Semi-supervised learning that leverages synthetic data for training has been widely adopted for developing automatic post-editing (APE) models due to the lack of training data. With this aim, we focus on data-synthesis methods to create high-quality synthetic data. Given that APE takes as input a machine-translation result that might include errors, we present a data-synthesis method by which the resulting synthetic data mimic the translation errors found in actual data. We introduce a noising-based data-synthesis method by adapting the masked language model approach, generating a noisy text from a clean text by infilling masked tokens with erroneous tokens. Moreover, we propose selective corpus interleaving that combines two separate synthetic datasets by taking only the advantageous samples to enhance the quality of the synthetic data further. Experimental results show that using the synthetic data created by our approach results in significantly better APE performance than other synthetic data created by existing methods.

Zero-shot slot filling has received considerable attention to cope with the problem of limited available data for the target domain.One of the important factors in zero-shot learning is to make the model learn generalized and reliable representations.For this purpose, we present mcBERT, which stands for 'm'omentum 'c'ontrastive learning with BERT, to develop a robust zero-shot slot filling model.mcBERT uses BERT to initialize the two encoders, the query encoder and key encoder, and is trained by applying momentum contrastive learning.Our experimental results on the SNIPS benchmark show that mcBERT substantially outperforms the previous models, recording a new state-of-theart.Besides, we also show that each component composing mcBERT contributes to the performance improvement.

Automatic Post-Editing (APE) aims to correct errors in the output of a given machine translation (MT) system.Although data-driven approaches have become prevalent also in the APE task as in many other NLP tasks, there has been a lack of qualified training data due to the high cost of manual construction.eSCAPE, a synthetic APE corpus, has been widely used to alleviate the data scarcity, but it might not address genuine APE corpora's characteristic that the post-edited sentence should be a minimally edited revision of the given MT output.Therefore, we propose two new methods of synthesizing additional MT outputs by adapting back-translation to the APE task, obtaining robust enlargements of the existing synthetic APE training dataset 1 .Experimental results on the WMT English-German APE benchmarks demonstrate that our enlarged datasets are effective in improving APE performance.

Automatic post-editing (APE) is the study of correcting translation errors in the output of an unknown machine translation (MT) system and has been considered as a method of improving translation quality without any modification to conventional MT systems. Recently, several variants of Transformer that take both the MT output and its corresponding source sentence as inputs have been proposed for APE; and models introducing an additional attention layer into the encoder to jointly encode the MT output with its source sentence recorded a high-rank in the WMT19 APE shared task. We examine the effectiveness of such joint-encoding strategy in a controlled environment and compare four types of decoder multi-source attention strategies that have been introduced into previous APE models. The experimental results indicate that the joint-encoding strategy is effective and that taking the final encoded representation of the source sentence is the more proper strategy than taking such representation within the same encoder stack. Furthermore, among the multi-source attention strategies combined with the joint-encoding, the strategy that applies attention to the concatenated input representation and the strategy that adds up the individual attention to each input improve the quality of APE results over the strategy using the joint-encoding only.

Machine translation aims to break the language barrier that prevents communication with others and increase access to information. Deaf people face huge language barriers in their daily lives, including access to digital and spoken information. There are very few digital resources for sign language processing. In this article, we present a transfer-based machine translation system for translating Korean-to-Korean Sign Language (KSL) glosses, mainly composed of (1) dictionary-based lexical transfer and (2) a hybrid syntactic transfer based on a data-driven model. In particular, we formulate complicated word reordering problems in syntactic transfer as multi-class classification tasks and propose “syntactically guided” data-driven syntactic transfer. The core part of our study is a neural classification model for reordering order-important constituent pairs with a reordering task that is newly designed for Korean-to-KSL translation. The experiment results evaluated on news transcript data show that the proposed system achieves a BLEU score of 0.512 and a RIBES score of 0.425, significantly improving upon the baseline system performance.

We provide a more optimized model for calculating credibility score of information in SNS. We premeditated two heuristics which using characteristics of the credibility score for each document: (1) Expertise and (2) unbiasedness. Also, we divide the users in SNS into three types: (1) Creator (2) Distributor, and (3) Follower. Our model is designed to calculate Expertise and Un-biasedness for three types of SNS users (Creator, Distributor, and Follower) by using logistic regression model. Our model not only reveals whether the information is 'accurate and unbiased', but also investigates the 'source, distribution channel, and audience' of the information. We expect our credibility scoring will give answers to the 'qualitative problem' our online world is currently facing.

