Related papers: Automatic Construction of Sememe Knowledge Bases v…
Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring a substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the…
Tokenization significantly influences language models(LMs)' performance. This paper traces the evolution of tokenizers from word-level to subword-level, analyzing how they balance tokens and types to enhance model adaptability while…
Search has for a long time been an important tool for users to retrieve information. Syntactic search is matching documents or objects containing specific keywords like user-history, location, preference etc. to improve the results.…
The inherent inflexibility and incompleteness of commonsense knowledge bases (KB) has limited their usefulness. We describe a system called Displacer for performing KB queries extended with the analogical capabilities of the word2vec…
Semantic feature norms, lists of features that concepts do and do not possess, have played a central role in characterizing human conceptual knowledge, but require extensive human labor. Large language models (LLMs) offer a novel avenue for…
We present OpenGloss, a synthetic encyclopedic dictionary and semantic knowledge graph for English that integrates lexicographic definitions, encyclopedic context, etymological histories, and semantic relationships in a unified resource.…
The Spoken Language Understanding Evaluation (SLUE) suite of benchmark tasks was recently introduced to address the need for open resources and benchmarking of complex spoken language understanding (SLU) tasks, including both classification…
We present a generative model to map natural language questions into SQL queries. Existing neural network based approaches typically generate a SQL query word-by-word, however, a large portion of the generated results are incorrect or not…
Bilingual word embeddings represent words of two languages in the same space, and allow to transfer knowledge from one language to the other without machine translation. The main approach is to train monolingual embeddings first and then…
Semantic map models (SMMs) construct a network-like conceptual space from cross-linguistic instances or forms, based on the connectivity hypothesis. This approach has been widely used to represent similarity and entailment relationships in…
Most people do not interact with Semantic Web data directly. Unless they have the expertise to understand the underlying technology, they need textual or visual interfaces to help them make sense of it. We explore the problem of generating…
Dense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art results in various tasks requiring semantic understanding.…
Semantic knowledge bases are regarded as a promising technology for upcoming 6G communications. However, existing studies mainly focus on source-side semantic modeling while overlooking the structural impact of propagation environments on…
The usefulness and usability of knowledge bases (KBs) is often limited by quality issues. One common issue is the presence of erroneous assertions, often caused by lexical or semantic confusion. We study the problem of correcting such…
We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal intervention. To achieve this, we adapt neural…
Knowledge Base Question Answering (KBQA) aims to answer natural language questions with factual information such as entities and relations in KBs. However, traditional Pre-trained Language Models (PLMs) are directly pre-trained on…
Building natural language interfaces typically uses a semantic parser to parse the user's natural language and convert it into structured \textbf{S}emantic \textbf{L}ogic \textbf{F}orms (SLFs). The mainstream approach is to adopt a…
We propose KDSL, a new word sense disambiguation (WSD) framework that utilizes knowledge to automatically generate sense-labeled data for supervised learning. First, from WordNet, we automatically construct a semantic knowledge base called…
Processing low-resource languages, such as Kiswahili, using machine learning is difficult due to lack of adequate training data. However, such low-resource languages are still important for human communication and are already in daily use…
In machine translation it is common phenomenon that machine-readable dictionaries and standard parsing rules are not enough to ensure accuracy in parsing and translating English phrases into Korean language, which is revealed in misleading…