Related papers: Slide, Constrain, Parse, Repeat: Synchronous Slidi…

Most previous studies aim at extracting events from a single sentence, while document-level event extraction still remains under-explored. In this paper, we focus on extracting event arguments from an entire document, which mainly faces two…

Multi-Modal automatic speech recognition (ASR) techniques aim to leverage additional modalities to improve the performance of speech recognition systems. While existing approaches primarily focus on video or contextual information, the…

The Abstract Meaning Representation (AMR) is a representation for open-domain rich semantics, with potential use in fields like event extraction and machine translation. Node generation, typically done using a simple dictionary lookup, is…

Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias…

This paper presents a novel semantic representation, WISeR, that overcomes challenges for Abstract Meaning Representation (AMR). Despite its strengths, AMR is not easily applied to languages or domains without predefined semantic frames,…

The performance bottleneck of Automatic Speech Recognition (ASR) in stuttering speech scenarios has limited its applicability in domains such as speech rehabilitation. This paper proposed an LLM-driven ASR-SED multi-task learning framework…

We develop a novel technique to parse English sentences into Abstract Meaning Representation (AMR) using SEARN, a Learning to Search approach, by modeling the concept and the relation learning in a unified framework. We evaluate our parser…

Large language models (LLMs) have ushered in a new era for document-level machine translation (\textit{doc}-mt), yet their whole-document outputs challenge existing evaluation methods that assume sentence-by-sentence alignment. We introduce…

Self-supervised learning (SSL) has advanced speech processing but suffers from quadratic complexity due to self-attention. To address this, SummaryMixing (SM) has been proposed as a linear-time alternative that summarizes entire utterances…

Traditional machine learning assumes a stationary data distribution, yet many real-world applications operate on nonstationary streams in which the underlying concept evolves over time. This problem can also be viewed as task-free continual…

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local…

Generating an abstract from a collection of documents is a desirable capability for many real-world applications. However, abstractive approaches to multi-document summarization have not been thoroughly investigated. This paper studies the…

We propose SLARM, a feed-forward model that unifies dynamic scene reconstruction, semantic understanding, and real-time streaming inference. SLARM captures complex, non-uniform motion through higher-order motion modeling, trained solely on…

Cross-modal retrieval is generally performed by projecting and aligning the data from two different modalities onto a shared representation space. This shared space often also acts as a bridge for translating the modalities. We address the…

Despite recent advances, Automatic Speech Recognition (ASR) systems are still far from perfect. Typical errors include acronyms, named entities, and domain-specific special words for which little or no labeled data is available. To address…

Abstract meaning representations (AMRs) are broad-coverage sentence-level semantic representations. AMRs represent sentences as rooted labeled directed acyclic graphs. AMR parsing is challenging partly due to the lack of annotated…

Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…

The paper steps outside the comfort-zone of the traditional NLP tasks like automatic speech recognition (ASR) and machine translation (MT) to addresses two novel problems arising in the automated multilingual news monitoring: segmentation…

Overlapping speech remains a major challenge for automatic speech recognition (ASR) in real-world applications, particularly in broadcast media with dynamic, multi-speaker interactions. We propose a light-weight, target-speaker-based…

Large language models (LLMs) have advanced in large strides due to the effectiveness of the self-attention mechanism that processes and compares all tokens at once. However, this mechanism comes with a fundamental issue -- the predetermined…