paper-with-me

Papers Word Alignment

“Word Alignment” 태그가 달린 논문 564편 · 필터 해제

Scaling Unsupervised Word Alignment to Documents via Structural Constraints

2026-08-21 · Michelle Wastl, Jannis Vamvas, Rico Sennrich arxiv

Word alignment has traditionally been studied between sentences, but many cross-lingual tasks increasingly require correspondences across full documents. While recent multilingual embedding models can encode long inputs,…

Word Alignment

OmniAlign: A Unified Multilingual Aligner for Word and Sentence Alignment

2026-08-19 · Mengpeng Yang, Jingxu Yang, Chao Chen, Tian Xia 외 arxiv

Cross-lingual sequence alignment is fundamental for building and exploiting parallel corpora, spanning mappings from documents and sentences down to words and subwords. Existing tools, however, typically specialize in a …

Long-Context UnderstandingSelf-Supervised LearningWord Alignment

Text Style Transfer with Machine Translation for Graphic Designs

2026-04-29 · Deergh Singh Budhauria, Sanyam Jain, Rishav Agarwal, Tracy King arxiv

Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audiences. To accomplish this, the textual content in the graphic designs need…

Text Style TransferMachine TranslationWord Alignment

Word Alignment-Based Evaluation of Uniform Meaning Representations

2026-03-27 · Daniel Zeman, Federica Gamba arxiv

Comparison and evaluation of graph-based representations of sentence meaning is a challenge because competing representations of the same sentence may have different number of nodes, and it is not obvious which nodes sho…

Word Alignment

Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation

2026-03-13 · Yifeng Liu, Siqi Ouyang, Yatish Hosmane Revanasiddappa, Lei Li arxiv

Large Language Models (LLMs) have demonstrated remarkable capability in machine translation on high-resource language pairs, yet their performance on low-resource translation still lags behind. Existing post-training met…

Reinforcement LearningMachine TranslationWord Alignment

EPIC-EuroParl-UdS: Information-Theoretic Perspectives on Translation and Interpreting

2026-03-10 · Maria Kunilovskaya, Christina Pollkläsener arxiv

This paper introduces an updated and combined version of the bidirectional English-German EPIC-UdS (spoken) and EuroParl-UdS (written) corpora containing original European Parliament speeches as well as their translation…

Machine TranslationWord Alignment

A Holistic Framework for Robust Bangla ASR and Speaker Diarization with Optimized VAD and CTC Alignment

2026-02-26 · Zarif Ishmam, Zarif Mahir, Shafnan Wasif, Md. Ishtiak Moin arxiv

Despite being one of the most widely spoken languages globally, Bangla remains a low-resource language in the field of Natural Language Processing (NLP). Mainstream Automatic Speech Recognition (ASR) and Speaker Diarizat…

Speaker DiarizationSpeech RecognitionActivity DetectionWord Alignment

Crowdsourcing Piedmontese to Test LLMs on Non-Standard Orthography

2026-02-16 · Gianluca Vico, Jindřich Libovický arxiv

We present a crowdsourced dataset for Piedmontese, an endangered Romance language of northwestern Italy. The dataset comprises 145 Italian-Piedmontese parallel sentences derived from Flores+, with translations produced b…

Machine TranslationWord Alignment

Unsupervised Cross-Lingual Part-of-Speech Tagging with Monolingual Corpora Only

2026-02-10 · Jianyu Zheng arxiv

Due to the scarcity of part-of-speech annotated data, existing studies on low-resource languages typically adopt unsupervised approaches for POS tagging. Among these, POS tag projection with word alignment method transfe…

Part-Of-Speech TaggingMachine TranslationWord AlignmentPOS Tagging

Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization

2026-02-10 · Joesph An, Phillip Keung, Jiaqi Wang, Orevaoghene Ahia 외 arxiv

Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level represe…

Speaker DiarizationWord Alignment

asr_eval: Algorithms and tools for multi-reference and streaming speech recognition evaluation

2026-01-28 · Oleg Sedukhin, Andrey Kostin arxiv

We propose several improvements to the speech recognition evaluation. First, we propose a string alignment algorithm that supports both multi-reference labeling, arbitrary-length insertions and better word alignment. Thi…

Speech RecognitionWord Alignment

Thinking With Bounding Boxes: Enhancing Spatio-Temporal Video Grounding via Reinforcement Fine-Tuning

2025-11-26 · Xin Gu, Haoji Zhang, Qihang Fan, Jingxuan Niu 외 arxiv

Spatio-temporal video grounding (STVG) requires localizing a target object in untrimmed videos both temporally and spatially from natural language descriptions. Despite their strong language understanding, multimodal lar…

Spatio-Temporal Video GroundingWord Alignment

The Arabic Generality Score: Another Dimension of Modeling Arabic Dialectness

2025-08-24 · Sanad Shaban, Nizar Habash arxiv

Arabic dialects form a diverse continuum, yet NLP models often treat them as discrete categories. Recent work addresses this issue by modeling dialectness as a continuous variable, notably through the Arabic Level of Dia…

Word Alignment

Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?

2025-07-17 · Xi Ai, Mahardika Krisna Ihsani, Min-Yen Kan arxiv

Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain the factuality of the model knowledge across languages, and preserve the parity of language model performance. We are thus …

Word Alignment

The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks

2025-05-15 · Benedikt Ebing, Goran Glavaš

Translation-based strategies for cross-lingual transfer XLT such as translate-train -- training on noisy target language data translated from the source language -- and translate-test -- evaluating on noisy source langua…

Cross-Lingual Transfertoken-classificationToken ClassificationTranslation+1

Large Language Models Often Say One Thing and Do Another

2025-03-10 · Ruoxi Xu, Hongyu Lin, Xianpei Han, Jia Zheng 외

As large language models (LLMs) increasingly become central to various applications and interact with diverse user populations, ensuring their reliable and consistent performance is becoming more important. This paper ex…

Word Alignment

Target word activity detector: An approach to obtain ASR word boundaries without lexicon

2024-09-20 · Sunit Sivasankaran, Eric Sun, Jinyu Li, Yan Huang 외

Obtaining word timestamp information from end-to-end (E2E) ASR models remains challenging due to the lack of explicit time alignment during training. This issue is further complicated in multilingual models. Existing met…

Word AlignmentWord Embeddings

BinaryAlign: Word Alignment as Binary Sequence Labeling

2024-07-16 · Gaetan Lopez Latouche, Marc-André Carbonneau, Ben Swanson

Real world deployments of word alignment are almost certain to cover both high and low resource languages. However, the state-of-the-art for this task recommends a different model class depending on the availability of g…

Word Alignment

Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning

2024-07-06 · Jingshen Zhang, Xinying Qiu, Teng Shen, Wenyu Wang 외

Cross-lingual word alignment plays a crucial role in various natural language processing tasks, particularly for low-resource languages. Recent study proposes a BiLSTM-based encoder-decoder model that outperforms pre-tra…

Contrastive LearningDecoderWord AlignmentWord Embeddings

Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment

2024-06-27 · Rotem Rousso, Eyal Cohen, Joseph Keshet, Eleanor Chodroff

Forced alignment (FA) plays a key role in speech research through the automatic time alignment of speech signals with corresponding text transcriptions. Despite the move towards end-to-end architectures for speech techno…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1
1–20 / 564 다음 →