Using sarcasm on social media platforms to express negative opinions towards a person or object has become increasingly common.However,detecting sarcasm in various forms of communication can be difficult due to confli...Using sarcasm on social media platforms to express negative opinions towards a person or object has become increasingly common.However,detecting sarcasm in various forms of communication can be difficult due to conflicting sentiments.In this paper,we introduce a contrasting sentiment-based model for multimodal sarcasm detection(CS4MSD),which identifies inconsistent emotions by leveraging the CLIP knowledge module to produce sentiment features in both text and image.Then,five external sentiments are introduced to prompt the model learning sentimental preferences among modalities.Furthermore,we highlight the importance of verbal descriptions embedded in illustrations and incorporate additional knowledge-sharing modules to fuse such imagelike features.Experimental results demonstrate that our model achieves state-of-the-art performance on the public multimodal sarcasm dataset.展开更多
Emotion cause extraction(ECE)task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently.However,current work neglects the implicit emotion expressed without an...Emotion cause extraction(ECE)task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently.However,current work neglects the implicit emotion expressed without any explicit emotional keywords,which appears more frequently in application scenarios.The lack of explicit emotion information makes it extremely hard to extract emotion causes only with the local context.Moreover,an entire event is usually across multiple clauses,while existing work merely extracts cause events at clause level and cannot effectively capture complete cause event information.To address these issues,the events are first redefined at the tuple level and a span-based tuple-level algorithm is proposed to extract events from different clauses.Based on it,a corpus for implicit emotion cause extraction that tries to extract causes of implicit emotions is constructed.The authors propose a knowledge-enriched jointlearning model of implicit emotion recognition and implicit emotion cause extraction tasks(KJ-IECE),which leverages commonsense knowledge from ConceptNet and NRC_VAD to better capture connections between emotion and corresponding cause events.Experiments on both implicit and explicit emotion cause extraction datasets demonstrate the effectiveness of the proposed model.展开更多
The performance of a machine translation system heavily depends on the quantity and quality of the bilingual language resource. However,getting a parallel corpus,which has a large scale and is of high quality,is a ver...The performance of a machine translation system heavily depends on the quantity and quality of the bilingual language resource. However,getting a parallel corpus,which has a large scale and is of high quality,is a very difficult task especially for low resource languages such as Chinese-Vietnamese. Fortunately,multilingual user generated contents（ UGC）,such as bilingual movie subtitles,provide us access to automatic construction of the parallel corpus. Although the amount of UGC parallel corpora can be considerable,the original corpus is not suitable for statistical machine translation（ SMT） systems. The corpus may contain translation errors,sentence mismatching,free translations,etc. To improve the quality of the bilingual corpus for SMT systems,three filtering methods are proposed： sentence length difference,the semantic of sentence pairs,and machine learning. Experiments are conducted on the Chinese to Vietnamese translation corpus.Experimental results demonstrate that all the three methods effectively improve the corpus quality,and the machine translation performance（ BLEU score） can be improved by 1. 32.展开更多
Crowdsourcing has been used recently as an alternative to traditional costly annotation by many natural language processing groups. In this paper, we explore the use of Wechat Official Account Platform (WOAP) in order...Crowdsourcing has been used recently as an alternative to traditional costly annotation by many natural language processing groups. In this paper, we explore the use of Wechat Official Account Platform (WOAP) in order to build a speech corpus and to assess the feasibility of using WOAP followers (also known as contributors) to assemble speech corpus of Mongolian. A Mongolian language qualification test was used to filter out potential non-qualified participants. We gathered natural speech recordings in our daily life, and constructed a Chinese-Mongolian Speech Corpus (CMSC) of 31472 utterances from 296 native speakers who are fluent in Mongolian, totalling 30.8 h of speech. Then,an evaluation experiment was performed, in where the contributors were asked to choose a correct sentence from a multiple choice list to ensure the high-quality of corpus. The results obtained so far showed that crowdsourcing for constructing CMSC with an evaluation mechanism could be more effective than traditional experiments requiring expertise.展开更多
