Learning to Extract Action Descriptions From Narrative Text

Ludwig, Oswaldo; Thi, Quynh Ngoc; Smith, Cameron; Cavazza, Marc; Moens, Marie‐Francine

doi:10.1109/tciaig.2017.2657690

Cited by 6 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consideration of the medical dataset along with domain specific study is carried out by Lu et al [16]. The work of Ludwig et al [17] have presented a mechanism to extract specific action from a given textual contents using Bayesian network. Park et al [18] have presented a visual analytical system where a bipolar concept has been introduced in modeling.…”

Section: A Backgroundmentioning

confidence: 99%

Modelling Simple and Efficient Data Transformation Scheme for Improving Natural Language Processing

J*,

Swamy

2020

IJITEE

View full text Add to dashboard Cite

The importance of natural language processing cannot be sided in the current era of communication and analytics where data is exponentially growing. Although, there has been various versions and schemes that has evolved in the past decade towards improving the performance of natural language processing, but still the problem towards precisely extracting the actual context is an open ended. Review of existing studies show a large scope of new work towards improving it. Therefore, this manuscript presents a unique simplified approach where natural language processing is carried out with a combined effort of syntactical and semantic based transformation scheme. The study is implemented using analytical methodology while the secondary motive of the work is also to balance the mining performance as well as optimizing storage performance too. The study outcome shows proposed scheme to excel better performance with respect to time duration in all the internal processes being involved for data transformation.

show abstract

Section: A Backgroundmentioning

confidence: 99%

Modelling Simple and Efficient Data Transformation Scheme for Improving Natural Language Processing

J*,

Swamy

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…The word embeddings do not contribute much to the problem of porting models trained in one subject domain to another subject domain. Our own research during the MUSE project on machine understanding of language in the context of interactive storytelling showed that the word embeddings used as features in a semantic role labeling task only could slightly improve the results, or needed extra resources that are manually built to largely improve the performance [22,39]. Third and most importantly for the theme of this paper, current word embeddings and language models are successful representations in simple language processing tasks.…”

Section: Current Proposed Solutions: Representation Learning and Deepmentioning

confidence: 99%

Argumentation mining: How can a machine acquire common sense and world knowledge?

Moens

2018

AAC

Self Cite

View full text Add to dashboard Cite

Abstract. Argumentation mining is an advanced form of human language understanding by the machine. This is a challenging task for a machine. When sufficient explicit discourse markers are present in the language utterances, the argumentation can be interpreted by the machine with an acceptable degree of accuracy. However, in many real settings, the mining task is difficult due to the lack or ambiguity of the discourse markers, and the fact that a substantial amount of knowledge needed for the correct recognition of the argumentation, its composing elements and their relationships is not explicitly present in the text, but makes up the background knowledge that humans possess when interpreting language. In this article 1 we focus on how the machine can automatically acquire the needed common sense and world knowledge. As very few research has been done in this respect, many of the ideas proposed in this article are tentative, but start being researched.We give an overview of the latest methods for human language understanding that map language to a formal knowledge representation that facilitates other tasks (for instance, a representation that is used to visualize the argumentation or that is easily shared in a decision or argumentation support system). Most current systems are trained on texts that are manually annotated. Then we go deeper into the new field of representation learning that nowadays is very much studied in computational linguistics. This field investigates methods for representing language as statistical concepts or as vectors, allowing straightforward methods of compositionality. The methods often use deep learning and its underlying neural network technologies to learn concepts from large text collections in an unsupervised way (i.e., without the need for manual annotations). We show how these methods can help the argumentation mining process, but also demonstrate that these methods need further research to automatically acquire the necessary background knowledge and more specifically common sense and world knowledge. We propose a number of ways to improve the learning of common sense and world knowledge by exploiting textual and visual data, and touch upon how we can integrate the learned knowledge in the argumentation mining process.

show abstract

“…Sequence to sequence (seq2seq) modeling is being successfully applied to neural machine translation [6], [7], since this model is language-independent and able to implicitly learn semantic [8], syntactic and contextual dependencies [9]. Further advances in end-to-end training with this model has made it possible to build successful systems [10] for different natural language tasks, including parsing [11], image captioning [12], and open domain dialogue generation [5].…”

Section: State-of-the-artmentioning

confidence: 99%

End-to-end Adversarial Learning for Generative Conversational Agents

Ludwig

2017

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents a new adversarial learning method for generative conversational agents (GCA) besides a new model of GCA. Similar to previous works on adversarial learning for dialogue generation, our method assumes the GCA as a generator that aims at fooling a discriminator that labels dialogues as human-generated or machine-generated; however, in our approach, the discriminator performs token-level classification, i.e. it indicates whether the current token was generated by humans or machines. To do so, the discriminator also receives the context utterances (the dialogue history) and the incomplete answer up to the current token as input. This new approach makes possible the end-to-end training by backpropagation. Moreover, the trained discriminator can be used to choose the best answer among the answers generated by different trained models to improve the performance even more. A self-conversation process enables to produce a set of generated data with more diversity for the adversarial training. This approach improves the performance on questions not related to the training data. Experimental results with human and adversarial evaluations show that the adversarial method yields significant performance gains over the usual teacher forcing training.

show abstract

Learning to Extract Action Descriptions From Narrative Text

Abstract: The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Cited by 6 publications

References 13 publications

Modelling Simple and Efficient Data Transformation Scheme for Improving Natural Language Processing

Modelling Simple and Efficient Data Transformation Scheme for Improving Natural Language Processing

Argumentation mining: How can a machine acquire common sense and world knowledge?

End-to-end Adversarial Learning for Generative Conversational Agents

Contact Info

Product

Resources

About