Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships
Published 1 January 2016Open access
Mohit Iyyer, Anupam Guha, Snigdha Chaturvedi, Jordan Boyd‐Graber, Hal Daumé
Citations148
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A novel unsupervised neural network is presented that incorporates dictionary learning to generate interpretable, accurate relationship trajectories and jointly learns a set of global relationship descriptors as well as a trajectory over these descriptors for each relationship in a dataset of raw text from novels.
Abstract
Mohit Iyyer, Anupam Guha, Snigdha Chaturvedi, Jordan Boyd-Graber, Hal Daumé III. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.
Keywords
Computer ScienceArts and Humanities
UvA-DARE (University of Amsterdam)Adam: A Method for Stochastic Optimization
84,783 Citations2014Diederik P. Kingma, Jimmy Ba
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)
50,318 Citations2021Mandi, Jayanta, Canoy, Rocsildes +2 more
A simple numeric simulation of DNA-co-polymerized hydrogel shape change and a genetic algorithm that generates and selects large batches of material designs that compete with one another to evolve and converge on optimal objective-matching designs are constructed.
Glove: Global Vectors for Word Representation
33,769 Citations2014Jeffrey Pennington, Richard Socher +1 more
A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
Neural NetworksIndependent component analysis: algorithms and applications
8,785 Citations2000Aapo Hyvärinen, Erkki Oja
The basic theory and applications of ICA are presented, and the goal is to find a linear representation of non-Gaussian data so that the components are statistically independent, or as independent as possible.
IEEE Transactions on Image ProcessingImage Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
5,385 Citations2006Michael Elad, Michal Aharon
This work addresses the image denoising problem, where zero-mean white and homogeneous Gaussian additive noise is to be removed from a given image, and uses the K-SVD algorithm to obtain a dictionary that describes the image content effectively.
Vision ResearchSparse coding with an overcomplete basis set: A strategy employed by V1?
3,720 Citations1997Bruno A. Olshausen, David J. Field
These deviations from linearity provide a potential explanation for the weak forms of non-linearity observed in the response properties of cortical simple cells, and they further make predictions about the expected interactions among units in response to naturalistic stimuli.
Language<b>Scripts, plans, goals, and understanding</b> : an inquiry into human knowledge structures. By Roger C. Schank and Robert P. Abelson. Hillsdale, NJ: Lawrence Erlbaum Associates, 1977. Pp. 248.
3,083 Citations1978David B. Kronenfeld
For both people and machines, each in their own way, there is a serious problem in common of making sense out of what they hear, see, or are told about the world.
The American Journal of PsychologyScripts, Plans, Goals, and Understanding: An Inquiry into Human Knowledge Structures
2,979 Citations1979Earl Hunt, Roger C. Schank +1 more
Reading Tea Leaves: How Humans Interpret Topic Models
1,874 Citations2009Jonathan Chang, Sean Gerrish +3 more
New quantitative methods for measuring semantic meaning in inferred topics are presented, showing that they capture aspects of the model that are undetected by previous measures of model quality based on held-out likelihood.
Transactions of the Association for Computational LinguisticsGrounded Compositional Semantics for Finding and Describing Images with Sentences
831 Citations2014Richard Socher, Andrej Karpathy +3 more
The DT-RNN model, which uses dependency trees to embed sentences into a vector space in order to retrieve images that are described by those sentences, outperform other recursive and recurrent neural networks, kernelized CCA and a bag-of-words baseline on the tasks of finding an image that fits a sentence description and vice versa.
Deep Unordered Composition Rivals Syntactic Methods for Text Classification
741 Citations2015Mohit Iyyer, Varun Manjunatha +2 more
This work presents a simple deep neural network that competes with and, in some cases, outperforms such models on sentiment analysis and factoid question answering tasks while taking only a fraction of the training time.
Unsupervised Learning of Narrative Event Chains
565 Citations2008Nathanael Chambers, Dan Jurafsky
A three step process to learning narrative event chains using unsupervised distributional methods to learn narrative relations between events sharing coreferring arguments and introduces two evaluations: the narrative cloze to evaluate event relatedness, and an order coherence task to evaluate narrative order.
