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

Transition-based dependency parsers often need sequences of local shift and reduce operations to produce certain attachments. Correct individual decisions hence require global information about the sentence context and mistakes cause error…

Transcribing and understanding multi-speaker conversations requires speech recognition, speaker attribution, and timestamp localization. While speech LLMs excel at single-speaker tasks, multi-speaker scenarios remain challenging due to…

Automating the annotation of scanned documents is challenging, requiring a balance between computational efficiency and accuracy. DocParseNet addresses this by combining deep learning and multi-modal learning to process both text and visual…

Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR…

We present algorithms for aligning components of Abstract Meaning Representation (AMR) graphs to spans in English sentences. We leverage unsupervised learning in combination with heuristics, taking the best of both worlds from previous AMR…

The Speaker Diarization and Recognition (SDR) task aims to predict "who spoke when and what" within an audio clip, which is a crucial task in various real-world multi-speaker scenarios such as meeting transcription and dialogue systems.…

We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window…

Cross-encoders are effective passage and document re-rankers but less efficient than other neural or classic retrieval models. A few previous studies have applied windowed self-attention to make cross-encoders more efficient. However, these…

A notable challenge in Multi-Document Summarization (MDS) is the extremely-long length of the input. In this paper, we present an extract-then-abstract Transformer framework to overcome the problem. Specifically, we leverage pre-trained…

When applied to processing long text, Large Language Models (LLMs) are limited by their context window. Existing efforts to address this limitation involve training specialized architectures, and cannot be easily applied to off-the-shelf…

Meaning Representation (AMR) is a graph-based semantic representation for sentences, composed of collections of concepts linked by semantic relations. AMR-based approaches have found success in a variety of applications, but a challenge to…

The construction of high-quality parallel corpora for translation research has increasingly evolved from simple sentence alignment to complex, multi-layered annotation tasks. This methodological shift presents significant challenges for…

Code-switching automatic speech recognition (ASR) aims to transcribe speech that contains two or more languages accurately. To better capture language-specific speech representations and address language confusion in code-switching ASR, the…

Retrieval-Augmented Generation (RAG) grounds large language model outputs in external evidence, but remains challenged on multi-hop question answering that requires long reasoning. Recent works scale RAG at inference time along two…

Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT with four…

In the era of Big Data and Deep Learning, there is a common view that machine learning approaches are the only way to cope with the robust and scalable information extraction and summarization. It has been recently proposed that the CNL…

Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and…

In the training of transition-based dependency parsers, an oracle is used to predict a transition sequence for a sentence and its gold tree. However, the transition system may exhibit ambiguity, that is, there can be multiple correct…

Abstract Meaning Representation (AMR) is a Semantic Parsing formalism that aims at providing a semantic graph abstraction representing a given text. Current approaches are based on autoregressive language models such as BART or T5,…

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward…