Papers by Ellen Jiang
Learning Prototypical Functions for Physical Artifacts (2021.acl-long)
Copied to clipboard
| Challenge: | a new task is designed to learn the prototypical uses of human-made physical objects . human beings are creative, and they create things for a reason . humans often infer that the object will be used in the most prototypical way unless told otherwise . |
| Approach: | They propose a task to learn the prototypical uses for human-made physical objects . they use frames from FrameNet to represent a set of common functions for objects based on their prototypical function . |
| Outcome: | The proposed task uses masked patterns to model prototypical uses for objects . the proposed model predicts the prototypical functions of objects and can be used to make models . |
Exploiting Definitions for Frame Identification (2021.eacl-main)
Copied to clipboard
| Challenge: | a frame-semantic parsing task is to determine which frame best captures the meaning of a word or phrase in a sentence. |
| Approach: | They propose a frame identification model that generates representations for frames and lexical units (senses) they evaluate the model on three data sets and show it consistently achieves better performance than previous systems. |
| Outcome: | The proposed model consistently outperforms previous systems on three data sets. |
Identifying Physical Object Use in Sentences (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prior research has focused on learning the prototypical functions of physical objects . but many sentences refer to objects even when they are not used . |
| Approach: | They propose a task that determines whether a physical object mentioned in a sentence was used or likely will be used. |
| Outcome: | The proposed model exploits data augmentation methods and FrameNet to fine-tune a pre-trainedmodel. |
Learning Prototypical Goal Activities for Locations (P18-1)
Copied to clipboard
| Challenge: | a goal-act is an activity that represents a common reason people go to a location . recognizing goals is essential for narrative text understanding and story comprehension . |
| Approach: | They use a text corpus and semi-supervised learning to learn goal-acts for specific locations . they extract activities and locations that co-occur in goal-oriented syntactic patterns . |
| Outcome: | The proposed method outperforms baseline methods when judged against goal-acts identified by human annotators. |
Exploiting Commonsense Knowledge about Objects for Visual Activity Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing tasks that aim to identify the objects in an image are object detection and image classification, but recent work has focused on more comprehensive image under- standing tasks. |
| Approach: | They propose to incorporate commonsense knowledge about physical objects into a transformer-based model that is trained to predict the actionverb for visual activity recognition. |
| Outcome: | The proposed model incorporates prototypical function knowledge about physical objects to predict the actionverb for visual activity recognition. |
Affective Event Classification with Discourse-enhanced Self-training (2020.emnlp-main)
Copied to clipboard
| Challenge: | Prior work on recognizing affective events focused on producing lexical resources of verbs or event phrases with corresponding affective polarity values. |
| Approach: | They propose a BERT-based model for affective event classification and a discourse-enhanced self-training method that iteratively improves the classifier with unlabeled data. |
| Outcome: | The proposed model outperforms existing models with unlabeled data and improves recall and precision. |
My Heart Skipped a Beat! Recognizing Expressions of Embodied Emotion in Natural Language (2024.naacl-long)
Copied to clipboard
| Challenge: | a new task is needed to recognize physical manifestations of emotions in natural language . physical manifestation of emotions affects not only our mental state but also our physical state . |
| Approach: | They propose a task to recognize expressions of embodied emotion in natural language . they use body part mentions with human annotations to extract emotional manner expressions . |
| Outcome: | The proposed model can train without gold data and improve performance with gold data. |
The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models (2020.emnlp-demos)
Copied to clipboard
Ian Tenney, James Wexler, Jasmijn Bastings, Tolga Bolukbasi, Andy Coenen, Sebastian Gehrmann, Ellen Jiang, Mahima Pushkarna, Carey Radebaugh, Emily Reif, Ann Yuan
| Challenge: | Existing tools for modeling and understanding models are limited . existing tools can assist practitioners in understanding and evaluating models . |
| Approach: | They present an open-source platform for visualization and understanding of NLP models. |
| Outcome: | The language interpretability tool (lit) is an open-source platform for visualization and understanding of NLP models. |