A Hierarchical Neural Autoencoder for Paragraphs and Documents
518 Citations2015Jiwei Li, Thang Luong +1 more
This paper introduces an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph and evaluates the reconstructed paragraph using standard metrics to show that neural models are able to encode texts in a way that preserve syntactic, semantic, and discourse coherence.
Choice Reviews OnlineMacroanalysis: digital methods and literary history
508 Citations2014
This volume introduces readers to large-scale literary computing and the revolutionary potential of macroanalysis--a new approach to the study of the literary record designed for probing the digital-textual world as it exists today, in digital form and in large quantities.
Unsupervised learning of narrative schemas and their participants
410 Citations2009Nathanael Chambers, Dan Jurafsky
An unsupervised system for learning narrative schemas, coherent sequences or sets of events whose arguments are filled with participant semantic roles defined over words to improve on previous results in narrative/frame learning and induce rich frame-specific semantic roles.
Gaussian LDA for Topic Models with Word Embeddings
324 Citations2015Rajarshi Das, Manzil Zaheer +1 more
Gaussian LDA is replaced with multivariate Gaussian distributions on the embedding space, which encourages the model to group words that are a priori known to be semantically related into topics into topics.
Political Ideology Detection Using Recursive Neural Networks
282 Citations2014Mohit Iyyer, Peter K. Enns +2 more
A RNN framework is applied to the task of identifying the political position evinced by a sentence to show the importance of modeling subsentential elements and outperforms existing models on a newly annotated dataset and an existing dataset.
Extracting Social Networks from Literary Fiction
255 Citations2010David K. Elson, Kathleen McKeown +1 more
The method involves character name chunking, quoted speech attribution and conversation detection given the set of quotes, which provides evidence that the majority of novels in this time period do not fit two characterizations provided by literacy scholars.
Hidden Topic Markov Models
245 Citations2007Amit Gruber, Yair Weiss +1 more
This paper proposes modeling the topics of words in the document as a Markov chain, and shows that incorporating this dependency allows us to learn better topics and to disambiguate words that can belong to different topics.
arXiv (Cornell University)A Hierarchical Neural Autoencoder for Paragraphs and Documents
207 Citations2015Jiwei Li, Minh-Thang Luong +1 more
A Bayesian Mixed Effects Model of Literary Character
187 Citations2014David Bamman, Ted Underwood +1 more
A model that employs multiple effects to account for the influence of extra-linguistic information (such as author) is introduced and it is found that this method leads to improved agreement with the preregistered judgments of a literary scholar, complementing the results of alternative models.
FigshareLearning Latent Personas of Film Characters
182 Citations2018David Bamman, Brendan O’Connor +1 more
Two latent variable models for learning character types, or personas, in film, are presented, in which a persona is defined as a set of mixtures over latent lexical classes.
Proceedings of the AAAI Conference on Artificial IntelligenceA Novel Neural Topic Model and Its Supervised Extension
164 Citations2015Ziqiang Cao, Sujian Li +3 more
A novel neural topic model (NTM) is proposed where the representation of words and documents are efficiently and naturally combined into a uniform framework and is competitive in both topic discovery and classification/regression tasks.
Sparse Overcomplete Word Vector Representations
161 Citations2015Manaal Faruqui, Yulia Tsvetkov +3 more
This work proposes methods that transform word vectors into sparse (and optionally binary) vectors, which are more similar to the interpretable features typically used in NLP, though they are discovered automatically from raw corpora.
Connections between the lines
121 Citations2009Jonathan Chang, Jordan Boyd‐Graber +1 more
A novel probabilistic topic model is presented to analyze text corpora and infer descriptions of its entities and of relationships between those entities and it is shown qualitatively and quantitatively that the model can construct and annotate graphs of relationships and make useful predictions.
Is this a wampimuk? Cross-modal mapping between distributional semantics and the visual world
98 Citations2014Angeliki Lazaridou, Elia Bruni +1 more
This work presents a simple approach to cross-modal vector-based semantics for the task of zero-shot learning, in which an image of a previously unseen object is mapped to a linguistic representation denoting its word.
Utopia/Dystopia: Conditions of Historical Possibility
85 Citations2010Michael D. Gordin, Helen Tilley +1 more
Learning Sparsely Used Overcomplete Dictionaries
73 Citations2014Alekh Agarwal, Animashree Anandkumar +3 more
This work considers the problem of learning sparsely used overcomplete dictionaries, where each observation is a sparse combination of elements from an unknown overcomplete dictionary, and establishes exact recovery when the dictionary elements are mutually incoherent.
A Compositional and Interpretable Semantic Space
63 Citations2015Alona Fyshe, Leila Wehbe +3 more
A new method is introduced that allows word and phrase vectors to adapt to the notion of composition and learn a VSM that is both tailored to support a chosen semantic composition operation, and whose resulting features have an intuitive interpretation.
Machine LearningModeling topic control to detect influence in conversations using nonparametric topic models
62 Citations2013Viet-An Nguyen, Jordan Boyd‐Graber +4 more
A nonparametric hierarchical Bayesian model capable of discovering the topics used in a set of conversations, how these topics are shared across conversations, when these topics change during conversations, and a speaker-specific measure of “topic control” is introduced.
Mr. Bennet, his coachman, and the Archbishop walk into a bar but only one of them gets recognized: On The Difficulty of Detecting Characters in Literary Texts
59 Citations2015Hardik Vala, David Jurgens +2 more
A novel technique for character detection is proposed, achieving significant improvements over state of the art on multiple datasets, and heavily reliant on NER to identify characters.
Character-based kernels for novelistic plot structure
56 Citations2012Micha Elsner
This work presents a kernel for comparing novelistic plots at a higher level, in terms of the cast of characters they depict and the social relationships between them, which can accurately distinguish held-out novels in their original form from artificially disordered or reversed surrogates.
Personality Profiling of Fictional Characters using Sense-Level Links between Lexical Resources
41 Citations2015Lucie Flek, Iryna Gurevych
A novel collaboratively built dataset of fictional character personality is presented and three machine learning models based on the speech, actions and predicatives of the main characters are evaluated, showing that especially the lexical-semantic features significantly outperform the baselines.
Computational IntelligenceA COMPUTATIONAL MODEL FOR PLOT UNITS
36 Citations2012Amit Goyal, Ellen Riloff +1 more
This research revisits plot units, which were developed in the 1980s as a conceptual knowledge structure to represent the affect states of and emotional tensions between characters in narrative stories, with a fully automated system, called AESOP, that generates plot unit representations for narrative texts.
Proceedings of the AAAI Conference on Artificial IntelligenceInferring Interpersonal Relations in Narrative Summaries
33 Citations2016Shashank Srivastava, Snigdha Chaturvedi +1 more
This work addresses the problem of inferring the polarity of relationships between people in narrative summaries as a joint structured prediction for each narrative, and presents a general model that combines evidence from linguistic and semantic features, as well as features based on the structure of the social community in the text.
arXiv (Cornell University)Inferring Interpersonal Relations in Narrative Summaries
30 Citations2015Shashank Srivastava, Snigdha Chaturvedi +1 more
Proceedings of the AAAI Conference on Artificial IntelligenceLearning Scripts as Hidden Markov Models
22 Citations2014J. Walker Orr, Prasad Tadepalli +3 more
This paper develops an algorithm for structure and parameter learning based on Expectation Maximization and evaluates it on a number of natural datasets, showing that the algorithm is superior to several informed baselines for predicting missing events in partialobservation sequences.
Learning Scripts as Hidden Markov Models
19 Citations2014John A. Orr, Prasad Tadepalli +3 more
arXiv (Cornell University)Annotating Character Relationships in Literary Texts
11 Citations2015Philip Massey, Patrick Xia +2 more
A dataset of manually annotated relationships between characters in literary texts is presented to support the training and evaluation of automatic methods for relation type prediction in this domain and the broader computational analysis of literary character.
arXiv (Cornell University)Modeling Dynamic Relationships Between Characters in Literary Novels
7 Citations2015Snigdha Chaturvedi, Shashank Srivastava +2 more
This work hypothesizes that relationships are dynamic and temporally evolve with the progress of the narrative, and proposes a semi-supervised framework to learn relationship sequences from fully as well as partially labeled data.
To Kill a Text: The Dialogic Fiction of Hugo, Dickens, and Zola
6 Citations1995Ilinca Zarifopol-Johnston