Related papers: Open-source Frame Semantic Parsing
Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: sometimes they tend to merely copy character sequences…
Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing. Recent work shows that the attention mechanism inside Transformer may not be…
In production recommender systems, feature preprocessing must be faithfully replicated across training and inference environments. This often requires duplicating logic between offline and online environments, increasing engineering effort…
Predictive modeling often faces challenges due to limited data availability and quality, especially in domains where collected features are weakly correlated with outcomes and where additional feature collection is constrained by ethical or…
Parameter-efficient fine-tuning (PEFT) has become a common method for fine-tuning large language models, where a base model can serve multiple users through PEFT module switching. To enhance user experience, base models require periodic…
Effectively parsing the facade is essential to 3D building reconstruction, which is an important computer vision problem with a large amount of applications in high precision map for navigation, computer aided design, and city generation…
Time normalization is the task of converting natural language temporal expressions into machine-readable representations. It underpins many downstream applications in information retrieval, question answering, and clinical decision-making.…
Recent advancements in Large Language Models (LLMs) have revealed a significant performance gap between closed-source and open-source models, particularly in tasks requiring complex reasoning and precise instruction following. This paper…
Neural machine translation (NMT) is nowadays commonly applied at the subword level, using byte-pair encoding. A promising alternative approach focuses on character-level translation, which simplifies processing pipelines in NMT…
Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes increasingly costly. Parameter-efficient fine-tuning methods…
Prepositions are an important vehicle for indicating semantic roles. Their meanings are difficult to analyze and they are often discarded in processing text. The Preposition Project is designed to provide a comprehensive database of…
Predicting linearized Abstract Meaning Representation (AMR) graphs using pre-trained sequence-to-sequence Transformer models has recently led to large improvements on AMR parsing benchmarks. These parsers are simple and avoid explicit…
Fine-tuning large pre-trained language models (LLMs) on particular datasets is a commonly employed strategy in Natural Language Processing (NLP) classification tasks. However, this approach usually results in a loss of models…
For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm. Semantic parsers map natural language into logical forms, the classic representation for many…
Many applications of unpaired image-to-image translation require the input contents to be preserved semantically during translations. Unaware of the inherently unmatched semantics distributions between source and target domains, existing…
Understanding the world around us and making decisions about the future is a critical component to human intelligence. As autonomous systems continue to develop, their ability to reason about the future will be the key to their success.…
Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer…
Artificial intelligence (AI) is ushering in a new era for communication. As a result, the establishment of a semantic communication framework is putting on the agenda. Based on a realistic semantic communication model, this paper develops a…
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate…
Framing is among the most extensively used concepts in the field of communication science. The availability of digital data offers new possibilities for studying how specific aspects of social reality are made more salient in online…