A Question Answering Approach for Emotion Cause Extraction

Gui, Lin; Hu, Jiannan; He, Yulan; Xu, Ruifeng; Lu, Qin; Liu, Baiyang

doi:10.18653/v1/d17-1167

Cited by 145 publications

(77 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The context embeddings obtained for all components individually can then be concatenated, producing a new representation of the document that encodes the most relevant representation of each component for the given task. It would also be possible to aggregate each key or value with its neighbors, by computing their average or sum [128].…”

Section: A Input Representationmentioning

confidence: 99%

Attention in Natural Language Processing

Galassi

Lippi

Torroni

2021

IEEE Trans. Neural Netw. Learning Syst.

415

130

View full text Add to dashboard Cite

Attention is an increasingly popular mechanism used in a wide range of neural architectures. The mechanism itself has been realized in a variety of formats. However, because of the fast-paced advances in this domain, a systematic overview of attention is still missing. In this article, we define a unified model for attention architectures in natural language processing, with a focus on those designed to work with vector representations of the textual data. We propose a taxonomy of attention models according to four dimensions: the representation of the input, the compatibility function, the distribution function, and the multiplicity of the input and/or output. We present the examples of how prior information can be exploited in attention models and discuss ongoing research efforts and open challenges in the area, providing the first extensive categorization of the vast body of literature in this exciting domain.

show abstract

Section: A Input Representationmentioning

confidence: 99%

Attention in Natural Language Processing

Galassi

Lippi

Torroni

2021

IEEE Trans. Neural Netw. Learning Syst.

415

130

View full text Add to dashboard Cite

show abstract

“…Memory network (Sukhbaatar et al, 2015b;Kumar et al, 2016;Xiong et al, 2016) is initially proposed to solve question answering problems. Recent researches show that memory network obtains the state-of-the-art results in many NLP tasks such as sentiment classification (Li et al, 2017) and analysis (Gui et al, 2017), poetry generation , spoken language understanding (Chen et al, 2016), etc. Inspired by the success of memory network used in many NLP tasks, we introduce it into WSD.…”

Section: Related Workmentioning

confidence: 99%

Incorporating Glosses into Neural Word Sense Disambiguation

Luo¹,

Liu²,

Qin³

et al. 2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Word Sense Disambiguation (WSD) aims to identify the correct meaning of polysemous words in the particular context. Lexical resources like WordNet which are proved to be of great help for WSD in the knowledge-based methods. However, previous neural networks for WSD always rely on massive labeled data (context), ignoring lexical resources like glosses (sense definitions). In this paper, we integrate the context and glosses of the target word into a unified framework in order to make full use of both labeled data and lexical knowledge. Therefore, we propose GAS: a gloss-augmented WSD neural network which jointly encodes the context and glosses of the target word. GAS models the semantic relationship between the context and the gloss in an improved memory network framework, which breaks the barriers of the previous supervised methods and knowledge-based methods. We further extend the original gloss of word sense via its semantic relations in WordNet to enrich the gloss information. The experimental results show that our model outperforms the state-of-theart systems on several English all-words WSD datasets 1 .

show abstract

“…Knowledge-based and rule-based methods have several disadvantages such as the heavy workload of constructing the knowledge and rules, the limited coverage, and the poor adaptability of different corpuses, whereas feature-based machine learning methods require rich experience for feature selection. Gui [71]and Mu [72] et al used deep learning technology to obtain the semantic representation through a word embedding model called Word2vec and then measured the effect of words for detecting emotional cause through an attention mechanism. It captures semantic continuity by integrating contextual semantic information.…”

Section: ) Deep Learning Methodsmentioning

confidence: 99%

“…(3) The effect of cause clue words The dataset in emotional cause extraction generally uses more formal news text data, such as literature [71], and there are clear syntax rules between the clue words, emotional words and emotional causes. However, in addition to the different roles of suicide words and emotional words discussed above, the relationship between cause clue words and SICs also become ambiguous because of the informal expression of posts.…”

Section: Don't Know What To Do Let Him Go and I'll Be Lonely/ipsgmentioning

confidence: 99%

Suicidal Ideation Cause Extraction From Social Texts

Liu

Wan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Suicide has become a major public health and social concern in the world. Suicidal ideation cause extraction (SICE) in social texts can provide support for suicide prevention. This article summarizes the research on suicidal ideation causes (SICs) through the use of psychological and sociological analysis. Then, a social text-based SIC dataset is constructed and analyzed statistically for various features. A CRF model is provided along with Char-BiLSTM-CRF, which uses concatenation of word embeddings and character embeddings as word representation inputs. Then, the effects on the task are explored by the word (W), part of speech (POS), dependence relationship (DP), suicidal psychology (PCS), emotion (ET), and language (LG) features in the CRF model. The experiment shows that the word features worked best. POS and DP can be somehow covered by word features. PCS, ET and LG features can improve the effect of SICE. It also shows that Char-BiLSTM-CRF is better than CRF in general, but CRF still has advantages in terms of precision. Adding character embeddings and CRF layers can significantly improve the extraction using Char-BiLSTM-CRF. The experiment also compared three-word embeddings with Word2vec, ELMo and BERT. Compared with Word2vec, the F-value of ELMo is increased by approximately 5% on average, and compared with ELMo, the C_F and E_F of BERT are increased by 3.5% and 2.3%, respectively. Finally, the challenge of SICE is discussed based on the experimental results of Char-BiLSTM-CRF.

show abstract

A Question Answering Approach for Emotion Cause Extraction

Cited by 145 publications

References 31 publications

Attention in Natural Language Processing

Attention in Natural Language Processing

Incorporating Glosses into Neural Word Sense Disambiguation

Suicidal Ideation Cause Extraction From Social Texts

Contact Info

Product

Resources

About