Articles

We present BPEmb, a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE). In an evaluation using fine-grained entity typing as testbed, BPEmb performs competitively, and for some languages bet- ter than alternative subword approaches, while requiring vastly fewer resources and no tokenization. BPEmb is …...

In Natural Language Generation (NLG), Referring Expression Generation (REG) lexical choice is the subtask that provides words to express a given input meaning representation. Since lexical choices made in real language use tend to vary greatly across speakers, computational models of lexicalisation have long addressed the issue of human variation …...

In the Natural Language Generation field, Referring Expression Generation (REG) studies often make use of experiments involving human subjects for the collection of corpora of definite descriptions. Experiments of this kind usually make use of web-based settings in which a single subject acts as a speaker with no particular addressee …...

This paper discusses the development and application of a Constraint Grammar parser for the Plains Cree language. The focus of this parser is the identification of relationships between verbs and arguments. The rich morphology and non-configurational syntax of Plains Cree make it an excellent candidate for the application of a …...

Recently, an abundance of deep learning toolkits has been made freely available. These toolkits typically offer the building blocks and sometimes simple example scripts, but designing and training a model still takes a considerable amount of time and knowledge. We present language modeling scripts based on TensorFlow that allow one …...

Learning word vectors from character level is an effective method to improve word embeddings for morphologically rich languages. However, most of these techniques have been applied to languages that are inflectional and written in Roman alphabets. In this paper, we investigate languages that are agglutinative and represented by non-alphabetic scripts, …...

Natural language interfaces to databases systems allow the user to use natural language to interrogate a database. Current systems mainly focus on simple queries but neglect nested queries, which are predominant in real cases. We present a NLIDB system, QUEST, which is able to cope with nested logic queries, without …...

Recently, there has been an increase of interest in constructing corpora containing social-affective interactions. But the availability of multimodal, multilingual, and emotionally rich corpora remains limited. The tasks of recording and transcribing actual human-to-human affective conversations are also tedious and time-consuming. This paper describes construction of a multimodal affective conversational …...

In this paper, we introduce a two-step corpora-based methodology, starting from a corpus of human-human interactions to construct a semi-autonomous system in order to collect a new corpus of human-machine interaction, a step before the development of a fully autonomous system constructed based on the analysis of the collected corpora. …...

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 …...

We present a multimodal corpus that has been recently developed within the MULTISIMO project and targets the investigation and modeling of collaborative aspects of multimodal behavior in groups that perform simple tasks. The corpus consists of a set of human-human interactions recorded in multiple modalities. In each interactive session two …...

Overuse of antibiotics and the attributed bacterial resistance is one of the most serious global public health crises today. Previous research reported that patients’ advocacy for antibiotic treatment was consequential on antibiotic over-prescribing. To investigate how the advocacy and other factors contribute to antibiotic over-prescribing, qualitative and quantitative analysis of …...

Large-scale dialogue data annotated with dialogue states is necessary to model a natural conversation with machines. However, large- scale conventional dialogue corpora are mainly built for specified tasks (e.g., task-oriented systems for restaurant or bus information navigation) with specially designed dialogue states. Text-chat based dialogue corpora have also been built …...

In recent years, the importance of dialogue understanding systems has been increasing. However, it is difficult for computers to deeply understand our daily conversations because we frequently use emotional expressions in conversations. This is partially because there are no large-scale corpora focusing on the detailed relationships between emotions and utterances. …...

In this paper, we present a new hierarchical and extensible schema for dialog representation. The schema captures the pragmatic intents of the conversation independently from any semantic representation. This schema was developed to support computational applications, be applicable to different types of dialogs and domains and enable large-scale non-expert annotation. …...

Speech and speaker recognition is one of the most important research and development areas and has received quite a lot of attention in recent years. The desire to produce a natural form of communication between humans and machines can be considered the motivating factor behind such developments. Speech has the …...

Mental health and well-being are growing issues in western civilizations. But at the same time, psychotherapy and further edu- cation in psychotherapy is a highly demanding occupation, resulting in a severe gap in patient-centered care. The question which arises from recent developments in natural language processing (NLP) and speech recognition …...

This paper describes a search system that we have developed specifically for speech corpus retrieval. It is difficult for speech corpus users to compare and select suitable corpora from the large number of various language resources in the world. It would be more convenient for users if each data center …...

We present GRAIN (German RAdio INterviews) as part of the SFB732 Silver Standard Collection. GRAIN contains German radio interviews and is annotated on multiple linguistic layers. The data has been processed with state-of-the-art tools for text and speech and therefore represents a resource for text-based linguistic research as well as …...

Automatic Speech Recognition (ASR) systems typically degrade in performance when recognizing an accent different from the accents in the training data. One way to overcome this problem without training new models for every accent is adaptation. India has over a hundred major languages, which leads to many variants in Indian …...