Workshop on Open Infrastructures and Analysis Frameworks for HLT (2016)


up

pdf (full)
bib (full)
Proceedings of the Third International Workshop on Worldwide Language Service Infrastructure and Second Workshop on Open Infrastructures and Analysis Frameworks for Human Language Technologies (WLSI/OIAF4HLT2016)

pdf bib
Proceedings of the Third International Workshop on Worldwide Language Service Infrastructure and Second Workshop on Open Infrastructures and Analysis Frameworks for Human Language Technologies (WLSI/OIAF4HLT2016)
Yohei Murakami | Donghui Lin | Nancy Ide | James Pustejovsky

pdf bib
Kathaa : NLP Systems as Edge-Labeled Directed Acyclic MultiGraphs
Sharada Mohanty | Nehal J Wani | Manish Srivastava | Dipti Sharma

We present Kathaa, an Open Source web-based Visual Programming Framework for Natural Language Processing (NLP) Systems. Kathaa supports the design, execution and analysis of complex NLP systems by visually connecting NLP components from an easily extensible Module Library. It models NLP systems an edge-labeled Directed Acyclic MultiGraph, and lets the user use publicly co-created modules in their own NLP applications irrespective of their technical proficiency in Natural Language Processing. Kathaa exposes an intuitive web based Interface for the users to interact with and modify complex NLP Systems; and a precise Module definition API to allow easy integration of new state of the art NLP components. Kathaa enables researchers to publish their services in a standardized format to enable the masses to use their services out of the box. The vision of this work is to pave the way for a system like Kathaa, to be the Lego blocks of NLP Research and Applications. As a practical use case we use Kathaa to visually implement the Sampark Hindi-Panjabi Machine Translation Pipeline and the Sampark Hindi-Urdu Machine Translation Pipeline, to demonstrate the fact that Kathaa can handle really complex NLP systems while still being intuitive for the end user.

pdf bib
LAPPS/Galaxy: Current State and Next Steps
Nancy Ide | Keith Suderman | Eric Nyberg | James Pustejovsky | Marc Verhagen

The US National Science Foundation (NSF) SI2-funded LAPPS/Galaxy project has developed an open-source platform for enabling complex analyses while hiding complexities associated with underlying infrastructure, that can be accessed through a web interface, deployed on any Unix system, or run from the cloud. It provides sophisticated tool integration and history capabilities, a workflow system for building automated multi-step analyses, state-of-the-art evaluation capabilities, and facilities for sharing and publishing analyses. This paper describes the current facilities available in LAPPS/Galaxy and outlines the project’s ongoing activities to enhance the framework.

pdf bib
Automatic Analysis of Flaws in Pre-Trained NLP Models
Richard Eckart de Castilho

Most tools for natural language processing today are based on machine learning and come with pre-trained models. In addition, third-parties provide pre-trained models for popular NLP tools. The predictive power and accuracy of these tools depends on the quality of these models. Downstream researchers often base their results on pre-trained models instead of training their own. Consequently, pre-trained models are an essential resource to our community. However, to be best of our knowledge, no systematic study of pre-trained models has been conducted so far. This paper reports on the analysis of 274 pre-models for six NLP tools and four potential causes of problems: encoding, tokenization, normalization and change over time. The analysis is implemented in the open source tool Model Investigator. Our work 1) allows model consumers to better assess whether a model is suitable for their task, 2) enables tool and model creators to sanity-check their models before distributing them, and 3) enables improvements in tool interoperability by performing automatic adjustments of normalization or other pre-processing based on the models used.

pdf bib
Combining Human Inputters and Language Services to provide Multi-language support system for International Symposiums
Takao Nakaguchi | Masayuki Otani | Toshiyuki Takasaki | Toru Ishida

In this research, we introduce and implement a method that combines human inputters and machine translators. When the languages of the participants vary widely, the cost of simultaneous translation becomes very high. However, the results of simply applying machine translation to speech text do not have the quality that is needed for real use. Thus, we propose a method that people who understand the language of the speaker cooperate with a machine translation service in support of multilingualization by the co-creation of value. We implement a system with this method and apply it to actual presentations. While the quality of direct machine translations is 1.84 (fluency) and 2.89 (adequacy), the system has corresponding values of 3.76 and 3.85.

pdf bib
Recurrent Neural Network with Word Embedding for Complaint Classification
Panuwat Assawinjaipetch | Kiyoaki Shirai | Virach Sornlertlamvanich | Sanparith Marukata

