相关论文: SETUP: Sentence-level English-To-Uniform Meaning R…

Structured text understanding on Visually Rich Documents (VRDs) is a crucial part of Document Intelligence. Due to the complexity of content and layout in VRDs, structured text understanding has been a challenging task. Most existing…

We propose an attention-based model that treats AMR parsing as sequence-to-graph transduction. Unlike most AMR parsers that rely on pre-trained aligners, external semantic resources, or data augmentation, our proposed parser is…

We present a system description of our contribution to the CoNLL 2019 shared task, Cross-Framework Meaning Representation Parsing (MRP 2019). The proposed architecture is our first attempt towards a semantic parsing extension of the UDPipe…

Generative Large Language Models (LLMs) are widely utilized for their excellence in various tasks. However, their tendency to produce inaccurate or misleading outputs poses a potential risk, particularly in high-stakes environments.…

Universal Multimodal Retrieval (UMR) aims to enable search across various modalities using a unified model, where queries and candidates can consist of pure text, images, or a combination of both. Previous work has attempted to adopt…

We present the Granular AMR Parsing Evaluation Suite (GrAPES), a challenge set for Abstract Meaning Representation (AMR) parsing with accompanying evaluation metrics. AMR parsers now obtain high scores on the standard AMR evaluation metric…

To capture user preference, transformer models have been widely applied to model sequential user behavior data. The core of transformer architecture lies in the self-attention mechanism, which computes the pairwise attention scores in a…

Despite the success of attention-based neural models for natural language generation and classification tasks, they are unable to capture the discourse structure of larger documents. We hypothesize that explicit discourse representations…

UniSpeech has achieved superior performance in cross-lingual automatic speech recognition (ASR) by explicitly aligning latent representations to phoneme units using multi-task self-supervised learning. While the learned representations…

Spatial Reasoning from language is essential for natural language understanding. Supporting it requires a representation scheme that can capture spatial phenomena encountered in language as well as in images and videos. Existing spatial…

Computing devices have recently become capable of interacting with their end users via natural language. However, they can only operate within a limited "supported" domain of discourse and fail drastically when faced with an out-of-domain…

Discourse Representation Structure (DRS) is an innovative semantic representation designed to capture the meaning of texts with arbitrary lengths across languages. The semantic representation parsing is essential for achieving natural…

Benchmarks that reflect the diversity and complexity of real-world documents are essential for accurately evaluating Automatic Text Recognition (ATR) systems, especially Vision-Large Language Models (vLLMs). Although recent models…

This report extends the Spectral Neuro-Symbolic Reasoning (Spectral NSR) framework by introducing three semantically grounded enhancements: (1) transformer-based node merging using contextual embeddings (e.g., Sentence-BERT, SimCSE) to…

Identifying semantically equivalent sentences is important for many cross-lingual and mono-lingual NLP tasks. Current approaches to semantic equivalence take a loose, sentence-level approach to "equivalence," despite previous evidence that…

Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions. Existing methods manifest limitations in leveraging nonverbal information for discerning complex…

Meaning in human language is relational, context dependent, and emergent, arising from dynamic systems of signs rather than fixed word-concept mappings. In computational settings, this semiotic and interpretive complexity complicates the…

A growing interest in tasks involving language understanding by the NLP community has led to the need for effective semantic parsing and inference. Modern NLP systems use semantic representations that do not quite fulfill the nuanced needs…

Universal language representation is the holy grail in machine translation (MT). Thanks to the new neural MT approach, it seems that there are good perspectives towards this goal. In this paper, we propose a new architecture based on…

Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed…