Search Results for author:
Found 11 papers, 4 papers with code
Analysis of Zero-Shot Crosslingual Learning between English and Korean for Named Entity Recognition
This paper presents a English-Korean parallel dataset that collects 381K news articles where 1, 400 of them, comprising 10K sentences, are manually labeled for crosslingual named entity recognition (NER).
FantasyCoref: Coreference Resolution on Fantasy Literature Through Omniscient Writer’s Point of View
This paper presents a new corpus and annotation guideline for a novel coreference resolution task on fictional texts, and analyzes its unique characteristics.
CAT: Contrastive Adapter Training for Personalized Image Generation
Finally, we mention the possibility of CAT in the aspects of multi-concept adapter and optimization.
TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation
In this paper, we propose Teacher-leading Multimodal fusion network for ERC (TelME).
Ranked #3 on
Emotion Recognition in Conversation
on MELD
Emotion Recognition in Conversation
Knowledge Distillation
+1
Topic Segmentation Model Focusing on Local Context
In the topic segmentation task, topic coherence is critical in predicting segmentation boundaries.
Evaluating Research Novelty Detection: Counterfactual Approaches
We find the novelty is not a singular concept, and thus inherently lacks of ground truth annotations with cross-annotator agreement, which is a major obstacle in evaluating these models.
AutoSense Model for Word Sense Induction
Thus, we aim to eliminate these requirements and solve the sense granularity problem by proposing AutoSense, a latent variable model based on two observations: (1) senses are represented as a distribution over topics, and (2) senses generate pairings between the target word and its neighboring word.
Ranked #2 on
Word Sense Induction
on SemEval 2010 WSI
Analyzing Impact, Trend, and Diffusion of Knowledge associated with Neoplasms Research
In this talk, we introduce the notion of entitymetrics to provide a new lens for understanding the impact, trend, and diffusion of knowledge associated with neoplasms research.
Building Content-driven Entity Networks for Scarce Scientific Literature using Content Information
The results show that the co-occurrence and citation networks constructed using the proposed method outperforms the traditional-based networks.