Statistical machine translation for low-resource language suffers from the lack of abundant training corpora. Several methods, such as the use of a pivot language, have been proposed as a bridge to translate from one ...Statistical machine translation for low-resource language suffers from the lack of abundant training corpora. Several methods, such as the use of a pivot language, have been proposed as a bridge to translate from one language to another. However, errors will accumulate during the extensive translation pipelines. In this paper, we propose an approach to low-resource language translation by exploiting the pronunciation correlations between languages. We find that the pronunciation features can improve both Chinese-Vietnamese and Vietnamese- Chinese translation qualities. Experimental results show that our proposed model yields effective improvements, and the translation performance （bilingual evaluation understudy score） is improved by a maximum value of 1.03.展开更多
We propose a novel unsupervised image captioning method.Image captioning involves two fields of deep learning,natural language processing and computer vision.The excessive pursuit ofmodel evaluation results makes the ...We propose a novel unsupervised image captioning method.Image captioning involves two fields of deep learning,natural language processing and computer vision.The excessive pursuit ofmodel evaluation results makes the caption style generated by the model too monotonous,which is difficult to meet people’s demands for vivid and stylized image captions.Therefore,we propose an image captioning model that combines text style transfer and image emotion recognition methods,with which the model can better understand images and generate controllable stylized captions.The proposed method can automatically judge the emotion contained in the image through the image emotion recognition module,better understand the image content,and control the description through the text style transfermethod,thereby generating captions thatmeet people’s expectations.To our knowledge,this is the first work to use both image emotion recognition and text style control.展开更多
Open-world knowledge graph completion aims to find a set of missing triples through entity description,where entities can be either in or out of the graph.However,when aggregating entity description’s word embedding ...Open-world knowledge graph completion aims to find a set of missing triples through entity description,where entities can be either in or out of the graph.However,when aggregating entity description’s word embedding matrix to a single embedding,most existing models either use CNN and LSTM to make the model complex and ineffective,or use simple semantic averaging which neglects the unequal nature of the different words of an entity description.In this paper,an aggregator is proposed,adopting an attention network to get the weights of words in the entity description.This does not upset information in the word embedding,and make the single embedding of aggregation more efficient.Compared with state-of-the-art systems,experiments show that the model proposed performs well in the open-world KGC task.展开更多
基金National Natural Science Foundation of China,Grant/Award Numbers:61671064,61732005National Key Research and Development Program of China,Grant/Award Number:2018YFC0831700。
文摘Using sarcasm on social media platforms to express negative opinions towards a person or object has become increasingly common.However,detecting sarcasm in various forms of communication can be difficult due to conflicting sentiments.In this paper,we introduce a contrasting sentiment-based model for multimodal sarcasm detection(CS4MSD),which identifies inconsistent emotions by leveraging the CLIP knowledge module to produce sentiment features in both text and image.Then,five external sentiments are introduced to prompt the model learning sentimental preferences among modalities.Furthermore,we highlight the importance of verbal descriptions embedded in illustrations and incorporate additional knowledge-sharing modules to fuse such imagelike features.Experimental results demonstrate that our model achieves state-of-the-art performance on the public multimodal sarcasm dataset.
基金National Natural Science Foundation of China,Grant/Award Numbers:61671064,61732005National Key Research&Development Program,Grant/Award Number:2018YFC0831700。
文摘Emotion cause extraction(ECE)task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently.However,current work neglects the implicit emotion expressed without any explicit emotional keywords,which appears more frequently in application scenarios.The lack of explicit emotion information makes it extremely hard to extract emotion causes only with the local context.Moreover,an entire event is usually across multiple clauses,while existing work merely extracts cause events at clause level and cannot effectively capture complete cause event information.To address these issues,the events are first redefined at the tuple level and a span-based tuple-level algorithm is proposed to extract events from different clauses.Based on it,a corpus for implicit emotion cause extraction that tries to extract causes of implicit emotions is constructed.The authors propose a knowledge-enriched jointlearning model of implicit emotion recognition and implicit emotion cause extraction tasks(KJ-IECE),which leverages commonsense knowledge from ConceptNet and NRC_VAD to better capture connections between emotion and corresponding cause events.Experiments on both implicit and explicit emotion cause extraction datasets demonstrate the effectiveness of the proposed model.