Quality estimation is an important task in machine translation that has attracted increased interest in recent years. A key problem in translation-quality estimation is the lack of a sufficient amount of the quality annotated training data. To address this shortcoming, the Predictor-Estimator was proposed recently by introducing “word prediction” as an additional pre-subtask that predicts a current target word with consideration of surrounding source and target contexts, resulting in a two-stage neural model composed of a predictor and an estimator . However, the original Predictor-Estimator is not trained on a continuous stacking model but instead in a cascaded manner that separately trains the predictor from the estimator. In addition, the Predictor-Estimator is trained based on single-task learning only, which uses target-specific quality-estimation data without using other training data that are available from other-level quality-estimation tasks. In this article, we thus propose a multi-task stack propagation , which extensively applies stack propagation to fully train the Predictor-Estimator on a continuous stacking architecture and multi-task learning to enhance the training data from related other-level quality-estimation tasks. Experimental results on WMT17 quality-estimation datasets show that the Predictor-Estimator trained with multi-task stack propagation provides statistically significant improvements over the baseline models. In particular, under an ensemble setting, the proposed multi-task stack propagation leads to state-of-the-art performance at all the sentence/word/phrase levels for WMT17 quality estimation tasks.

This paper proposes an efficient video coding algorithm for high dynamic range (HDR) video to improve quality of compressed frame using the HEVC Main 10 profile. The proposed scheme applies an adaptive chroma QP offset based on primary of reference picture using multiple picture parameters set (PPS). The result shows improved perceptual quality with negligible bit-rate increase as compared to the anchor used in MPEG HDR/WCG Call for Evidence reference software and its chroma QP offset method.

Recently, quality estimation has been attracting increasing interest from machine translation researchers, aiming at finding a good estimator for the “quality” of machine translation output. The common approach for quality estimation is to treat the problem as a supervised regression/classification task using a quality-annotated noisy parallel corpus, called quality estimation data , as training data. However, the available size of quality estimation data remains small, due to the too-expensive cost of creating such data. In addition, most conventional quality estimation approaches rely on manually designed features to model nonlinear relationships between feature vectors and corresponding quality labels. To overcome these problems, this article proposes a novel neural network architecture for quality estimation task—called the predictor-estimator —that considers word prediction as an additional pre-task. The major component of the proposed neural architecture is a word prediction model based on a modified neural machine translation model—a probabilistic model for predicting a target word conditioned on all the other source and target contexts. The underlying assumption is that the word prediction model is highly related to quality estimation models and is therefore able to transfer useful knowledge to quality estimation tasks. Our proposed quality estimation method sequentially trains the following two types of neural models: (1) Predictor : a neural word prediction model trained from parallel corpora and (2) Estimator : a neural quality estimation model trained from quality estimation data. To transfer word a prediction task to a quality estimation task, we generate quality estimation feature vectors from the word prediction model and feed them into the quality estimation model. The experimental results on WMT15 and 16 quality estimation datasets show that our proposed method has great potential in the various sub-challenges.

This paper presents a novel approach using recurrent neural networks for estimating the quality of machine translation output.A sequence of vectors made by the prediction method is used as the input of the final recurrent neural network.The prediction method uses bi-directional recurrent neural network architecture both on source and target sentence to fully utilize the bi-directional quality information from source and target sentence.Our experiments show that the proposed recurrent neural networks approach achieves a performance comparable to the existing stateof-the-art models for estimating the sentencelevel quality of English-to-Spanish translation.

To provide very high quality and/or high resolution video content under limited bandwidth conditions for transmission or storage, the high efficiency video coding (HEVC) has been recently finalised by the joint collaborative team on video coding. In this study, the authors propose a fast prediction unit (PU) decision method to reduce the computational complexity of HEVC encoder. They use an early PU decision in each coding unit‐level based on spatio‐temporal analyses and depth correlations. They also consider a classification of motion activity. Experimental results show that the encoding complexity can be reduced by up to 38% on average in the random access main profile configuration with only a small bit‐rate increment and a peak signal to noise ratio (PSNR) decrement, compared to high efficiency video coding test model (HM) 7.0 reference software.

H.264/AVC is the most widely used recent video coding standard. It provides a high encoding efficiency but it also has a high computational complexity. The block mode decision for motion estimation is the most time‐consuming procedure. A complexity reduction method for the block mode decision procedure is proposed. To reduce the complexity, all block modes are divided into several candidate block mode groups. The sum of the absolute difference (SAD) value, including the motion cost of each mode, is used as a classification feature to divide the block modes into several groups. A refinement method using a Bayesian model based on the average SAD value is also proposed. For B‐slices, a differential block mode allocation method is suggested. A different number of candidate modes are allocated for lists (list 0, list 1) based on the SAD value of each list after 16 × 16 block motion estimation. The proposed method achieves an average time‐saving for the total encoding time of 65% for IPPP and 66.01% for the hierarchical‐B structure.

