Papers by Dhivya Chinnappa
Possessors Change Over Time: A Case Study with Artworks (D18-1)
Copied to clipboard
| Challenge: | Existing methods to extract possession relations from Wikipedia articles can be used to extract possessors over time. |
| Approach: | They propose to extract possession relations from Wikipedia articles and temporal information indicating when these relations are true. |
| Outcome: | The proposed annotation scheme yields many possessors over time for a given artwork, and an LSTM ensemble can automate the task. |
Beyond Possession Existence: Duration and Co-Possession (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work on possession existence targets possession existence, but there is complementary information that can be extracted. |
| Approach: | They propose to use corpora to annotate possession existence and experimental results to determine possession duration and co-possessions. |
| Outcome: | The proposed annotations show that text is more useful than the image for solving these tasks. |
Determining Event Outcomes: The Case of #fail (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that edibility is easier to predict than outcome quality. |
| Approach: | They use tweets containing #cookingFail or #bakingFails to determine event outcomes in social media. |
| Outcome: | The results show that edibility is easier to predict than outcome quality. |
Mining Possessions: Existence, Type and Temporal Anchors (N18-1)
Copied to clipboard
| Challenge: | Existing annotations for possession relations can be used to predict possession existence, possession type and temporal anchors. |
| Approach: | They propose to use text annotations to mine possession relations from text . they assign temporal anchors indicating when possession holds between possessor and possessee . |
| Outcome: | The proposed task can predict possession existence, possession type and temporal anchors, and it can be automated. |
Interpreting Answers to Yes-No Questions in User-Generated Content (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on yes-no questions outside social media have found that yes and no keywords are rare in answers. |
| Approach: | They propose a corpus of 4,442 yes-no question-answer pairs from twitter . they find that yes and no keywords are rare in answers and poor indicators of correct interpretation . |
| Outcome: | The proposed corpus of 4,442 yes-no question-answer pairs shows that large language models are far from solving the problem. |
An Analysis of Negation in Natural Language Understanding Corpora (2022.acl-short)
Copied to clipboard
| Challenge: | Using annotator-generated examples, one can evaluate systems with synthetic language that is not representative of language in the wild. |
| Approach: | They analyze negation in eight popular corpora spanning six natural language understanding tasks. |
| Outcome: | The proposed corpora have few negations compared to general-purpose English and are often unimportant . state-of-the-art transformers obtain significantly worse results with instances that contain negation, especially if the negations are important. |
WikiPossessions: Possession Timeline Generation as an Evaluation Benchmark for Machine Reading Comprehension of Long Texts (2020.lrec-1)
Copied to clipboard
| Challenge: | a new corpus of articles is created for the task of temporally-oriented possession . the task is open-domain and can be used to track possession in other texts . |
| Approach: | They propose a new corpus for the task of temporally-oriented possession . they annotate Wikipedia articles for 90 different well-known artifacts . |
| Outcome: | The proposed task is based on annotated Wikipedia articles for 90 artifacts, including paintings, diamonds, and archaeological artifos. |
Extracting Possessions from Social Media: Images Complement Language (D19-1)
Copied to clipboard
| Challenge: | Existing studies show that authors of tweets possess objects they tweet about. |
| Approach: | They propose a dataset and experiments to determine whether tweet authors possess objects they tweet about. |
| Outcome: | The proposed strategy incorporates visual information into any neural network beyond weights from pretrained networks. |