Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings

Liu, Pengfei; Joty, Shafiq; Meng, Helen

doi:10.18653/v1/d15-1168

Cited by 361 publications

(254 citation statements)

References 30 publications

Supporting

Mentioning

252

Contrasting

Unclassified

Order By: Relevance

“…An LSTM (Long Short-Term Memory) is an extension of an RNN with more stable gradients (Hochreiter and Schmidhuber, 1997). Bi-LSTM have recently successfully been used for a variety of tasks (Collobert et al, 2011;Huang et al, 2015;Kiperwasser and Goldberg, 2016;Liu et al, 2015;. For further details, cf.…”

Section: Modelmentioning

confidence: 99%

When is multitask learning effective? Semantic sequence prediction under varying data conditions

Alonso¹,

Plank²

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

Multitask learning has been applied successfully to a range of tasks, mostly morphosyntactic. However, little is known on when MTL works and whether there are data characteristics that help to determine its success. In this paper we evaluate a range of semantic sequence labeling tasks in a MTL setup. We examine different auxiliary tasks, amongst which a novel setup, and correlate their impact to datadependent conditions. Our results show that MTL is not always effective, significant improvements are obtained only for 1 out of 5 tasks. When successful, auxiliary tasks with compact and more uniform label distributions are preferable.

show abstract

Section: Modelmentioning

confidence: 99%

When is multitask learning effective? Semantic sequence prediction under varying data conditions

Alonso¹,

Plank²

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

show abstract

“…Bi-LSTMs have already been used for finegrained sentiment analysis (Liu et al, 2015), syntactic chunking (Huang et al, 2015), and semantic role labeling (Zhou and Xu, 2015). These and other recent applications of bi-LSTMs were constructed for solving a single task in isolation, however.…”

mentioning

confidence: 99%

Improving sentence compression by learning to predict gaze

Klerke¹,

Goldberg²,

Søgaard³

2016

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…For sentiment detection, saccade channel seems to be handing text having semantic incongruity (due 5 a standard range (Liu et al, 2015;Melamud et al, 2016) to the presence of irony / sarcasm) better. Fixation channel does not help much, may be because of higher variance in fixation duration.…”

Section: Effect Of Fixation / Saccade Channelsmentioning

confidence: 99%

Learning Cognitive Features from Gaze Data for Sentiment and Sarcasm Classification using Convolutional Neural Network

Mishra¹,

Dey²,

Bhattacharyya³

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

100

View full text Add to dashboard Cite

Cognitive NLP systems-i.e., NLP systems that make use of behavioral data -augment traditional text-based features with cognitive features extracted from eye-movement patterns, EEG signals, brain-imaging etc.. Such extraction of features is typically manual. We contend that manual extraction of features may not be the best way to tackle text subtleties that characteristically prevail in complex classification tasks like sentiment analysis and sarcasm detection, and that even the extraction and choice of features should be delegated to the learning system. We introduce a framework to automatically extract cognitive features from the eye-movement / gaze data of human readers reading the text and use them as features along with textual features for the tasks of sentiment polarity and sarcasm detection. Our proposed framework is based on Convolutional Neural Network (CNN). The CNN learns features from both gaze and text and uses them to classify the input text. We test our technique on published sentiment and sarcasm labeled datasets, enriched with gaze information, to show that using a combination of automatically learned text and gaze features often yields better classification performance over (i) CNN based systems that rely on text input alone and (ii) existing systems that rely on handcrafted gaze and textual features.

show abstract

Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings

Cited by 361 publications

References 30 publications

When is multitask learning effective? Semantic sequence prediction under varying data conditions

When is multitask learning effective? Semantic sequence prediction under varying data conditions

Improving sentence compression by learning to predict gaze

Learning Cognitive Features from Gaze Data for Sentiment and Sarcasm Classification using Convolutional Neural Network

Contact Info

Product

Resources

About