Abstract: An apparatus for processing natural language according to an embodiment includes a collection module that collects documents having tags, a parsing module that extracts text from the collected documents and extracts tag-related information on the tag surrounding each extracted text, and a preprocessing module that generates tokens of a preset unit by tokenizing each extracted text, generates token position information for each token in full text of the document, and sets the token and the token position information as training data in matching with the tag-related information.

Abstract: An apparatus for training a document summarization model includes a token generation unit, a named entity recognition unit, and a model training unit. The token generation unit generates document tokens and summarization tokens. The named entity recognition unit assigns named entity token status to a summarization token, recognized as a named entity through NER, and assigns non-named entity token status to the other tokens. The model training unit obtains feature vectors by inputting the plurality of document tokens into an encoder inside a document summarization model, obtains a first loss related to the named entity token, a second loss related to the other tokens, and a total loss using a weighted value by inputting the feature vectors, the summarization tokens, the named entity token, and the non-named entity token into a decoder inside the document summarization model, and trains the document summarization model on the basis of the total loss.

Abstract: An apparatus for training a dialogue summary model according to an embodiment includes a parameter transferer configured to transfer one or more learning parameter values of a pre-trained natural language processing model to a sequence-to-sequence-based dialogue summary model, and a model trainer configured to train the dialogue summary model by using the transferred learning parameter values as initial values for learning parameters of each of an encoder and a decoder in the dialogue summary model.

Abstract: Provided are a method for generating a summary and a system therefor. The method according to some embodiments may include calculating a likelihood loss for a summary model using a first text sample and a first summary sentence corresponding to the first text sample, calculating an unlikelihood loss for the summary model using a second text sample and the first summary sentence, the second text sample being a negative sample generated from the first text sample, and updating the summary model based on the likelihood loss and the unlikelihood loss.

Abstract: An apparatus for embedding a sentence feature vector according to an embodiment includes a sentence acquisitor configured to acquire a first sentence and a second sentence, each including one or more words; a vector extractor configured to extract a first feature vector corresponding to the first sentence and a second feature vector corresponding to the second sentence by independently inputting each of the first sentence and the second sentence into a feature extraction network; and a vector compressor configured to compress the first feature vector and the second feature vector into a first compressed vector and a second compressed vector, respectively, by independently inputting each of the first feature vector and the second feature vector into a convolutional neural network (CNN)-based vector compression network.

Abstract: An apparatus for processing natural language according to an embodiment includes a collection module that collects documents having tags, a parsing module that extracts text from the collected documents and extracts tag-related information on the tag surrounding each extracted text, and a preprocessing module that generates tokens of a preset unit by tokenizing each extracted text, generates token position information for each token in full text of the document, and sets the token and the token position information as training data in matching with the tag-related information.

Abstract: An apparatus for training a document summarization model includes a token generation unit, a named entity recognition unit, and a model training unit. The token generation unit generates document tokens and summarization tokens. The named entity recognition unit assigns named entity token status to a summarization token, recognized as a named entity through NER, and assigns non-named entity token status to the other tokens. The model training unit obtains feature vectors by inputting the plurality of document tokens into an encoder inside a document summarization model, obtains a first loss related to the named entity token, a second loss related to the other tokens, and a total loss using a weighted value by inputting the feature vectors, the summarization tokens, the named entity token, and the non-named entity token into a decoder inside the document summarization model, and trains the document summarization model on the basis of the total loss.

Abstract: An apparatus for training a dialogue summary model according to an embodiment includes a parameter transferer configured to transfer one or more learning parameter values of a pre-trained natural language processing model to a sequence-to-sequence-based dialogue summary model, and a model trainer configured to train the dialogue summary model by using the transferred learning parameter values as initial values for learning parameters of each of an encoder and a decoder in the dialogue summary model.

Abstract: An apparatus for embedding a sentence feature vector according to an embodiment includes a sentence acquisitor configured to acquire a first sentence and a second sentence, each including one or more words; a vector extractor configured to extract a first feature vector corresponding to the first sentence and a second feature vector corresponding to the second sentence by independently inputting each of the first sentence and the second sentence into a feature extraction network; and a vector compressor configured to compress the first feature vector and the second feature vector into a first compressed vector and a second compressed vector, respectively, by independently inputting each of the first feature vector and the second feature vector into a convolutional neural network (CNN)-based vector compression network.

Abstract: An apparatus for calculating a similarity of images according to one embodiment includes a first feature extractor configured to extract an image feature vector from an image, a text region detector configured to detect one or more text object regions included in the image, a second feature extractor configured to extract a text image feature vector from each of the detected text object regions, a third feature extractor configured to recognize text from each of the text object regions and extract a text semantic feature vector from the recognized text, and a concatenator configured to generate a text object feature vector from the text image feature vector and the text semantic feature vector, which are extracted from the same text object region.

Abstract: Apparatuses for camera calibration using a light source are provided, one of apparatus comprises, a n-light sources (n is 3 or more) which can be mounted on the camera, an actual coordinate computation processing unit which irradiates light to an image pickup surface being captured by the camera through the n-light sources to capture an image of an n-sided polygon made up of n-light spots formed on the image pickup surface, and analyses a degree of distortion on the n-sided screen to obtain n or more coordinate pairs obtained by matching the coordinates on the screen and the coordinates on an actual space and a calibration computation processing unit which receives the n or more coordinate pairs as input to convert a two-dimensional coordinate on the screen into a three-dimensional coordinate on the actual space.

Abstract: A system and method for searching for a position of an object are provided. The system includes an image matching unit configured to extract a path from a map indicating a target region, and match a node present in the path and a captured image obtained by a capturing device installed at a position corresponding to the node; a path synthesis unit configured to synthesize the path in the captured image; and an object search unit configured to receive an estimated path of a target object and information related to an exposure direction in an image from a user, and select one or more among a plurality of capturing devices installed in the target region using the received information and the captured image.