Elahe Rahimtoroghi


2020

pdf bib
What Happens To BERT Embeddings During Fine-tuning?
Amil Merchant | Elahe Rahimtoroghi | Ellie Pavlick | Ian Tenney
Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

While much recent work has examined how linguistic information is encoded in pre-trained sentence representations, comparatively little is understood about how these models change when adapted to solve downstream tasks. Using a suite of analysis techniques—supervised probing, unsupervised similarity analysis, and layer-based ablations—we investigate how fine-tuning affects the representations of the BERT model. We find that while fine-tuning necessarily makes some significant changes, there is no catastrophic forgetting of linguistic phenomena. We instead find that fine-tuning is a conservative process that primarily affects the top layers of BERT, albeit with noteworthy variation across tasks. In particular, dependency parsing reconfigures most of the model, whereas SQuAD and MNLI involve much shallower processing. Finally, we also find that fine-tuning has a weaker effect on representations of out-of-domain sentences, suggesting room for improvement in model generalization.

2017

pdf bib
Inference of Fine-Grained Event Causality from Blogs and Films
Zhichao Hu | Elahe Rahimtoroghi | Marilyn Walker
Proceedings of the Events and Stories in the News Workshop

Human understanding of narrative is mainly driven by reasoning about causal relations between events and thus recognizing them is a key capability for computational models of language understanding. Computational work in this area has approached this via two different routes: by focusing on acquiring a knowledge base of common causal relations between events, or by attempting to understand a particular story or macro-event, along with its storyline. In this position paper, we focus on knowledge acquisition approach and claim that newswire is a relatively poor source for learning fine-grained causal relations between everyday events. We describe experiments using an unsupervised method to learn causal relations between events in the narrative genres of first-person narratives and film scene descriptions. We show that our method learns fine-grained causal relations, judged by humans as likely to be causal over 80% of the time. We also demonstrate that the learned event pairs do not exist in publicly available event-pair datasets extracted from newswire.

pdf bib
Modelling Protagonist Goals and Desires in First-Person Narrative
Elahe Rahimtoroghi | Jiaqi Wu | Ruimin Wang | Pranav Anand | Marilyn Walker
Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue

Many genres of natural language text are narratively structured, a testament to our predilection for organizing our experiences as narratives. There is broad consensus that understanding a narrative requires identifying and tracking the goals and desires of the characters and their narrative outcomes. However, to date, there has been limited work on computational models for this problem. We introduce a new dataset, DesireDB, which includes gold-standard labels for identifying statements of desire, textual evidence for desire fulfillment, and annotations for whether the stated desire is fulfilled given the evidence in the narrative context. We report experiments on tracking desire fulfillment using different methods, and show that LSTM Skip-Thought model achieves F-measure of 0.7 on our corpus.

2016

pdf bib
Learning Fine-Grained Knowledge about Contingent Relations between Everyday Events
Elahe Rahimtoroghi | Ernesto Hernandez | Marilyn Walker
Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

2014

pdf bib
Identifying Narrative Clause Types in Personal Stories
Reid Swanson | Elahe Rahimtoroghi | Thomas Corcoran | Marilyn Walker
Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)

2013

pdf bib
Unsupervised Induction of Contingent Event Pairs from Film Scenes
Zhichao Hu | Elahe Rahimtoroghi | Larissa Munishkina | Reid Swanson | Marilyn A. Walker
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing