A Survey of Machine Narrative Reading Comprehension Assessments

Sang, Yisi; Mou, Xiangyang; Li, Jing; Stanton, Jeffrey M.; Yu, Mei

doi:10.48550/arxiv.2205.00299

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The task of narrative understanding is a challenging topic of research and has been studied in numerous domains (Piper et al, 2021;Sang et al, 2022). Recent studies include important applications of this task in supporting professionals in mental health.…”

Section: Introductionmentioning

confidence: 99%

Whats New? Identifying the Unfolding of New Events in Narratives

Mousavi¹,

Tanaka²,

Roccabruna³

et al. 2023

Preprint

View full text Add to dashboard Cite

Narratives include a rich source of events unfolding over time and context. Automatic understanding of these events may provide a summarised comprehension of the narrative for further computation (such as reasoning).In this paper, we study the Information Status (IS) of the events and propose a novel challenging task: the automatic identification of new events in a narrative. We define an event as a triplet of subject, predicate, and object. The event is categorized as new with respect to the discourse context and whether it can be inferred through commonsense reasoning. We annotated a publicly available corpus of narratives with the new events at sentence level using human annotators. We present the annotation protocol and a study aiming at validating the quality of the annotation and the difficulty of the task. We publish the annotated dataset, annotation materials, and machine learning baseline models for the task of new event extraction for narrative understanding.

show abstract

Section: Introductionmentioning

confidence: 99%

Whats New? Identifying the Unfolding of New Events in Narratives

Mousavi¹,

Tanaka²,

Roccabruna³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…According to the data modality and format, character comprehension can be categorized into several classes (Sang et al, 2022a). In this work, we focus on character understanding in scripts (Chen and Choi, 2016;Sang et al, 2022b).…”

Section: Introductionmentioning

confidence: 99%

Multi-level Contrastive Learning for Script-based Character Understanding

Li,

Zhang,

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

In this work, we tackle the scenario of understanding characters in scripts, which aims to learn the characters' personalities and identities from their utterances. We begin by analyzing several challenges in this scenario, and then propose a multi-level contrastive learning framework to capture characters' global information in a fine-grained manner. To validate the proposed framework, we conduct extensive experiments on three character understanding sub-tasks by comparing with strong pretrained language models, including SpanBERT, Longformer, BigBird and ChatGPT-3.5. Experimental results demonstrate that our method improves the performances by a considerable margin. Through further in-depth analysis, we show the effectiveness of our method in addressing the challenges and provide more hints on the scenario of character understanding. We will open-source our work in this URL. Character Sheldon Jennifer Story Title TBBT The Test Dataset TVSHOWGUESS ROCStories Text Length 528832 41 Character's Related Text Sheldon: " ... we take on Koothrappaliand his dog. Really give ourselves a challenge." Jennifer has a big exam tomorrow. ... Jennifer felt bittersweet about it.

show abstract

On solving textual ambiguities and semantic vagueness in MRC based question answering using generative pre-trained transformers

Khan

Iqbal

Alarfaj

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

Machine reading comprehension (MRC) is one of the most challenging tasks and active fields in natural language processing (NLP). MRC systems aim to enable a machine to understand a given context in natural language and to answer a series of questions about it. With the advent of bi-directional deep learning algorithms and large-scale datasets, MRC achieved improved results. However, these models are still suffering from two research issues: textual ambiguities and semantic vagueness to comprehend the long passages and generate answers for abstractive MRC systems. To address these issues, this paper proposes a novel Extended Generative Pretrained Transformers-based Question Answering (ExtGPT-QA) model to generate precise and relevant answers to questions about a given context. The proposed architecture comprises two modified forms of encoder and decoder as compared to GPT. The encoder uses a positional encoder to assign a unique representation with each word in the sentence for reference to address the textual ambiguities. Subsequently, the decoder module involves a multi-head attention mechanism along with affine and aggregation layers to mitigate semantic vagueness with MRC systems. Additionally, we applied syntax and semantic feature engineering techniques to enhance the effectiveness of the proposed model. To validate the proposed model’s effectiveness, a comprehensive empirical analysis is carried out using three benchmark datasets including SQuAD, Wiki-QA, and News-QA. The results of the proposed ExtGPT-QA outperformed state of art MRC techniques and obtained 93.25% and 90.52% F1-score and exact match, respectively. The results confirm the effectiveness of the ExtGPT-QA model to address textual ambiguities and semantic vagueness issues in MRC systems.

show abstract

A Survey of Machine Narrative Reading Comprehension Assessments

Cited by 3 publications

References 11 publications

Whats New? Identifying the Unfolding of New Events in Narratives

Whats New? Identifying the Unfolding of New Events in Narratives

Multi-level Contrastive Learning for Script-based Character Understanding

On solving textual ambiguities and semantic vagueness in MRC based question answering using generative pre-trained transformers

Contact Info

Product

Resources

About