Zero-shot cross-lingual transfer is a central task in multilingual NLP,
...
Version incompatibility issues are rampant when reusing or reproducing d...
Recognizing software entities such as library names from free-form text ...
Large language models (LLMs) have demonstrated remarkable generalizabili...
Traditional text classification typically categorizes texts into pre-def...
Natural language understanding (NLU) models often suffer from unintended...
Software developers often resort to Stack Overflow (SO) to fill their
pr...
Improving factual consistency of abstractive summarization has been a wi...
Event temporal reasoning aims at identifying the temporal relations betw...
With the emergence of more powerful large language models (LLMs), such a...
Language models are often at risk of diverse backdoor attacks, especiall...
Instruction-tuned models are trained on crowdsourcing datasets with task...
Entity bias widely affects pretrained (large) language models, causing t...
Traditional sentence embedding models encode sentences into vector
repre...
Entity names play an effective role in relation extraction (RE) and ofte...
Goal-oriented Script Generation is a new task of generating a list of st...
Large language models (LLMs) encode parametric knowledge about world fac...
Relation extraction (RE), which has relied on structurally annotated cor...
Relation Extraction (RE) has been extended to cross-document scenarios
b...
Two key obstacles in biomedical relation extraction (RE) are the scarcit...
Neural language models (LMs) have achieved impressive results on various...
Abstractive summarization models typically learn to capture the salient
...
Named geographic entities (geo-entities for short) are the building bloc...
In this paper, we seek to improve the faithfulness of TempRel extraction...
Parameter-efficient tuning aims at updating only a small subset of param...
Natural language often describes events in different granularities, such...
In recent years, vision-language models (VLMs) have shown remarkable
per...
Recently there is an increasing scholarly interest in time-varying knowl...
This work presents an extended ordinary state-based peridynamics (XOSBPD...
Reasoning with preconditions such as "glass can be used for drinking wat...
The entity typing task aims at predicting one or more words or phrases t...
Relation extraction (RE) models have been challenged by their reliance o...
Controlled table-to-text generation seeks to generate natural language
d...
Entity types and textual context are essential properties for sentence-l...
Recent literature focuses on utilizing the entity information in the
sen...
We study dangling-aware entity alignment in knowledge graphs (KGs), whic...
Semantic typing aims at classifying tokens or spans of interest in a tex...
Current question answering (QA) systems primarily consider the single-an...
The task of ultra-fine entity typing (UFET) seeks to predict diverse and...
Deep neural networks are often overparameterized and may not easily achi...
Humans use natural language to compose common concepts from their enviro...
Representing a label distribution as a one-hot vector is a common practi...
Taxonomies are valuable resources for many applications, but the limited...
Storytelling, whether via fables, news reports, documentaries, or memoir...
Event mentions in text correspond to real-world events of varying degree...
Tables provide valuable knowledge that can be used to verify textual
sta...
Inspired by evidence that pretrained language models (LMs) encode common...
Drilling and Extraction Automated System (DREAMS) is a fully automated
p...
This study presents a finite element analysis approach to non-linear and...
The task of natural language table retrieval (NLTR) seeks to retrieve
se...