An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

A mobile terminal including a body; a touchscreen provided to a front and extending to side of the body and configured to display content; and a controller configured to detect one side of the body comes into contact with one side of an external terminal, display a first area on the touchscreen corresponding to a contact area of the body and the external terminal and a second area including the content, receive an input of moving the content displayed in the second area to the first area, display the content in the first area, and share the content in the first area with the external terminal.

Mobile terminal and method for controlling the same

We present a syntax-based statistical translation model. Our model transforms a source-language parse tree into a target-language string by applying stochastic operations at each node. These operations capture linguistic differences such as word order and case marking. Model parameters are estimated in polynomial time using an EM algorithm. The model produces word alignments that are better than those produced by IBM Model 5.

https://faculty.washington.edu/fxia/courses/LING580MT/yamada_2001.pdf

A Syntax-based Statistical Translation Model

An information retrieval system that deals with the problems of synonymy, polysemy, and retrieval by concept by allowing for a wide margin of uncertainty in the initial choice of keywords in a query. For each input query vector and an information matrix, the disclosed system solves an optimization problem which maximizes the stability of a solution at a given level of misfit. The disclosed system may include a decomposition of the information matrix in terms of orthogonal basis functions. Each basis encodes groups of conceptually related keywords. The bases are arranged in order of decreasing statistical relevance to a query. The disclosed search engine approximates the input query with a weighted sum of the first few bases. Other commercial applications than the disclosed search engine can also be built on the disclosed techniques.

Inverse inference engine for high performance web search

Beginning with the basic issues of NLP, this chapter aims to chart the major research activities in this area since the last ARIST Chapter in 1996 (Haas, 1996), including: (i) natural language text processing systems - text summarization, information extraction, information retrieval, etc., including domain-specific applications; (ii) natural language interfaces; (iii) NLP in the context of www and digital libraries ; and (iv) evaluation of NLP systems.

/pdf/natural-language-processing-1xjqdh0kou.pdf

Natural language processing

A query transformation system and method capable of not only solving an ambiguousness of words involved in the transformation of queries from one language to another language, but also executing its processing independently of the processing of an information retrieval system used, so that it can be applied to a variety of information retrieval systems, thereby enabling the information retrieval system used to function as a multilingual information retrieval system. The system includes a translation generator for generating all possible translations of an input query consisting of a source language by reference to a translation dictionary, a semantic category verifier for receiving the generated translations from the translation generator, and eliminating translations having a low semantic similarity from the received translations, based on a semantic category tree, and a collocation information verifier for receiving the translations, which includes no translation having a low semantic similarity, from the semantic category verifier, and eliminating translations having no collocation from the received translations, based on word collocation information.

Query transformation system and method enabling retrieval of multilingual web documents

DDoS attacks mounted by botnets today target a specific service, mobilizing only a small amount of legitimate-looking traffic to compromise the server. Detecting or blocking such clever attacks by only using anomalous traffic statistics has become difficult, and devising countermeasures has been mostly left to the victim server. In this paper, we investigate how a software-defined network (SDN) can be utilized to overcome the difficulty and effectively block legitimate looking DDoS attacks mounted by a larger number of bots. Specifically, we discuss a DDoS blocking application that runs over the SDN controller while using the standard OpenFlow interface.

A SDN-oriented DDoS blocking scheme for botnet-based attacks

One of the main challenges in Spoken Language Understanding (SLU) is dealing with ‘open-vocabulary’ slots. Recently, SLU models based on neural network were proposed, but it is still difficult to recognize the slots of unknown words or ‘open-vocabulary’ slots because of the high cost of creating a manually tagged SLU dataset. This paper proposes data noising, which reflects the characteristics of the ‘open-vocabulary’ slots, for data augmentation. We applied it to an attention based bi-directional recurrent neural network (Liu and Lane, 2016) and experimented with three datasets: Airline Travel Information System (ATIS), Snips, and MIT-Restaurant. We achieved performance improvements of up to 0.57% and 3.25 in intent prediction (accuracy) and slot filling (f1-score), respectively. Our method is advantageous because it does not require additional memory and it can be applied simultaneously with the training process of the model.

Data Augmentation by Data Noising for Open-vocabulary Slots in Spoken Language Understanding

This paper describes the implementation of FromTo-CLIR, a Web-based natural language interface for cross-language information retrieval, which consists of four parts: query translator, meta-search engine, front-end and back-end processors, and a robust hybrid machine translator. We propose a method that uses a semantic category tree and collocation to resolve the ambiguity of query translation. We use the front-end and back-end processors in which domain identifier determines the domain of the retrieved documents, machine translators translate the retrieved documents and tag manager deals with the HTML tags to preserve the layout of the original web document. To obtain a robust translation within the Web environment, we use a hybrid translation engine that combines a pattern-based module with a rule-based translator and includes pre- and post-fail softeners.

FromTo-CLIR: Web-Based Natural Language Interface for Cross-Language Information Retrieval

This paper presents a chatbot for a Dialogue-Based Computer-Assisted second Language Learning (DB-CALL) system. A DB-CALL system normally leads dialogues by asking questions according to given scenarios. User utterances outside the scenarios are normally considered as semantically improper and simply rejected. In this paper, we assume that raising the freedom of dialogue can stimulate the user's interest in learning. For this, a chatbot based on a search engine with a dialogue corpus has been developed to deal with conversations out of the scenarios. We evaluate the chatbot separately in two different cases: as an independent bot and as an auxiliary system. The results showed that, unlike the independent chatbot system, the chatbot as an auxiliary system showed a much lower turn success ratio.

/pdf/a-chatbot-for-a-dialogue-based-second-language-learning-3qm0nrpgi3.pdf

Young-Kil Kim

Papers

Query transformation system and method enabling retrieval of multilingual web documents

A SDN-oriented DDoS blocking scheme for botnet-based attacks

Data Augmentation by Data Noising for Open-vocabulary Slots in Spoken Language Understanding

FromTo-CLIR: Web-Based Natural Language Interface for Cross-Language Information Retrieval

A Chatbot for a Dialogue-Based Second Language Learning System.