annotated only the test data and left the annotation of the training data incomplete. In order to train the classification model on such training data, we applied the positive/unlabeled (PU) learning method, which assumes that only a part of the data is labeled with positive examples. The experimental results show that the PU learning method achieved better performance than the general positive/negative (PN) learning method to classify thoughtful actions given an ambiguous user request.
Expressing emotion is known as an efficient way to persuade one’s dialogue partner to accept one’s claim or proposal. Emotional expression in speech can express the speaker’s emotion more directly than using only emotion expression in the text, which will lead to a more persuasive dialogue. In this paper, we built a speech dialogue corpus in a persuasive scenario that uses emotional expressions to build a persuasive dialogue system with emotional expressions. We extended an existing text dialogue corpus by adding variations of emotional responses to cover different combinations of broad dialogue context and a variety of emotional states by crowd-sourcing. Then, we recorded emotional speech consisting of of collected emotional expressions spoken by a voice actor. The experimental results indicate that the collected emotional expressions with their speeches have higher emotional expressiveness for expressing the system’s emotion to users.
Word embeddings, which often represent such analogic relations as king - man + woman queen, can be used to change a word’s attribute, including its gender. For transferring king into queen in this analogy-based manner, we subtract a difference vector man - woman based on the knowledge that king is male. However, developing such knowledge is very costly for words and attributes. In this work, we propose a novel method for word attribute transfer based on reflection mappings without such an analogy operation. Experimental results show that our proposed method can transfer the word attributes of the given words without changing the words that do not have the target attributes.
Spoken language understanding (SLU), which converts user requests in natural language to machine-interpretable expressions, is becoming an essential task. The lack of training data is an important problem, especially for new system tasks, because existing SLU systems are based on statistical approaches. In this paper, we proposed to use two sources of the “wisdom of crowds,” crowdsourcing and knowledge community website, for improving the SLU system. We firstly collected paraphrasing variations for new system tasks through crowdsourcing as seed data, and then augmented them using similar questions from a knowledge community website. We investigated the effects of the proposed data augmentation method in SLU task, even with small seed data. In particular, the proposed architecture augmented more than 120,000 samples to improve SLU accuracies.
We propose a novel method for selecting coherent and diverse responses for a given dialogue context. The proposed method re-ranks response candidates generated from conversational models by using event causality relations between events in a dialogue history and response candidates (e.g., “be stressed out” precedes “relieve stress”). We use distributed event representation based on the Role Factored Tensor Model for a robust matching of event causality relations due to limited event causality knowledge of the system. Experimental results showed that the proposed method improved coherency and dialogue continuity of system responses.
Building a controllable neural conversation model (NCM) is an important task. In this paper, we focus on controlling the responses of NCMs by using dialogue act labels of responses as conditions. We introduce an adversarial learning framework for the task of generating conditional responses with a new objective to a discriminator, which explicitly distinguishes sentences by using labels. This change strongly encourages the generation of label-conditioned sentences. We compared the proposed method with some existing methods for generating conditional responses. The experimental results show that our proposed method has higher controllability for dialogue acts even though it has higher or comparable naturalness to existing methods.
Positive emotion elicitation seeks to improve user’s emotional state through dialogue system interaction, where a chat-based scenario is layered with an implicit goal to address user’s emotional needs. Standard neural dialogue system approaches still fall short in this situation as they tend to generate only short, generic responses. Learning from expert actions is critical, as these potentially differ from standard dialogue acts. In this paper, we propose using a hierarchical neural network for response generation that is conditioned on 1) expert’s action, 2) dialogue context, and 3) user emotion, encoded from user input. We construct a corpus of interactions between a counselor and 30 participants following a negative emotional exposure to learn expert actions and responses in a positive emotion elicitation scenario. Instead of relying on the expensive, labor intensive, and often ambiguous human annotations, we unsupervisedly cluster the expert’s responses and use the resulting labels to train the network. Our experiments and evaluation show that the proposed approach yields lower perplexity and generates a larger variety of responses.
