Manual vs Automatic Bitext Extraction (L18-1)

Copied to clipboard

Challenge: targeted, site-specific crawling results in cleaner bitexts with a higher ratio of parallel sentences . general crawlers combined with boilerplate removal tools tend to retrieve shorter texts .
Approach: They compare manual and automatic approaches to extracting bitexts from the Web . they use targeted site-specific crawling to extract cleaner bitext sentences .
Outcome: The proposed methods extract more parallel sentences from the Web than manual methods.

Similar Papers

CCMatrix: Mining Billions of High-Quality Parallel Sentences on the Web (2021.acl-long)

Copied to clipboard

Challenge: Using a curated common crawl corpus, we were able to mine 10.8 billion parallel sentences out of which only 2.9 billions are aligned with English.
Approach: They use 32 snapshots of a curated common crawl corpus totaling 71 billion unique sentences to mine 10.8 billion parallel sentences out of which only 2.9 billions are aligned with English.
Outcome: The proposed system outperforms the best single systems on the WMT’19 test set for English-German/Russian/Chinese and outperformed the best submission at the 2020 WAT workshop.
Recovering document annotations for sentence-level bitext (2024.findings-acl)

Copied to clipboard

Challenge: In machine translation, historical models were incapable of handling longer contexts, so the lack of document-level datasets was less noticeable.
Approach: They propose a document-level filtering technique that discards document- level metadata.
Outcome: The proposed method improves translation without degradation of sentence-level translation.
WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia (2021.eacl-main)

Copied to clipboard

Challenge: a new approach to extract parallel sentences from Wikipedia articles is proposed . the approach is based on multilingual sentence embeddings, but does not limit it to English .
Approach: They propose to automatically extract parallel sentences from Wikipedia articles in 96 languages . they train neural MT baseline systems on the mined data and evaluate them on the TED corpus .
Outcome: The proposed approach extracts parallel sentences from Wikipedia articles in 96 languages . the extracted sentences achieve strong BLEU scores for many language pairs .
Better Together: Modern Methods Plus Traditional Thinking in NP Alignment (2020.lrec-1)

Copied to clipboard

Challenge: a recent study shows that end-to-end systems are not structurally free.
Approach: They propose to use dictionary- and word vector-based baselines to align NPs in the bitext . they argue that alignment of NP's in MT can be improved by using old-fashioned methods .
Outcome: a new study shows that alignment of NPs in the bitext is relevant even in an end-to-end paradigm . the proposed system can be improved by bringing in old-fashioned methods, the authors argue .
Trafilatura: A Web Scraping Library and Command-Line Tool for Text Discovery and Extraction (2021.acl-demo)

Copied to clipboard

Challenge: Existing tools for text extraction and web corpus construction are not enough to extract and pre-process web data to meet scientific expectations with respect to text quality.
Approach: They propose a text discovery and extraction tool published under open-source license that allows for main text, comments and metadata extraction while also providing building blocks for web crawling tasks.
Outcome: The proposed tool performs significantly better than other open-source solutions on real-world data and in external benchmarks.
A Gold Standard for Multilingual Automatic Term Extraction from Comparable Corpora: Term Structure and Translation Equivalents (L18-1)

Copied to clipboard

Challenge: Terms are notoriously difficult to identify, both automatically and manually.
Approach: They propose a method to annotate terms manually from a comparable corpus . they show that the gold standard provides a tool for evaluation and a rich source of information .
Outcome: The proposed method provides a tool for evaluation and rich source of information about terms.
Simple and Effective Paraphrastic Similarity from Parallel Translations (P19-1)

Copied to clipboard

Challenge: Existing methods for learning paraphrastic sentence embeddings on bitext are expensive and require manual annotation.
Approach: They propose a method that trains paraphrastic sentence embeddings directly from bitext, eliminating the time-consuming step of creating paraphrase corpora.
Outcome: The proposed model outperforms and is faster than state-of-the-art models on cross-lingual tasks.
BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods to improve Neural Machine Translation (NMT) for lowresource languages are often trained on heuristically aligned or automatically mined data.
Approach: They propose to filter out imperfect translations that yield unreliable training signals for Neural Machine Translation (NMT) instead, they propose to refine mined bitexts by automatic editing .
Outcome: The proposed method improves the quality of mined bitexts for low-resource languages by up to 8 BLEU points.
BiSECT: Learning to Split and Rephrase Sentences with Bitexts (2021.emnlp-main)

Copied to clipboard

Challenge: Several past efforts have created Split and Rephrase training sets, which consist of long, complex input sentences paired with multiple shorter sentences that preserve the meaning of the input sentence.
Approach: They propose a new dataset and a model for this task by extracting 1-2 sentence alignments from bilingual parallel corpora and using machine translation to convert both sides of the corpus into the same language.
Outcome: The proposed model can perform a wider variety of split operations and improve upon previous state-of-the-art approaches in automatic and human evaluations.
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus (2021.emnlp-main)

Copied to clipboard

Challenge: Large text corpora are often introduced with minimal documentation . documenting collection process, composition, intended uses, and other are key for structured, task-specific datasets.
Approach: They propose to document a dataset created by applying filters to a single snapshot of Common Crawl.
Outcome: The proposed dataset shows that blocklist filtering removes text from minority individuals and patents.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations