Word Alignment

84 papers with code • 7 benchmarks • 4 datasets

Word Alignment is the task of finding the correspondence between source and target words in a pair of sentences that are translations of each other.

Source: Neural Network-based Word Alignment through Score Aggregation

Cross-lingual Contextualized Phrase Retrieval

ghrua/ccpr_release 25 Mar 2024

In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information.

1
25 Mar 2024

Multilingual Coreference Resolution in Low-resource South Asian Languages

ritwikmishra/transmucores 21 Feb 2024

We introduce a Translated dataset for Multilingual Coreference Resolution (TransMuCoRes) in 31 South Asian languages using off-the-shelf tools for translation and word-alignment.

0
21 Feb 2024

Constrained Decoding for Cross-lingual Label Projection

duonglm38/codec 5 Feb 2024

Therefore, it is common to exploit translation and label projection to further improve the performance by (1) translating training data that is available in a high-resource language (e. g., English) together with the gold labels into low-resource languages, and/or (2) translating test data in low-resource languages to a high-source language to run inference on, then projecting the predicted span-level labels back onto the original test data.

1
05 Feb 2024

Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models

pangjh3/llm4mt 16 Jan 2024

This study revisits these challenges, offering insights into their ongoing relevance in the context of advanced Large Language Models (LLMs): domain mismatch, amount of parallel data, rare word prediction, translation of long sentences, attention model as word alignment, and sub-optimal beam search.

9
16 Jan 2024

Aligning and Prompting Everything All at Once for Universal Visual Perception

shenyunhang/ape 4 Dec 2023

However, predominant paradigms, driven by casting instance-level tasks as an object-word alignment, bring heavy cross-modality interaction, which is not effective in prompting object detection and visual grounding.

383
04 Dec 2023

CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

cvmi-lab/codet NeurIPS 2023

CoDet then leverages visual similarities to discover the co-occurring objects and align them with the shared concept.

79
25 Oct 2023

On Bilingual Lexicon Induction with Large Language Models

cambridgeltl/prompt4bli 21 Oct 2023

Bilingual Lexicon Induction (BLI) is a core task in multilingual NLP that still, to a large extent, relies on calculating cross-lingual word representations.

6
21 Oct 2023

Improving Translation Faithfulness of Large Language Models via Augmenting Instructions

pppa2019/swie_overmiss_llm4mt 24 Aug 2023

The experimental results demonstrate significant improvements in translation performance with SWIE based on BLOOMZ-3b, particularly in zero-shot and long text translations due to reduced instruction forgetting risk.

11
24 Aug 2023

Towards Arabic Multimodal Dataset for Sentiment Analysis

belgats/arabic-multimodal-dataset 10 Jun 2023

In contrast, Arabic DL-based multimodal sentiment analysis (MSA) is still in its infantile stage due, mainly, to the lack of standard datasets.

4
10 Jun 2023

WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction

qiyuw/wspalign 9 Jun 2023

Most existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness.

4
09 Jun 2023