Training of neural machine translation (NMT) models usually uses mini-batches for efficiency purposes. During the mini-batched training process, it is necessary to pad shorter sentences in a mini-batch to be equal in length to the longest sentence therein for efficient computation. Previous work has noted that sorting the corpus based on the sentence length before making mini-batches reduces the amount of padding and increases the processing speed. However, despite the fact that mini-batch creation is an essential step in NMT training, widely used NMT toolkits implement disparate strategies for doing so, which have not been empirically validated or compared. This work investigates mini-batch creation strategies with experiments over two different datasets. Our results suggest that the choice of a mini-batch creation strategy has a large effect on NMT training and some length-based sorting strategies do not always work well compared with simple shuffling.
We demonstrate an information navigation system for sightseeing domains that has a dialogue interface for discovering user interests for tourist activities. The system discovers interests of a user with focus detection on user utterances, and proactively presents related information to the discovered user interest. A partially observable Markov decision process (POMDP)-based dialogue manager, which is extended with user focus states, controls the behavior of the system to provide information with several dialogue acts for providing information. We transferred the belief-update function and the policy of the manager from other system trained on a different domain to show the generality of defined dialogue acts for our information navigation system.
In a dialogue system, the dialogue manager selects one of several system actions and thereby determines the system’s behaviour. Defining all possible system actions in a dialogue system by hand is a tedious work. While efforts have been made to automatically generate such system actions, those approaches are mostly focused on providing functional system behaviour. Adapting the system behaviour to the user becomes a difficult task due to the limited amount of system actions available. We aim to increase the adaptability of a dialogue system by automatically generating variants of system actions. In this work, we introduce an approach to automatically generate action variants for elaborateness and indirectness. Our proposed algorithm extracts RDF triplets from a knowledge base and rates their relevance to the original system action to find suitable content. We show that the results of our algorithm are mostly perceived similarly to human generated elaborateness and indirectness and can be used to adapt a conversation to the current user and situation. We also discuss where the results of our algorithm are still lacking and how this could be improved: Taking into account the conversation topic as well as the culture of the user is likely to have beneficial effect on the user’s perception.
The IWSLT 2017 evaluation campaign has organised three tasks. The Multilingual task, which is about training machine translation systems handling many-to-many language directions, including so-called zero-shot directions. The Dialogue task, which calls for the integration of context information in machine translation, in order to resolve anaphoric references that typically occur in human-human dialogue turns. And, finally, the Lecture task, which offers the challenge of automatically transcribing and translating real-life university lectures. Following the tradition of these reports, we will described all tasks in detail and present the results of all runs submitted by their participants.
In this paper, we propose a new method for calculating the output layer in neural machine translation systems. The method is based on predicting a binary code for each word and can reduce computation time/memory requirements of the output layer to be logarithmic in vocabulary size in the best case. In addition, we also introduce two advanced approaches to improve the robustness of the proposed model: using error-correcting codes and combining softmax and binary codes. Experiments on two English-Japanese bidirectional translation tasks show proposed models achieve BLEU scores that approach the softmax, while reducing memory usage to the order of less than 1/10 and improving decoding speed on CPUs by x5 to x10.
Emotional aspects play a vital role in making human communication a rich and dynamic experience. As we introduce more automated system in our daily lives, it becomes increasingly important to incorporate emotion to provide as natural an interaction as possible. To achieve said incorporation, rich sets of labeled emotional data is prerequisite. However, in Japanese, existing emotion database is still limited to unimodal and bimodal corpora. Since emotion is not only expressed through speech, but also visually at the same time, it is essential to include multiple modalities in an observation. In this paper, we present the first audio-visual emotion corpora in Japanese, collected from 14 native speakers. The corpus contains 100 minutes of annotated and transcribed material. We performed preliminary emotion recognition experiments on the corpus and achieved an accuracy of 61.42% for five classes of emotion.