Robust Coreference Resolution and Entity Linking on Dialogues:
            Character Identification on TV Show Transcripts

Chen, Henry Y.; Zhou, Ethan; Choi, Jinho D.

doi:10.18653/v1/k17-1023

Cited by 25 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They identify the concerned character by using predefined rules, exploiting the presence of a proper noun in the chain, or connections to utterances whose speaker could be identified. They propose an automatic method based on agglomerative convolutional networks to take advantage of the latter type of information [52] when solving co-references and identifying characters associated to co-reference chains. In [41], Bredin & Gelly combine face track clustering and speaker diarization: they first detect speakers through standard speech activity detection tools, before using face embeddings to cluster the face tracks corresponding to the resulting speech segments.…”

Section: Visualmentioning

confidence: 99%

Extraction and Analysis of Fictional Character Networks

Labatut

Bost

2019

ACM Comput. Surv.

View full text Add to dashboard Cite

A character network is a graph extracted from a narrative, in which vertices represent characters and edges correspond to interactions between them. A number of narrative-related problems can be addressed automatically through the analysis of character networks, such as summarization, classification, or role detection. Character networks are particularly relevant when considering works of fictions (e.g. novels, plays, movies, TV series), as their exploitation allows developing information retrieval and recommendation systems. However, works of fiction possess specific properties making these tasks harder.This survey aims at presenting and organizing the scientific literature related to the extraction of character networks from works of fiction, as well as their analysis. We first describe the extraction process in a generic way, and explain how its constituting steps are implemented in practice, depending on the medium of the narrative, the goal of the network analysis, and other factors. We then review the descriptive tools used to characterize character networks, with a focus on the way they are interpreted in this context. We illustrate the relevance of character networks by also providing a review of applications derived from their analysis. Finally, we identify the limitations of the existing approaches, and the most promising perspectives.

show abstract

Section: Visualmentioning

confidence: 99%

Extraction and Analysis of Fictional Character Networks

Labatut

Bost

2019

ACM Comput. Surv.

View full text Add to dashboard Cite

show abstract

“…Summarization has a main focus on plot line understanding. There has been considerable recent interest in evaluating a model's understanding of stories via summarization, e.g., NovelChapters [Ladhak et al, 2020], BookSum [Kryściński et al, 2021] and Screen-Sum [Chen et al, 2021]. Intuitively, summarization requires a deep understanding of the global information of a story, to enable generation of story summaries.…”

Section: Assessments Of Narrative Compressionmentioning

confidence: 99%

“…SumScreen [Chen et al, 2021] summarization TV show scripts [Flekova and Gurevych, 2015] classification literature [Chen and Choi, 2016] / [Chen et al, 2017] coref resolution TV show scripts…”

Section: Dataset Task Formatmentioning

confidence: 99%

“…From the perspective of cognitive and narrative theories, understanding narratives is a complex process that requires the development of multiple capabilities at the same time, such as story grammar, theory of mind, and perspectivetaking [Paris and Paris, 2003]. In NLP research, people have developed linguistic resources and tools for analyzing narrative texts [Bamman, 2020], and evaluation benchmarks on various high-level narrative understanding tasks such as event relation identification [Glavaš et al, 2014], question answering [Kočiskỳ and others, 2018] and story summarization [Chen et al, 2021].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Machine Narrative Reading Comprehension Assessments

Sang¹,

Mou²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

As the body of research on machine narrative comprehension grows, there is a critical need for consideration of performance assessment strategies as well as the depth and scope of different benchmark tasks. Based on narrative theories, reading comprehension theories, as well as existing machine narrative reading comprehension tasks and datasets, we propose a typology that captures the main similarities and differences among assessment tasks; and discuss the implications of our typology for new task design and the challenges of narrative reading comprehension.

show abstract

“…All other annotations are ignored. Table 3 shows the results using the default fastText (Bojanowski et al, 2017) (Chen et al, 2017) and TE is from (Zhou and Choi, 2018). More details can be found in the Experiments section.…”

Section: Evaluation On Other Tasksmentioning

confidence: 99%

A Unified Approach to Entity-Centric Context Tracking in Social Conversations

Rückert¹,

Sunkara²,

Rastogi³

et al. 2022

Preprint

View full text Add to dashboard Cite

In human-human conversations, Context Tracking deals with identifying important entities and keeping track of their properties and relationships. This is a challenging problem that encompasses several subtasks such as slot tagging, coreference resolution, resolving plural mentions and entity linking. We approach this problem as an end-to-end modeling task where the conversational context is represented by an entity repository containing the entity references mentioned so far, their properties and the relationships between them. The repository is updated turn-by-turn, thus making training and inference computationally efficient even for long conversations. This paper lays the groundwork for an investigation of this framework in two ways. First, we release Contrack, a large scale human-human conversation corpus for context tracking with people and location annotations. It contains over 7000 conversations with an average of 11.8 turns, 5.8 entities and 15.2 references per conversation. Second, we open-source a neural network architecture for context tracking. Finally we compare this network to state-of-the-art approaches for the subtasks it subsumes and report results on the involved tradeoffs.

show abstract

Robust Coreference Resolution and Entity Linking on Dialogues: Character Identification on TV Show Transcripts

Cited by 25 publications

References 15 publications

Extraction and Analysis of Fictional Character Networks

Extraction and Analysis of Fictional Character Networks

A Survey of Machine Narrative Reading Comprehension Assessments

A Unified Approach to Entity-Centric Context Tracking in Social Conversations

Contact Info

Product

Resources

About