Дәл сәйкестік ұпайы
Related Papers
A deep-learning framework to detect sarcasm targets
AbstractIn this paper we propose a deep learning framework for sarcasm target detection in predefined sarcastic texts. Identification of sarcasm targets can help in many core natural language processing tasks …...
TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions
AbstractA critical part of reading is being able to understand the temporal relationships between events described in a passage of text, even when those relationships are not explicitly stated. However, …...
What’s in a Name? Answer Equivalence For Open-Domain Question Answering
AbstractA flaw in QA evaluation is that annotations often only provide one gold answer. Thus, model predictions semantically equivalent to the answer but superficially different are considered incorrect. This work …...
FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering
AbstractGenerative models have recently started to outperform extractive models in Open Domain Question Answering, largely by leveraging their decoder to attend over multiple encoded passages and combining their information. However, …...
Improving Event Duration Question Answering by Leveraging Existing Temporal Information Extraction Data
AbstractUnderstanding event duration is essential for understanding natural language. However, the amount of training data for tasks like duration question answering, i.e., McTACO, is very limited, suggesting a need for …...
You Only Need One Model for Open-domain Question Answering
AbstractRecent approaches to Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank passages with a separate reranker model and generate an answer using another …...
Party Extraction from Legal Contract Using Contextualized Span Representations of Parties
AbstractExtracting legal entities from legal documents, particularly legal parties in contract documents, poses a significant challenge for legal assistive software. Many existing party extraction systems tend to generate numerous false …...