The Inversion Transduction Grammar (ITG) constraints have been widely used for word reordering in machine translation studies. They are, however, so restricted that some types of word reordering cannot be handled properly. We analyze three corpora between SVO and SOV languages: Chinese-Korean, English-Japanese, and English-Korean. In our analysis, sentences that require non-ITG word reordering are manually categorized. We also report the results for two quantitative measures that reveal the significance of non-ITG word reordering. In conclusion, we suggest that ITG constraints are insufficient to deal with word reordering in real situations.

In this paper, we propose a fast PU decision method to reduce encoder complexity. We use an early PU decision in each CU-level based on spatio-temporal analyses and depth correlations. We also consider a classification of motion activity. Experimental results show that the encoding complexity can be reduced by up to 37.98% on average in the random access Main profile configuration with only a small bit-rate increment and a PSNR decrement, compared to high efficiency video coding test model (HM) 7.0 reference software.

Block-based motion estimation (ME) has been widely used in various video coding standards due to its effectiveness in removing temporal redundancy. However, this traditional ME technique suffers the limitation that it can only compensate for a pure parallel translation between frames. Various algorithms have been proposed for estimating other motion models, such as zooming, rotating, tilting, and warping. In spite of good performance for these algorithms, they are not used in the current industrial world because of their high computational complexity and incompatibility with current block-based video coding standards that limit their practical usage. In this paper, we present a novel zoom motion estimation (ZME) and motion compensation algorithm using the local area scaling technique. To represent and encode the zoom motion, we introduce a zoom vector (ZV) that either increases or decreases a reference block size. The resized reference block is then interpolated to the size of the current block in order to perform block matching. For fast ZME, we have also designed a 3-D diamond pattern search to reduce the number of unnecessary search points for the ZV. We have integrated the proposed algorithm into H.264/AVC JM reference software. Experimental results show that an average bit-rate savings of 11.01% (up to 16.87%) can be achieved for high-definition size sequences with an average 0.20 dB gain in peak signal-to-noise ratio and a less than 10% time increment in the hierarchical B structure.

The analysis of query logs from blog search engines show that news-related queries occupy a significant portion of the logs. This raises a interesting research question on whether the blogosphere can be used to identify important news stories. In this paper, we present novel approaches to identify important news story headlines from the blogosphere for a given day. The proposed system consists of two components based on the language model framework, the query likelihood and the news headline prior. For the query likelihood, we propose several approaches to estimate the query language model and the news headline language model. We also suggest several criteria to evaluate the news headline prior that is the prior belief about the importance or newsworthiness of the news headline for a given day. Experimental results show that our system significantly outperforms a baseline system. Specifically, the proposed approach gives 2.62% and 10.19% further increases in MAP and P@5 over the best performing result of the TREC'09 Top Stories Identification Task.

Blog feed search aims to identify a blog feed with a recurring interest in a given topic. In this paper, we investigate the "pseudo-relevance feedback" for blog feed search task, where its unit of relevance judgment is not based on a blog post but a blog feed (the collection of all its constituent posts). This paper focuses on two characteristics of feed search task, blog feed's topical diversity and multifaceted property of query. We propose a novel feed-level selection of local posts which uses only highly relevant local posts in each top-ranked feed, in order to capture the correct and diverse relevant information to a given topic. Experimental results show that the proposed approach outperforms traditional feedback approaches. Especially, the proposed approach gives 2% further increase of nDCG over the best performing result of TREC '08 Blog Distillation Task.

Language modeling approaches have been effectively dealing with the dependency among query terms based on N-gram such as bigram or trigram models. However, bigram language models suffer from adjacency-sparseness problem which means that dependent terms are not always adjacent in documents, but can be far from each other, sometimes with distance of a few sentences in a document. To resolve the adjacency-sparseness problem, this paper proposes a new type of bigram language model by explicitly incorporating the proximity feature between two adjacent terms in a query. Experimental results on three test collections show that the proposed bigram language model significantly improves previous bigram model as well as Tao's approach, the state-of-art method for proximity-based method.

In natural language database interfaces (NLDBI), manual construction of translation knowledge normally undermines domain portability because of its expensive human intervention. To overcome this, this paper proposes linguistically-motivated database semantics in order to systematically construct translation knowledge. Database semantics consists of two structures which are designed to function as a translation dictionary, and to contain selectional restriction constraints on domain classes. The database semantics is semi-automatically obtained from a semantic data model for a target database. Based on this database semantics, a conceptual NLDBI translation scheme is developed. Translating a natural language question into a database query suffers from the translation ambiguity problem, which has not received significant attention in this field. To deal with translation ambiguity, we suggest an ambiguity resolution method based on the proposed database semantics. Experiments showed the usefulness of the proposed database semantics and its disambiguation procedures.

