Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships

Iyyer, Mohit; Guha, Anupam; Chaturvedi, Snigdha; Boyd-Graber, Jordan; Daumé, Hal

doi:10.18653/v1/n16-1180

Cited by 126 publications

(159 citation statements)

References 32 publications

Supporting

Mentioning

155

Contrasting

Unclassified

Order By: Relevance

“…We adopted the contrastive max-margin objective function used in previous work (Weston et al, 2011;Socher et al, 2014;Iyyer et al, 2016). For each input sentence, we randomly sample m sentences from our training data as negative samples.…”

Section: Training Objectivementioning

confidence: 99%

An Unsupervised Neural Attention Model for Aspect Extraction

Lee

Ng³

et al. 2017

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

361

296

View full text Add to dashboard Cite

Aspect extraction is an important and challenging task in aspect-based sentiment analysis. Existing works tend to apply variants of topic models on this task. While fairly successful, these methods usually do not produce highly coherent aspects. In this paper, we present a novel neural approach with the aim of discovering coherent aspects. The model improves coherence by exploiting the distribution of word co-occurrences through the use of neural word embeddings. Unlike topic models which typically assume independently generated words, word embedding models encourage words that appear in similar contexts to be located close to each other in the embedding space. In addition, we use an attention mechanism to de-emphasize irrelevant words during training, further improving the coherence of aspects. Experimental results on real-life datasets demonstrate that our approach discovers more meaningful and coherent aspects, and substantially outperforms baseline methods on several evaluation tasks.

show abstract

Section: Training Objectivementioning

confidence: 99%

An Unsupervised Neural Attention Model for Aspect Extraction

Lee

Ng³

et al. 2017

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

361

296

View full text Add to dashboard Cite

show abstract

“…Elsner (2012) explore the plot structure of novels to distinguish original texts from novels from synthetically altered versions of the same. Some recent approaches have also focused on modeling relationships between literary characters (Chaturvedi, 2016;Iyyer et al, 2016;, and their social networks (Elson et al, 2010;Agarwal et al, 2013;Krishnan and Eisenstein, 2015;. Other research has focused on characterizing narratives in terms of their structure.…”

Section: Related Workmentioning

confidence: 99%

Where Have I Heard This Story Before? Identifying Narrative Similarity in Movie Remakes

Chaturvedi

Srivastava

Roth

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

Self Cite

View full text Add to dashboard Cite

People can identify correspondences between narratives in everyday life. For example, an analogy with the Cinderella story may be made in describing the unexpected success of an underdog in seemingly different stories. We present a new task and dataset for story understanding: identifying instances of similar narratives from a collection of narrative texts. We present an initial approach for this problem, which finds correspondences between narratives in terms of plot events, and resemblances between characters and their social relationships. Our approach yields an 8% absolute improvement in performance over an information-retrieval baseline on a novel dataset of plot summaries of 577 movie remakes from Wikipedia.

show abstract

“…RNNs have been used successfully for other narrative modeling tasks (Iyyer et al, 2016; Rand She waited for months for her hair to grow back out. Back He put a bowl of soup into the microwave.…”

Section: Supervised Approachesmentioning

confidence: 99%

Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics

Roth¹,

Mostafazadeh²,

Chambers³

et al. 2017

View full text Add to dashboard Cite

This workshop takes place for the second time, with the goal of gathering and showcasing theoretical and computational approaches to joint models of semantics, and applications that incorporate multi-level semantics. Improved computational models of semantics hold great promise for applications in language technology, be it semantics at the lexical level, sentence level or discourse level. This year we have an additional focus on the comprehensive understanding of narrative structure in language. Recently a range of tasks have been proposed in the area of learning and applying commonsense/procedural knowledge. Such tasks include, for example, learning prototypical event sequences and event participants, modeling the plot structure of novels, and resolving anaphora in Winograd schemas. This year's workshop further includes a shared task, the Story Cloze Test-a new evaluation for story understanding and script learning. This test provides a system with a four-sentence story and two possible endings, and the system must choose the correct ending to the story. Successful narrative understanding (getting closer to human performance of 100%) requires systems to link various levels of semantics to commonsense knowledge. A total of eight systems participated in the shared task, with a variety of approaches including end-to-end neural networks, feature-based regression models, and rule-based methods. The highest performing system achieves an accuracy of 75.2%, a substantial improvement over the previous state-of-the-art of 58.5%.We received 19 papers in total, out of which we accepted 13. These papers are presented as talks at the workshop as well as in a poster session. In addition, the workshop program features talks from two invited speakers who work on different aspects of semantics. The day will end with a discussion session where invited speakers and workshop participants further discuss the insights gained during the workshop.Our program committee consisted of 23 researchers who provided constructive and thoughtful reviews. This workshop would not have been possible without their hard work. Many thanks to you all. Finally, a huge thank you to all the authors who submitted papers to this workshop and made it a big success.Michael, Nasrin, Nate, and Annie AbstractWe present a semi-supervised clustering approach to induce script structure from crowdsourced descriptions of event sequences by grouping event descriptions into paraphrase sets (representing event types) and inducing their temporal order. Our model exploits semantic and positional similarity and allows for flexible event order, thus overcoming the rigidity of previous approaches. We incorporate crowdsourced alignments as prior knowledge and show that exploiting a small number of alignments results in a substantial improvement in cluster quality over state-of-the-art models and provides an appropriate basis for the induction of temporal order. We also show a coverage study to demonstrate the scalability of our approach.

show abstract

Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships

Cited by 126 publications

References 32 publications

An Unsupervised Neural Attention Model for Aspect Extraction

An Unsupervised Neural Attention Model for Aspect Extraction

Where Have I Heard This Story Before? Identifying Narrative Similarity in Movie Remakes

Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics

Contact Info

Product

Resources

About