Papers with statistical machine translation
Surface Realization Shared Task 2019 (MSR19): The Team 6 Approach (D19-63)
Copied to clipboard
| Challenge: | This paper describes the approach developed by the Tilburg University team for the shallow track of the Multilingual Surface Realization Shared Task 2019 (SR'19). |
| Approach: | They propose a method for the shallow track of the Multilingual Surface Realization Shared Task 2019 using a rule-based and a statistical machine translation (SMT) model. |
| Outcome: | The proposed approach can generate texts in 11 languages, compared with the submission of the same approach for the same task in 2018 which only covered 6 languages. |
Rethinking Round-Trip Translation for Machine Translation Evaluation (2023.findings-acl)
Copied to clipboard
| Challenge: | Automatic evaluation methods for translation often require model training and the availability of parallel corpora limits their applicability to low-resource settings. |
| Approach: | They revisit the statistical machine translation technique and use it to improve translation quality. |
| Outcome: | The proposed method improves translation quality estimation models and identifies adversarial competitors in shared tasks via cross-system verification. |
Construction of an Evaluation Corpus for Grammatical Error Correction for Learners of Japanese as a Second Language (2020.lrec-1)
Copied to clipboard
| Challenge: | The Lang-8 corpus is suitable as a training dataset for machine translation-based grammatical error correction systems but it is not suitable as an evaluation dataset because corrected sentences sometimes include inappropriate sentences. |
| Approach: | They created an evaluation corpus for correcting grammatical errors made by Japanese as a second language learners using neural machine translation and statistical machine translation techniques. |
| Outcome: | The proposed corpus has less noise and its annotation scheme reflects the characteristics of the dataset, making it ideal for correcting grammatical errors in sentences written by learners of Japanese as a Second Language (JSL). |
Revisiting Negation in Neural Machine Translation (2021.tacl-1)
Copied to clipboard
| Challenge: | Negation is an important linguistic phenomenon in machine translation, as errors in translating negation may change the meaning of source sentences completely. |
| Approach: | They evaluate the translation of negation in English–German (EN–DE) and English– Chinese (EN-ZH) . they find that NMT models can distinguish negation and non-negation tokens very well and encode a lot of information about negation . |
| Outcome: | The accuracy of manual evaluation in ENDE, DEEN, ENZH, and ZHEN is 95.7%, 94.8%, 93.4%, and 91.7% respectively. |
Multi-Granularity Self-Attention for Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Existing neural machine translation models use a deep multi-head self-attention network with no explicit phrase information. |
| Approach: | They propose a neural network that combines multi-head self-attention and phrase modeling to train attention heads to attend to phrases in either n-gram or syntactic formalisms. |
| Outcome: | The proposed approach improves on English-to-German and NIST Chinese-to English translation tasks. |
Forest-Based Neural Machine Translation (P18-1)
Copied to clipboard
| Challenge: | Compared with string-to-string systems, tree-based NMT methods use more syntactic information and can incorporate prior knowledge. |
| Approach: | They propose a tree-based neural machine translation method that translates a linearized packed forest under a simple sequence-to-sequence framework. |
| Outcome: | The proposed method outperforms tree-based approaches in the BLEU score of the proposed model. |
Conversational Word Embedding for Retrieval-Based Dialog System (2020.acl-main)
Copied to clipboard
| Challenge: | Existing word embedding methods for retrieval-based dialog systems are based on co-occurrence statistics and train them based upon the same co-existence statistics. |
| Approach: | They propose a conversational word embedding method which uses the conversation pairs post, reply, and 'reply' they introduce a word alignment model from statistical machine translation and train it on word-level and sentence-level. |
| Outcome: | The proposed method improves the quality of the selected response on retrieval-based dialog systems. |
HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Existing methods to incorporate bilingual lexicons into statistical machine translation are unclear how to do so in the neural framework. |
| Approach: | They present a dataset to test methods for bilingual lexicon integration into neural machine translation using human generated alignments of words and phrases in three language pairs. |
| Outcome: | The proposed method improves on baselines and improves training to address overfitting. |
End-to-End Neural Word Alignment Outperforms GIZA++ (2020.acl-main)
Copied to clipboard
| Challenge: | Word alignment was once a core unsupervised learning task in natural language processing . but word alignment still plays an important role in interactive applications of neural machine translation, such as annotation transfer and lexicon injection. |
| Approach: | They propose to use a Transformer model to train an unsupervised word alignment model. |
| Outcome: | The proposed method outperforms GIZA++ on three data sets and is tightly integrated and does not affect translation quality. |
Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings (P18-1)
Copied to clipboard
| Challenge: | Neural machine translation uses source and target word embeddings to improve translation quality . source and targeted word embeds are at the two ends of a long information processing procedure . |
| Approach: | They propose a method to shorten the distance between source and target words in neural machine translation by bridging source and targeting word embeddings. |
| Outcome: | The proposed method shortens the distance between source and target words in neural machine translation and strengthens their association. |
Pipeline Signed Japanese Translation Focusing on a Post-positional Particle Complement and Conjugation in a Low-resource Setting (2021.findings-acl)
Copied to clipboard
| Challenge: | a pipeline translation method is proposed to take advantage of the similarities and differences between sign language and spoken language. |
| Approach: | They propose a pipeline translation method that takes advantage of similarities between spoken and spoken Japanese . they map glosses to spoken language words and train them using a monolingual Japanese corpus . |
| Outcome: | The proposed method performs robustly on the low-resource corpus and is +4.4/+4.9 points above baseline. |
Can Automatic Post-Editing Improve NMT? (2020.emnlp-main)
Copied to clipboard
| Challenge: | APE has been successful with statistical machine translation systems but has not been as successful over neural machine translation (NMT) systems. |
| Approach: | They propose to train neural APE models on a corpus of human post-edits of NMT and compile a larger corpus to test their hypothesis. |
| Outcome: | The proposed model can improve a strong in-domain NMT system, challenging the current understanding in the field. |
Building a Macro Chinese Discourse Treebank (L18-1)
Copied to clipboard
| Challenge: | Discourse structure analysis is an important research topic in natural language processing. |
| Approach: | They propose to construct a macro discourse structure framework and annotate 147 Newswire articles. |
| Outcome: | The proposed framework can lay the foundation for further analysis of macro discourse structure. |
Benchmarking Neural and Statistical Machine Translation on Low-Resource African Languages (2020.lrec-1)
Copied to clipboard
| Challenge: | a recent study has focused on languages where large amounts of resources are available. |
| Approach: | They benchmark state of the art statistical and neural machine translation systems on Somali and Swahili languages . they find that statistical machine translation and neural translation can perform similarly in low-resource scenarios . |
| Outcome: | The results show that statistical machine translation and neural machine translation perform similarly in low-resource scenarios. |
Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning (2020.lrec-1)
Copied to clipboard
| Challenge: | Subword segmentation is a standard preprocessing step in many neural approaches to natural language processing. |
| Approach: | They propose to train a unigram subword model using a recursive algorithm and lexicon pruning algorithm. |
| Outcome: | The proposed method improves on the original training algorithm and improves morphological segmentation accuracy. |
Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection (D18-1)
Copied to clipboard
| Challenge: | grammatical error correction is a labor-intensive task that requires large amounts of training data. |
| Approach: | They propose to use a human-annotated corpus of human-generated grammatical errors to generate a synthetic model. |
| Outcome: | The proposed method outperforms the current state of the art in grammatical error correction . human annotators achieve 39.39 F1 scores, suggesting the model generates mostly human-like instances . |