Most errors in Korean morphological analysis and part-of-speech (POS) tagging are caused by unknown morphemes. This paper presents a syllable-pattern-based generalized unknown-morpheme-estimation method with POSTAG (POStech TAGger), 1 which is a statistical and rule-based hybrid POS tagging system. This method of guessing unknown morphemes is based on a combination of a morpheme pattern dictionary that encodes general lexical patterns of Korean morphemes with a posteriori syllable trigram estimation. The syllable trigrams help to calculate lexical probabilities of the unknown morphemes and are utilized to search for the best tagging result. This method can guess the POS tags of unknown morphemes regardless of their numbers and/or positions in an eojeol (a Korean spacing unit similar to an English word), which is not possible with other systems for tagging Korean. In a series of experiments using three different domain corpora, the system achieved a 97% tagging accuracy even though 10% of the morphemes in the test corpora were unknown. It also achieved very high coverage and accuracy of estimation for all classes of unknown morphemes. 1 The binary code of POSTAG is open to the public for research and evaluation purposes at http://nlp.postech.ac.kr/. Follow the link OpenResources→DownLoad.

Both dictionary-based and rule-based methods on grapheme-to-phoneme conversion have their own advantages and limitations. For example, a large sized phonetic dictionary and complex morphophonemic rules are required for the dictionary-based method and the LTS (letter to sound) rule-based method itself cannot model the complete morphophonemic constraints.This paper describes a grapheme-to-phoneme conversion method for Korean using a dictionary-based and rule-based hybrid method with a phonetic pattern dictionary and CCV (consonant consonant vowel) LTS (letter to sound) rules. The phonetic pattern dictionary, standing for the dictionary-based method, contains entries in the form of a morpheme pattern and its phonetic pattern. The patterns represent candidate phonological changes in left and right boundaries of morphemes. Obviously, the CCV LTS rules stand for the rule-based method. The rules are in charge of grapheme-to-phoneme conversion within morphemes.The conversion method consists of mainly two steps including morpheme to phoneme conversion and morphophonemic connectivity check, and two preprocessing steps including phrase break prediction and morpheme normalization. Phrase break prediction presumes phrase breaks using the stochastic method on part-of-speech (POS) information. Morpheme normalization is to replace non-Korean symbols with their corresponding standard Korean graphemes. In the morpheme-phoneticizing module, each morpheme in the phrase is converted into phonetic patterns by looking it up in the phonetic pattern dictionary. Graphemes within a morpheme are grouped into CCV units and converted into phonemes by the CCV LTS rules. The morphophonemic connectivity table supports grammaticality checking of the two adjacent phonetic morphemes.In experiments with a non-Korean symbol free corpus of 4,973 sentences, we achieved a 99.98% grapheme-to-phoneme conversion performance rate and a 99.0% sentence conversion performance rate. With a broadcast news corpus of 621 sentences, 99.7% of the graphemes and 86.6% of the sentences are correctly converted. The full Korean TTS (Text-to-Speech) system is now being implemented using this conversion method.

This paper describes a method for disambiguating word senses by using semi-automatically constructed ontology. The ontology stores rich semantic constraints among 1,110 concepts, and enables a natural language processing system to resolve semantic ambiguities by making inferences with the concept network of the ontology. In order to acquire a reasonably practical ontology in limited time and with less manpower, we extend the existing Kadokawa thesaurus by inserting additional semantic relations into its hierarchy, which are classified as case relations and other semantic relations. The former can be obtained by converting valency information and case frames from previously-built electronic dictionaries used in machine translation. The latter can be acquired from concept co-occurrence information, which is extracted automatically from large corpora. In our practical machine translation system, our word sense disambiguation method achieved a 9.2% improvement over methods which do not use an ontology for Korean translation.

In a dictionary-based query translation for cross-language text retrieval, transfer ambiguity is one of the main causes of performance deterioration, but the problem has not received significant attention in this field. To resolve transfer ambiguity, this paper proposes a two-phase query translation based on term reweighting, which uses a bilingual transfer dictionary, originally designed for machine translation. In general, source language query terms each show some word association with others, so that their correct translations should be more likely to co-occur in target documents. Based on this simple intuition, the first phase discriminates more relevant target documents from the others. Using statistical and ranking information from the highly relevant documents, the second phase then converts a translated query vector into reweighted form to add an extra weight on probably correct target terms. In experiments, the results were remarkable: the proposed method achieved almost the same performance as the monolingual IR system, actually contributing to an improvement of precision by about 9% over a baseline system.

This paper proposes a method for lexical transfer ambiguity resolution using corpus and conceptual information. Previous researches have restricted the use of linguistic knowledge to the lexical level. Since the extracted knowledge is stored in words themselves, these methods require a large amount of space with a low recall rate. On the contrary, we resolve word sense ambiguity by using concept co-occurrence information extracted from an automatically sense-tagged corpus. In one experiment, it achieved, on average, a precision of 82.4% for nominal words, and 83% for verbal words. Considering that the test corpus is completely irrelevant to the learning corpus, this is a promising result.