Evan Jaffe


2021

pdf bib
Coreference-aware Surprisal Predicts Brain Response
Evan Jaffe | Byung-Doh Oh | William Schuler
Findings of the Association for Computational Linguistics: EMNLP 2021

Recent evidence supports a role for coreference processing in guiding human expectations about upcoming words during reading, based on covariation between reading times and word surprisal estimated by a coreference-aware semantic processing model (Jaffe et al. 2020).The present study reproduces and elaborates on this finding by (1) enabling the parser to process subword information that might better approximate human morphological knowledge, and (2) extending evaluation of coreference effects from self-paced reading to human brain imaging data. Results show that an expectation-based processing effect of coreference is still evident even in the presence of the stronger psycholinguistic baseline provided by the subword model, and that the coreference effect is observed in both self-paced reading and fMRI data, providing evidence of the effect’s robustness.

2020

pdf bib
Coreference information guides human expectations during natural reading
Evan Jaffe | Cory Shain | William Schuler
Proceedings of the 28th International Conference on Computational Linguistics

Models of human sentence processing effort tend to focus on costs associated with retrieving structures and discourse referents from memory (memory-based) and/or on costs associated with anticipating upcoming words and structures based on contextual cues (expectation-based) (Levy,2008). Although evidence suggests that expectation and memory may play separable roles in language comprehension (Levy et al., 2013), theories of coreference processing have largely focused on memory: how comprehenders identify likely referents of linguistic expressions. In this study, we hypothesize that coreference tracking also informs human expectations about upcoming words, and we test this hypothesis by evaluating the degree to which incremental surprisal measures generated by a novel coreference-aware semantic parser explain human response times in a naturalistic self-paced reading experiment. Results indicate (1) that coreference information indeed guides human expectations and (2) that coreference effects on memory retrieval may exist independently of coreference effects on expectations. Together, these findings suggest that the language processing system exploits coreference information both to retrieve referents from memory and to anticipate upcoming material.

2018

pdf bib
Coreference and Focus in Reading Times
Evan Jaffe | Cory Shain | William Schuler
Proceedings of the 8th Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2018)

2017

pdf bib
Combining CNNs and Pattern Matching for Question Interpretation in a Virtual Patient Dialogue System
Lifeng Jin | Michael White | Evan Jaffe | Laura Zimmerman | Douglas Danforth
Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications

For medical students, virtual patient dialogue systems can provide useful training opportunities without the cost of employing actors to portray standardized patients. This work utilizes word- and character-based convolutional neural networks (CNNs) for question identification in a virtual patient dialogue system, outperforming a strong word- and character-based logistic regression baseline. While the CNNs perform well given sufficient training data, the best system performance is ultimately achieved by combining CNNs with a hand-crafted pattern matching system that is robust to label sparsity, providing a 10% boost in system accuracy and an error reduction of 47% as compared to the pattern-matching system alone.

2016

pdf bib
A Corpus of Word-Aligned Asked and Anticipated Questions in a Virtual Patient Dialogue System
Ajda Gokcen | Evan Jaffe | Johnsey Erdmann | Michael White | Douglas Danforth
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

We present a corpus of virtual patient dialogues to which we have added manually annotated gold standard word alignments. Since each question asked by a medical student in the dialogues is mapped to a canonical, anticipated version of the question, the corpus implicitly defines a large set of paraphrase (and non-paraphrase) pairs. We also present a novel process for selecting the most useful data to annotate with word alignments and for ensuring consistent paraphrase status decisions. In support of this process, we have enhanced the earlier Edinburgh alignment tool (Cohn et al., 2008) and revised and extended the Edinburgh guidelines, in particular adding guidance intended to ensure that the word alignments are consistent with the overall paraphrase status decision. The finished corpus and the enhanced alignment tool are made freely available.

2015

pdf bib
AZMAT: Sentence Similarity Using Associative Matrices
Evan Jaffe | Lifeng Jin | David King | Marten van Schijndel
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

pdf bib
Interpreting Questions with a Log-Linear Ranking Model in a Virtual Patient Dialogue System
Evan Jaffe | Michael White | William Schuler | Eric Fosler-Lussier | Alex Rosenfeld | Douglas Danforth
Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications