Browse State-of-the-Art › Word Alignment
Word Alignment
92 papers with code · 7 benchmarks · 4 datasets archive 2025-07-28
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
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
7 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): fr-en (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| en-es (2 rows) | Barycenter Alignment | Unsupervised Multilingual Alignment using Wasserstein Barycenter | code | — | Compare |
| en-fr (2 rows) | Barycenter Alignment | Unsupervised Multilingual Alignment using Wasserstein Barycenter | code | — | Compare |
| es-en (2 rows) | Barycenter Alignment | Unsupervised Multilingual Alignment using Wasserstein Barycenter | code | — | Compare |
| fr-en (2 rows) | Barycenter Alignment | Unsupervised Multilingual Alignment using Wasserstein Barycenter | code | — | Compare |
| en-it (1 row) | Barycenter Alignment | Unsupervised Multilingual Alignment using Wasserstein Barycenter | code | — | Compare |
| MUSE en-de (1 row) | Barycenter Alignment | Unsupervised Multilingual Alignment using Wasserstein Barycenter | code | — | Compare |
| MUSE en-pt (1 row) | Barycenter Alignment | Unsupervised Multilingual Alignment using Wasserstein Barycenter | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
4 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 551 · with a code link: 92 · where Syntology ran a sample: 23 (20 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (23 of 551 tagged: 20 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 6: papers 1 to 100 of 551, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
11 Oct 2017 20 repositories listed Syntology community repositories only · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 8 pointer-only (licence)We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine…
-
30 Oct 2014 5 repositories listedOur experiments on the WMT14 English to French translation task show that this method provides a substantial improvement of up to 2.
-
30 Sep 2021 4 repositories listed Syntology official (archive's flag): 4 ran · 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 12 harvested samples) · 6 pointer-only (licence)Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel.
-
14 Apr 2021 3 repositories listed Syntology official: harvested, nothing ran · 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants.
-
20 Jan 2021 3 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)In addition, we demonstrate that we are able to train multilingual word aligners that can obtain robust performance on different language pairs.
-
29 Apr 2020 3 repositories listedWe introduce MultiATIS++, a new multilingual NLU corpus that extends the Multilingual ATIS corpus to nine languages across four language families, and evaluate our method using the corpus.
-
18 Apr 2020 3 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples)We find that alignments created from embeddings are superior for four and comparable for two language pairs compared to those produced by traditional statistical aligners, even with abundant parallel data; e. g.…
-
4 Dec 2023 2 repositories listed Syntology official (archive's flag): 4 ran · 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 14 harvested samples)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.
-
9 Jun 2023 2 repositories listedMost existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness.
-
19 May 2023 2 repositories listedAttention is the core mechanism of today's most used architectures for natural language processing and has been analyzed from many perspectives, including its effectiveness for machine translation-related tasks.
-
28 Nov 2022 2 repositories listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples)Translating training data into many languages has emerged as a practical solution for improving cross-lingual transfer.
-
15 Mar 2022 2 repositories listedRecent dominant methods for video-language pre-training (VLP) learn transferable representations from the raw pixels in an end-to-end manner to achieve advanced performance on downstream video-language retrieval.
-
30 Jul 2021 2 repositories listedThe quantitative evaluation demonstrates that our backbone translation models achieve state-of-the-art translation performance and our quality estimation well correlates with both BLEU and human judgment.
-
15 May 2025 1 repository listedIn this work, we revisit WAs for label projection, systematically investigating the effects of low-level design decisions on token-level XLT: (i) the algorithm for projecting labels between (multi-)token spans, (ii)…
-
10 Mar 2025 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)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.
-
16 Jul 2024 1 repository listedReal world deployments of word alignment are almost certain to cover both high and low resource languages.
-
5 Apr 2024 1 repository listedThis paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations.
-
25 Mar 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 11 harvested samples) · 11 pointer-only (licence)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.
-
21 Feb 2024 1 repository listedWe introduce a Translated dataset for Multilingual Coreference Resolution (TransMuCoRes) in 31 South Asian languages using off-the-shelf tools for translation and word-alignment.
-
15 Feb 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples)Recent work has shown that, while large language models (LLMs) demonstrate strong word translation or bilingual lexicon induction (BLI) capabilities in few-shot setups, they still cannot match the performance of…
-
5 Feb 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)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…
-
Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models16 Jan 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 8 pointer-only (licence)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…
-
1 Jan 2024 1 repository listedWe propose a novel Linguistic-Aware Patch Slimming (LAPS) framework for fine-grained alignment which explicitly identifies redundant visual patches with language supervision and rectifies their semantic and spatial…
-
25 Oct 2023 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 8 pointer-only (licence)CoDet then leverages visual similarities to discover the co-occurring objects and align them with the shared concept.