基金Supported by the National Basic Research Program of China(973Program)(2013CB329303)the National Natural Science Foundation of China(61502035)
文摘The performance of a machine translation system heavily depends on the quantity and quality of the bilingual language resource. However,getting a parallel corpus,which has a large scale and is of high quality,is a very difficult task especially for low resource languages such as Chinese-Vietnamese. Fortunately,multilingual user generated contents（ UGC）,such as bilingual movie subtitles,provide us access to automatic construction of the parallel corpus. Although the amount of UGC parallel corpora can be considerable,the original corpus is not suitable for statistical machine translation（ SMT） systems. The corpus may contain translation errors,sentence mismatching,free translations,etc. To improve the quality of the bilingual corpus for SMT systems,three filtering methods are proposed： sentence length difference,the semantic of sentence pairs,and machine learning. Experiments are conducted on the Chinese to Vietnamese translation corpus.Experimental results demonstrate that all the three methods effectively improve the corpus quality,and the machine translation performance（ BLEU score） can be improved by 1. 32.
文摘Crowdsourcing has been used recently as an alternative to traditional costly annotation by many natural language processing groups. In this paper, we explore the use of Wechat Official Account Platform (WOAP) in order to build a speech corpus and to assess the feasibility of using WOAP followers (also known as contributors) to assemble speech corpus of Mongolian. A Mongolian language qualification test was used to filter out potential non-qualified participants. We gathered natural speech recordings in our daily life, and constructed a Chinese-Mongolian Speech Corpus (CMSC) of 31472 utterances from 296 native speakers who are fluent in Mongolian, totalling 30.8 h of speech. Then,an evaluation experiment was performed, in where the contributors were asked to choose a correct sentence from a multiple choice list to ensure the high-quality of corpus. The results obtained so far showed that crowdsourcing for constructing CMSC with an evaluation mechanism could be more effective than traditional experiments requiring expertise.
基金supported by the National key Basic Research and Development(973)Program of China(No.2013CB329303)the National Natural Science Foundation of China(Nos.61502035,61132009,and 61671064)Beijing Advanced Innovation Center for Imaging Technology(No.BAICIT-2016007)
文摘Statistical machine translation for low-resource language suffers from the lack of abundant training corpora. Several methods, such as the use of a pivot language, have been proposed as a bridge to translate from one language to another. However, errors will accumulate during the extensive translation pipelines. In this paper, we propose an approach to low-resource language translation by exploiting the pronunciation correlations between languages. We find that the pronunciation features can improve both Chinese-Vietnamese and Vietnamese- Chinese translation qualities. Experimental results show that our proposed model yields effective improvements, and the translation performance （bilingual evaluation understudy score） is improved by a maximum value of 1.03.
基金supported by the National Key Research&Development Program (Grant No.2018YFC0831700)National Natural Science Foundation of China (Grant No.61671064,No.61732005).
文摘We propose a novel unsupervised image captioning method.Image captioning involves two fields of deep learning,natural language processing and computer vision.The excessive pursuit ofmodel evaluation results makes the caption style generated by the model too monotonous,which is difficult to meet people’s demands for vivid and stylized image captions.Therefore,we propose an image captioning model that combines text style transfer and image emotion recognition methods,with which the model can better understand images and generate controllable stylized captions.The proposed method can automatically judge the emotion contained in the image through the image emotion recognition module,better understand the image content,and control the description through the text style transfermethod,thereby generating captions thatmeet people’s expectations.To our knowledge,this is the first work to use both image emotion recognition and text style control.
基金the National Natural Science Foundation of China(Grant No.61671064,No.61732005)National Key Research&Development Program(Grant No.2018YFC0831700).
文摘Open-world knowledge graph completion aims to find a set of missing triples through entity description,where entities can be either in or out of the graph.However,when aggregating entity description’s word embedding matrix to a single embedding,most existing models either use CNN and LSTM to make the model complex and ineffective,or use simple semantic averaging which neglects the unequal nature of the different words of an entity description.In this paper,an aggregator is proposed,adopting an attention network to get the weights of words in the entity description.This does not upset information in the word embedding,and make the single embedding of aggregation more efficient.Compared with state-of-the-art systems,experiments show that the model proposed performs well in the open-world KGC task.