Complaint classification aims at using information to deliver greater insights to enhance user experience after purchasing the products or services. Categorized information can help us quickly collect emerging problems in order to provide a support needed. Indeed, the response to the complaint without the delay will grant users highest satisfaction. In this paper, we aim to deliver a novel approach which can clarify the complaints precisely with the aim to classify each complaint into nine predefined classes i.e. acces-sibility, company brand, competitors, facilities, process, product feature, staff quality, timing respec-tively and others. Given the idea that one word usually conveys ambiguity and it has to be interpreted by its context, the word embedding technique is used to provide word features while applying deep learning techniques for classifying a type of complaints. The dataset we use contains 8,439 complaints of one company.

pdf bib
Universal dependencies for Uyghur
Marhaba Eli | Weinila Mushajiang | Tuergen Yibulayin | Kahaerjiang Abiderexiti | Yan Liu

The Universal Dependencies (UD) Project seeks to build a cross-lingual studies of treebanks, linguistic structures and parsing. Its goal is to create a set of multilingual harmonized treebanks that are designed according to a universal annotation scheme. In this paper, we report on the conversion of the Uyghur dependency treebank to a UD version of the treebank which we term the Uyghur Universal Dependency Treebank (UyDT). We present the mapping of the Uyghur dependency treebank’s labelling scheme to the UD scheme, along with a clear description of the structural changes required in this conversion.

pdf bib
A non-expert Kaldi recipe for Vietnamese Speech Recognition System
Hieu-Thi Luong | Hai-Quan Vu

In this paper we describe a non-expert setup for Vietnamese speech recognition system using Kaldi toolkit. We collected a speech corpus over fifteen hours from about fifty Vietnamese native speakers and using it to test the feasibility of our setup. The essential linguistic components for the Automatic Speech Recognition (ASR) system was prepared basing on the written form of the language instead of expertise knowledge on linguistic and phonology as commonly seen in rich resource languages like English. The modeling of tones by integrating them into the phoneme and using the phonetic decision tree is also discussed. Experimental results showed this setup for ASR systems does yield competitive results while still have potentials for further improvements.

pdf bib
Evaluating Ensemble Based Pre-annotation on Named Entity Corpus Construction in English and Chinese
Tingming Lu | Man Zhu | Zhiqiang Gao | Yaocheng Gui

Annotated corpora are crucial language resources, and pre-annotation is an usual way to reduce the cost of corpus construction. Ensemble based pre-annotation approach combines multiple existing named entity taggers and categorizes annotations into normal annotations with high confidence and candidate annotations with low confidence, to reduce the human annotation time. In this paper, we manually annotate three English datasets under various pre-annotation conditions, report the effects of ensemble based pre-annotation, and analyze the experimental results. In order to verify the effectiveness of ensemble based pre-annotation in other languages, such as Chinese, three Chinese datasets are also tested. The experimental results show that the ensemble based pre-annotation approach significantly reduces the number of annotations which human annotators have to add, and outperforms the baseline approaches in reduction of human annotation time without loss in annotation performance (in terms of F1-measure), on both English and Chinese datasets.

pdf bib
An Ontology for Language Service Composability
Yohei Murakami | Takao Nakaguchi | Donghui Lin | Toru Ishida

Fragmentation and recombination is a key to create customized language environments for supporting various intercultural activities. Fragmentation provides various language resource components for the customized language environments and recombination builds each language environment according to user’s request by combining these components. To realize this fragmentation and recombination process, existing language resources (both data and programs) should be shared as language services and combined beyond mismatch of their service interfaces. To address this issue, standardization is inevitable: standardized interfaces are necessary for language services as well as data format required for language resources. Therefore, we have constructed a hierarchy of language services based on inheritance of service interfaces, which is called language service ontology. This ontology allows users to create a new customized language service that is compatible with existing ones. Moreover, we have developed a dynamic service binding technology that instantiates various executable customized services from an abstract workflow according to user’s request. By using the ontology and service binding together, users can bind the instantiated language service to another abstract workflow for a new customized one.

pdf bib
Between Platform and APIs: Kachako API for Developers
Yoshinobu Kano

Different types of users require different functions in NLP software. It is difficult for a single platform to cover all types of users. When a framework aims to provide more interoperability, users are required to learn more concepts; users’ application designs are restricted to be compliant with the framework. While an interoperability framework is useful in certain cases, some types of users will not select the framework due to the learning cost and design restrictions. We suggest a rather simple framework for the interoperability aiming at developers. Reusing an existing NLP platform Kachako, we created an API oriented NLP system. This system loosely couples rich high-end functions, including annotation visualizations, statistical evaluations, an-notation searching, etc. This API do not require users much learning cost, providing customization ability for power users while also allowing easy users to employ many GUI functions.