-
21 Oct 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)Bilingual Lexicon Induction (BLI) is a core task in multilingual NLP that still, to a large extent, relies on calculating cross-lingual word representations.
-
24 Aug 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 9 pointer-only (licence)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.
-
10 Jun 2023 1 repository listedIn contrast, Arabic DL-based multimodal sentiment analysis (MSA) is still in its infantile stage due, mainly, to the lack of standard datasets.
-
7 Jun 2023 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 14 harvested samples)Monolingual word alignment is crucial to model semantic interactions between sentences.
-
26 May 2023 1 repository listedOn the task of Machine Translation (MT), multiple works have investigated few-shot prompting mechanisms to elicit better translations from LLMs.
-
22 May 2023 1 repository listedAutomatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications.
-
19 Apr 2023 1 repository listed
-
Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models15 Feb 2023 1 repository listed
-
28 Jan 2023 1 repository listed
-
23 Jan 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
8 Nov 2022 1 repository listed
-
30 Oct 2022 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
12 Oct 2022 1 repository listed
-
9 Oct 2022 1 repository listed
-
21 Jul 2022 1 repository listed
-
29 Jun 2022 1 repository listed
-
23 May 2022 1 repository listed
-
9 May 2022 1 repository listed
-
15 Mar 2022 1 repository listed Syntology official (archive's flag): 2 ran · 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 4 pointer-only (licence)
-
23 Nov 2021 1 repository listed
-
16 Nov 2021 1 repository listed
-
13 Sep 2021 1 repository listed
-
13 Sep 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
11 Jun 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
4 Jun 2021 1 repository listed Syntology official: harvested for another paper · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
4 Jun 2021 1 repository listed
-
1 Jun 2021 1 repository listed
-
1 May 2021 1 repository listed
-
18 Apr 2021 1 repository listed
-
15 Apr 2021 1 repository listed
-
31 Mar 2021 1 repository listed
-
13 Dec 2020 1 repository listed
-
27 Oct 2020 1 repository listed
-
12 Oct 2020 1 repository listed
-
30 Apr 2020 1 repository listed
-
30 Apr 2020 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)
-
28 Apr 2020 1 repository listed
-
21 Apr 2020 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
9 Apr 2020 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples)
-
28 Jan 2020 1 repository listed
-
8 Nov 2019 1 repository listed
-
4 Sep 2019 1 repository listed
-
1 Aug 2019 1 repository listed
-
24 Jul 2019 1 repository listed
-
1 Jul 2019 1 repository listed
-
1 Jul 2019 1 repository listed
-
25 Jun 2019 1 repository listed
-
24 Apr 2019 1 repository listed
-
31 Jan 2019 1 repository listed
-
1 Nov 2018 1 repository listed
-
1 Oct 2018 1 repository listed
-
3 Sep 2018 1 repository listed
-
29 Aug 2018 1 repository listed
-
1 May 2018 1 repository listed
-
1 May 2018 1 repository listed
-
1 May 2018 1 repository listed
-
1 Nov 2017 1 repository listed
-
20 Jul 2017 1 repository listed
-
A Web-Based Interactive Tool for Creating, Inspecting, Editing, and Publishing Etymological Datasets1 Apr 2017 1 repository listed
-
6 Jul 2016 1 repository listed
-
1 Jun 2016 1 repository listed
-
15 Dec 2015 1 repository listed
-
5 Nov 2014 1 repository listed
-
1 Jun 2014 1 repository listed
-
20 Dec 2013 1 repository listed
-
1 Jun 2013 1 repository listed
-
Target word activity detector: An approach to obtain ASR word boundaries without lexicon20 Sep 2024 0 repositories listed
-
Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning6 Jul 2024 0 repositories listed
-
Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment27 Jun 2024 0 repositories listed
-
Learning Language Structures through Grounding14 Jun 2024 0 repositories listed
-
Word Alignment as Preference for Machine Translation15 May 2024 0 repositories listed
-
Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment3 Apr 2024 0 repositories listed
-
DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment27 Mar 2024 0 repositories listed
-
Exploring Region-Word Alignment in Built-in Detector for Open-Vocabulary Object Detection1 Jan 2024 0 repositories listed
Syntology lines on 25 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections