I-Ta Lee


2021

pdf bib
Modeling Human Mental States with an Entity-based Narrative Graph
I-Ta Lee | Maria Leonor Pacheco | Dan Goldwasser
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Understanding narrative text requires capturing characters’ motivations, goals, and mental states. This paper proposes an Entity-based Narrative Graph (ENG) to model the internal- states of characters in a story. We explicitly model entities, their interactions and the context in which they appear, and learn rich representations for them. We experiment with different task-adaptive pre-training objectives, in-domain training, and symbolic inference to capture dependencies between different decisions in the output space. We evaluate our model on two narrative understanding tasks: predicting character mental states, and desire fulfillment, and conduct a qualitative analysis.

2020

pdf bib
Weakly-Supervised Modeling of Contextualized Event Embedding for Discourse Relations
I-Ta Lee | Maria Leonor Pacheco | Dan Goldwasser
Findings of the Association for Computational Linguistics: EMNLP 2020

Representing, and reasoning over, long narratives requires models that can deal with complex event structures connected through multiple relationship types. This paper suggests to represent this type of information as a narrative graph and learn contextualized event representations over it using a relational graph neural network model. We train our model to capture event relations, derived from the Penn Discourse Tree Bank, on a huge corpus, and show that our multi-relational contextualized event representation can improve performance when learning script knowledge without direct supervision and provide a better representation for the implicit discourse sense classification task.

2019

pdf bib
Multi-Relational Script Learning for Discourse Relations
I-Ta Lee | Dan Goldwasser
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Modeling script knowledge can be useful for a wide range of NLP tasks. Current statistical script learning approaches embed the events, such that their relationships are indicated by their similarity in the embedding. While intuitive, these approaches fall short of representing nuanced relations, needed for downstream tasks. In this paper, we suggest to view learning event embedding as a multi-relational problem, which allows us to capture different aspects of event pairs. We model a rich set of event relations, such as Cause and Contrast, derived from the Penn Discourse Tree Bank. We evaluate our model on three types of tasks, the popular Mutli-Choice Narrative Cloze and its variants, several multi-relational prediction tasks, and a related downstream task—implicit discourse sense classification.

2017

pdf bib
Ideological Phrase Indicators for Classification of Political Discourse Framing on Twitter
Kristen Johnson | I-Ta Lee | Dan Goldwasser
Proceedings of the Second Workshop on NLP and Computational Social Science

Politicians carefully word their statements in order to influence how others view an issue, a political strategy called framing. Simultaneously, these frames may also reveal the beliefs or positions on an issue of the politician. Simple language features such as unigrams, bigrams, and trigrams are important indicators for identifying the general frame of a text, for both longer congressional speeches and shorter tweets of politicians. However, tweets may contain multiple unigrams across different frames which limits the effectiveness of this approach. In this paper, we present a joint model which uses both linguistic features of tweets and ideological phrase indicators extracted from a state-of-the-art embedding-based model to predict the general frame of political tweets.

pdf bib
PurdueNLP at SemEval-2017 Task 1: Predicting Semantic Textual Similarity with Paraphrase and Event Embeddings
I-Ta Lee | Mahak Goindani | Chang Li | Di Jin | Kristen Marie Johnson | Xiao Zhang | Maria Leonor Pacheco | Dan Goldwasser
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

This paper describes our proposed solution for SemEval 2017 Task 1: Semantic Textual Similarity (Daniel Cer and Specia, 2017). The task aims at measuring the degree of equivalence between sentences given in English. Performance is evaluated by computing Pearson Correlation scores between the predicted scores and human judgements. Our proposed system consists of two subsystems and one regression model for predicting STS scores. The two subsystems are designed to learn Paraphrase and Event Embeddings that can take the consideration of paraphrasing characteristics and sentence structures into our system. The regression model associates these embeddings to make the final predictions. The experimental result shows that our system acquires 0.8 of Pearson Correlation Scores in this task.

2016

pdf bib
Adapting Event Embedding for Implicit Discourse Relation Recognition
Maria Leonor Pacheco | I-Ta Lee | Xiao Zhang | Abdullah Khan Zehady | Pranjal Daga | Di Jin | Ayush Parolia | Dan Goldwasser
Proceedings of the CoNLL-16 shared task