Related papers: Towards Evaluation of Cross-document Coreference R…
Considering the rapidly increasing number of academic papers, searching for and citing appropriate references has become a non-trial task during the wiring of papers. Recommending a handful of candidate papers to a manuscript before…
The recent integration of deep learning and pairwise similarity annotation-based constrained clustering -- i.e., $\textit{deep constrained clustering}$ (DCC) -- has proven effective for incorporating weak supervision into massive data…
Although WordNet is a valuable resource because of its structured semantic networks and extensive vocabulary, its fine-grained sense distinctions can be challenging for second-language learners. To address this issue, we developed a version…
Cross-domain sequential recommendation (CDSR) shifts the modeling of user preferences from flat to stereoscopic by integrating and learning interaction information from multiple domains at different granularities (ranging from…
The evaluation of cross-lingual semantic search models is often limited to existing datasets from tasks such as information retrieval and semantic textual similarity. We introduce Cross-Lingual Semantic Discrimination (CLSD), a lightweight…
Diacritics are orthographic marks that clarify pronunciation, distinguish similar words, or alter meaning. They play a central role in many writing systems, yet their impact on language technology has not been systematically quantified…
RAG systems enhance LLMs by incorporating external knowledge, which is crucial for domains that demand factual accuracy and up-to-date information. However, evaluating the multifaceted quality of RAG outputs, spanning aspects such as…
Cross-domain data integration drives interdisciplinary data reuse and knowledge transfer across domains. However, each discipline maintains its own metadata schemas and domain ontologies, employing distinct conceptual models and application…
Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge…
We describe the design and use of the CREER dataset, a large corpus annotated with rich English grammar and semantic attributes. The CREER dataset uses the Stanford CoreNLP Annotator to capture rich language structures from Wikipedia plain…
Multilingual document understanding remains limited for low-resource languages due to scarce training data and model-based annotation pipelines that perpetuate existing biases. We introduce DocAtlas, a framework that constructs…
This paper develops and implements a scalable methodology for (a) estimating the noisiness of labels produced by a typical crowdsourcing semantic annotation task, and (b) reducing the resulting error of the labeling process by as much as…
While measuring bias and robustness in coreference resolution are important goals, such measurements are only as good as the tools we use to measure them. Winogender Schemas (Rudinger et al., 2018) are an influential dataset proposed to…
Most approaches to cross-modal retrieval (CMR) focus either on object-centric datasets, meaning that each document depicts or describes a single object, or on scene-centric datasets, meaning that each image depicts or describes a complex…
Keyphrase generation aims to produce a set of phrases summarizing the essentials of a given document. Conventional methods normally apply an encoder-decoder architecture to generate the output keyphrases for an input document, where they…
News articles usually contain knowledge entities such as celebrities or organizations. Important entities in articles carry key messages and help to understand the content in a more direct way. An industrial news recommender system contains…
To support efficient, balanced news consumption, merging articles from diverse sources into one, potentially through crowdsourcing, could alleviate some hurdles. However, the merging process could also impact annotators' attitudes towards…
Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language…
In this paper, we propose a novel approach to consider multiple dimensions of relevance beyond topicality in cross-encoder re-ranking. On the one hand, current multidimensional retrieval models often use na\"ive solutions at the re-ranking…
Event coreference resolution (ECR) aims to group event mentions referring to the same real-world event into clusters. Most previous studies adopt the "encoding first, then scoring" framework, making the coreference judgment rely on event…