Junji Tomita

Calculating similarity between texts using graph-based text representation model

Knowledge discovery from a large volumes of texts usually requires many complex analysis steps. The graph-based text representation model has been proposed to simplify the steps. The model represents texts in a formal manner, Subject Graphs, and provides text handling operations whose inputs and outputs are identical in form, i.e. a set of subject graphs, so they can be combined in any order. A subject graph uses node weight to represent the significance of each term, and link weight to represent that of each term-term association. This paper concentrates on the algorithms for making subject graphs and calculating the similarity between them. An evaluation shows that Subject Graphs can calculate the similarity between texts more precisely than term vectors, since they incorporate the significance of association between terms.

Automatically Generating Head Nods with Linguistic Information.

In addition to verbal behavior, nonverbal behavior is an important aspect for an embodied dialogue system to be able to conduct a smooth conversation with the user. Researchers have focused on automatically generating nonverbal behavior from speech and language information of dialogue systems. We propose a model to generate head nods accompanying an utterance from natural language. To the best of our knowledge, previous studies generated nods from the final words at the end of an utterance, i.e. bag of words. In this study, we focused on various text analyzed using linguistic information such as dialog act, part of speech, a large-scale Japanese thesaurus, and word position in a sentence. First, we compiled a Japanese corpus of 24 dialogues including utterance and nod information. Next, using the corpus, we created a model that generates nod during a phrase by using dialog act, part of speech, a large-scale Japanese thesaurus, word position in a sentence in addition to bag of words. The results indicate that our model outperformed a model using only bag of words and chance level. The results indicate that dialog act, part of speech, the large-scale Japanese thesaurus, and word position are useful to generate nods. Moreover, the model using all types of linguistic information had the highest performance. This result indicates that several types of linguistic information have the potential to be strong predictors with which to generate nods automatically.

Retrieve-and-Read: Multi-task Learning of Information Retrieval and Reading Comprehension

This study considers the task of machine reading at scale (MRS) wherein, given a question, a system first performs the information retrieval (IR) task of finding relevant passages in a knowledge source and then carries out the reading comprehension (RC) task of extracting an answer span from the passages. Previous MRS studies, in which the IR component was trained without considering answer spans, struggled to accurately find a small number of relevant passages from a large set of passages. In this paper, we propose a simple and effective approach that incorporates the IR and RC tasks by using supervised multi-task learning in order that the IR component can be trained by considering answer spans. Experimental results on the standard benchmark, answering SQuAD questions using the full Wikipedia as the knowledge source, showed that our model achieved state-of-the-art performance. Moreover, we thoroughly evaluated the individual contributions of our model components with our new Japanese dataset and SQuAD. The results showed significant improvements in the IR task and provided a new perspective on IR for RC: it is effective to teach which part of the passage answers the question rather than to give only a relevance score to the whole passage.

Query Expansion with Neural Question-to-Answer Translation for FAQ-based Question Answering

We propose a novel Frequently Asked Question (FAQ) retrieval technique with a neural query expansion model. With the growth in Question Answering systems and mobile communications, FAQ retrieval systems have become widely used in site searches and call center support. However, FAQ retrieval often has lexical gaps between queries and answer documents. To bridge these gaps, we design a query expansion model on the basis of an Encoder-Decoder model as a type of deep neural network. The model learns the words that appear in answers for questions using Q&A pair documents and generates the expanded queries from inputted queries to retrieve answer documents. We evaluate our proposed technique in a multi-domain FAQ retrieval task. Experimental results show that our technique retrieves FAQs more accurately than the previous methods.

Analyzing Gaze Behavior and Dialogue Act during Turn-taking for Estimating Empathy Skill Level

We explored the gaze behavior towards the end of utterances and dialogue act (DA), i.e., verbal-behavior information indicating the intension of an utterance, during turn-keeping/changing to estimate empathy skill levels in multiparty discussions. This is the first attempt to explore the relationship between such a combination. First, we collected data on Davis Interpersonal Reactivity Index (which measures empathy skill level), utterances that include the DA categories of Provision, Self-disclosure, Empathy, Turn-yielding, and Others, and gaze behavior from participants in four-person discussions. The results of analysis indicate that the gaze behavior accompanying utterances that include these DA categories during turn-keeping/changing differs in accordance with peoples empathy skill levels. The most noteworthy result was that speakers with low empathy skill levels tend to avoid making eye contact with the listener when the DA category is Self-disclosure during turn-keeping. However, they tend to maintain eye contact when the DA category is Empathy. A listener who has a high empathy skill level often looks away from the speaker during turn-changing when the DA category of a speakers utterance is Provision or Empathy. There was also no difference in gaze behavior between empathy skill levels when the DA category of the speakers utterance was turn-yielding. From these findings, we constructed and evaluated models for estimating empathy skill level using gaze behavior and DA information. The evaluation results indicate that using both gaze behavior and DA during turn-keeping/changing is effective for estimating an individuals empathy skill level in multi-party discussions.