Fei-Tzin Lee


2023

pdf bib
Contrastive Loss is All You Need to Recover Analogies as Parallel Lines
Narutatsu Ri | Fei-Tzin Lee | Nakul Verma
Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)

While static word embedding models are known to represent linguistic analogies as parallel lines in high-dimensional space, the underlying mechanism as to why they result in such geometric structures remains obscure. We find that an elementary contrastive-style method employed over distributional information performs competitively with popular word embedding models on analogy recovery tasks, while achieving dramatic speedups in training time. Further, we demonstrate that a contrastive loss is sufficient to create these parallel structures in word embeddings, and establish a precise relationship between the co-occurrence statistics and the geometric structure of the resulting word embeddings.

2022

pdf bib
Using Structured Content Plans for Fine-grained Syntactic Control in Pretrained Language Model Generation
Fei-Tzin Lee | Miguel Ballesteros | Feng Nan | Kathleen McKeown
Proceedings of the 29th International Conference on Computational Linguistics

Large pretrained language models offer powerful generation capabilities, but cannot be reliably controlled at a sub-sentential level. We propose to make such fine-grained control possible in pretrained LMs by generating text directly from a semantic representation, Abstract Meaning Representation (AMR), which is augmented at the node level with syntactic control tags. We experiment with English-language generation of three modes of syntax relevant to the framing of a sentence - verb voice, verb tense, and realization of human entities - and demonstrate that they can be reliably controlled, even in settings that diverge drastically from the training distribution. These syntactic aspects contribute to how information is framed in text, something that is important for applications such as summarization which aim to highlight salient information.

2019

pdf bib
Identifying therapist conversational actions across diverse psychotherapeutic approaches
Fei-Tzin Lee | Derrick Hull | Jacob Levine | Bonnie Ray | Kathy McKeown
Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology

While conversation in therapy sessions can vary widely in both topic and style, an understanding of the underlying techniques used by therapists can provide valuable insights into how therapists best help clients of different types. Dialogue act classification aims to identify the conversational “action” each speaker takes at each utterance, such as sympathizing, problem-solving or assumption checking. We propose to apply dialogue act classification to therapy transcripts, using a therapy-specific labeling scheme, in order to gain a high-level understanding of the flow of conversation in therapy sessions. We present a novel annotation scheme that spans multiple psychotherapeutic approaches, apply it to a large and diverse corpus of psychotherapy transcripts, and present and discuss classification results obtained using both SVM and neural network-based models. The results indicate that identifying the structure and flow of therapeutic actions is an obtainable goal, opening up the opportunity in the future to provide therapeutic recommendations tailored to specific client situations.

2018

pdf bib
Detecting Gang-Involved Escalation on Social Media Using Context
Serina Chang | Ruiqi Zhong | Ethan Adams | Fei-Tzin Lee | Siddharth Varia | Desmond Patton | William Frey | Chris Kedzie | Kathy McKeown
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Gang-involved youth in cities such as Chicago have increasingly turned to social media to post about their experiences and intents online. In some situations, when they experience the loss of a loved one, their online expression of emotion may evolve into aggression towards rival gangs and ultimately into real-world violence. In this paper, we present a novel system for detecting Aggression and Loss in social media. Our system features the use of domain-specific resources automatically derived from a large unlabeled corpus, and contextual representations of the emotional and semantic content of the user’s recent tweets as well as their interactions with other users. Incorporating context in our Convolutional Neural Network (CNN) leads to a significant improvement.