Search Results for author:
Found 23 papers, 4 papers with code
Dartmouth at SemEval-2022 Task 6: Detection of Sarcasm
This paper introduces the result of Team Dartmouth’s experiments on each of the five subtasks for the detection of sarcasm in English and Arabic tweets.
Multi-resolution Annotations for Emoji Prediction
The lack of multi-label and aspect-level emoji prediction datasets is one of the bottlenecks for this task.
DartmouthCS at SemEval-2022 Task 8: Predicting Multilingual News Article Similarity with Meta-Information and Translation
This paper presents our approach for tackling SemEval-2022 Task 8: Multilingual News Article Similarity.
On the Exploration of LM-Based Soft Modular Robot Design
Recent large language models (LLMs) have demonstrated promising capabilities in modeling real-world knowledge and enhancing knowledge-based generation tasks.
Judging the Judges: A Systematic Investigation of Position Bias in Pairwise Comparative Assessments by LLMs
LLM-as-a-Judge presents a promising alternative to human evaluators across various tasks, but inherent biases, especially position bias - a tendency to favor solutions based on their position in the prompt - have compromised its effectiveness.
Joint Latent Topic Discovery and Expectation Modeling for Financial Markets
In the pursuit of accurate and scalable quantitative methods for financial market analysis, the focus has shifted from individual stock models to those capturing interrelations between companies and their stocks.
Graph-Level Embedding for Time-Evolving Graphs
We evaluate our proposed model on five publicly available datasets for the task of temporal graph similarity ranking, and our model outperforms baseline methods.
Capturing Topic Framing via Masked Language Modeling
Differential framing of issues can lead to divergent world views on important issues.
EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English
While cultural backgrounds have been shown to affect linguistic expressions, existing natural language processing (NLP) research on culture modeling is overly coarse-grained and does not examine cultural differences among speakers of the same language.
Cultural Vocal Bursts Intensity Prediction
Language Modelling
+5
Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization
Recent years have seen a rise in the development of representational learning methods for graph data.
Embedding Node Structural Role Identity Using Stress Majorization
In this paper, we present a novel and flexible framework using stress majorization, to transform the high-dimensional role identities in networks directly (without approximation or indirect modeling) to a low-dimensional embedding space.
GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks
Compared to AUTOSEM, a strong baseline method, GradTS improves the performance of MT-DNN with a bert-base-cased backend model, from 0. 33% to 17. 93% on 8 natural language understanding (NLU) tasks in the GLUE benchmarks.
Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks
Through extensive experiments, we show that (1) pruning a number of attention heads in a multi-lingual Transformer-based model has, in general, positive effects on its performance in cross-lingual and multi-lingual tasks and (2) the attention heads to be pruned can be ranked using gradients and identified with a few trial experiments.
Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
A common type of network is the heterogeneous network, where the nodes (and edges) can be of different types.
BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models
This paper describes a system submitted by team BigGreen to LCP 2021 for predicting the lexical complexity of English words in a given context.
Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic
This paper describes our approach to the Toxic Spans Detection problem (SemEval-2021 Task 5).
Improvements and Extensions on Metaphor Detection
Finally, we clean up the improper or outdated annotations in one of the MD benchmark datasets and re-benchmark it with our Transformer-based model.
An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data
The field of NLP has seen unprecedented achievements in recent years.
Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation
For instance, Data Boost improves F1 for the three tasks by 8. 7% on average when given only 10% of the whole data for training.
Towards Improved Model Design for Authorship Identification: A Survey on Writing Style Understanding
While other tasks based on linguistic style understanding benefit from deep learning methods, these methods have not behaved as well as traditional machine learning methods in many authorship-based tasks.
BIG-bench Machine Learning
Natural Language Understanding
+1
Emoji Prediction: Extensions and Benchmarking
In this paper, we extend the existing setting of the emoji prediction task to include a richer set of emojis and to allow multi-label classification on the task.
ChiMed: A Chinese Medical Corpus for Question Answering
Question answering (QA) is a challenging task in natural language processing (NLP), especially when it is applied to specific domains.
