Statistical Machine Translation

By Hany Hassan, Kareem Darwish. 2014

1,705 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Improving Neural Language Modeling via Adversarial Training (2019, background): “Statistical language modeling is a fundamental task in machine learning, with wide applications in various areas, including automatic speech recognition (e.g., Yu & Deng, 2016), machine translation (e.g., Koehn, 2009) and computer vision (e.g., Xu et al., 2015), to name a few.”
A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion (2015, methodology): “The solution to the problem can be approximated using standard word-level decoding techniques such as beam-search [11, 22].”
Guided Open Vocabulary Image Captioning with Constrained Beam Search (2016, methodology): “Beam search [14] is an approximate inference algorithm that is commonly used to decode output sequences from Recurrent Neural Networks (RNNs).”
An Analysis of Neural Language Modeling at Multiple Scales (2018, methodology): “Trained LMs are useful in many applications including speech recognition (Yu & Deng, 2014), machine translation (Koehn, 2009), natural language generation (Radford et al., 2017; Merity et al., 2017a), learning token embeddings, and as a general-purpose feature extractor for downstream tasks (P.…”
Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation (T) (2015, neutral): “1 is one example of the type of parallel corpus targeted in this study, in which have one-by-one correspondences between each line in the source code and pseudo-code.”
Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search (2017, methodology): “For example, in Phrase-Based Statistical MT (PB-SMT) (Koehn, 2010), beams are organized by the number of source words that are covered by the hypotheses in the beam – a hypothesis is “finished” when it has covered all source words.”
Information Extraction over Structured Data: Question Answering with Freebase (2014, methodology): “To symmetrize the alignment, common MT heuristics INTERSECTION, UNION, GROW-DIAG-FINAL, and GROW-DIAGFINAL-AND (Koehn, 2010) were separately applied and evaluated later.”
RankME: Reliable Human Ratings for Natural Language Generation (2018, neutral): “This is in line with previous research in MT (Callison-Burch et al., 2007; Koehn, 2010).”
Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation (2020, positive): “Language-aware Linear Transformation Different language pairs have different translation correspondences or word alignments (Koehn, 2010).”
Document Context Language Models (2015, background): “Statistical language models are essential components of natural language processing systems, such as machine translation (Koehn, 2009), automatic speech recognition (Jurafsky & Martin, 2000), text generation (Sordoni et al., 2015) and information retrieval (Manning et al., 2008).”
Datasheet for the Pile (2022, methodology): “EuroParl: EuroParl has been extensively used, including by [Bouma, 2009, Koehn, 2009, Heafield, 2011, Navigli and Ponzetto, 2012, Cho et al., 2014].”
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT (2016, methodology): “Figure 3 contains our complete proposal for two-pass stack decoding, a modiﬁcation of the original stack decoding algorithm described in Koehn (2010).”
A Survey of Cross-lingual Word Embedding Models (2017, methodology): “The monolingual objective is the classic LM objective of minimizing the negative log likelihood of the current word wi given its C previous context words: L = − logP (wi | wi−C+1:i−1) (25) For the cross-lingual regularization term, they first obtain an alignment matrix As→t that indicates how often ”
Evaluating the morphological competence of Machine Translation Systems (2017, background): “The previous phrase-based (PBMT) architectures were complex (Koehn, 2010) and hard to diagnose, and Neural MT (NMT) systems, which dispense with any sort of symbolic representation of the learned knowledge, are probably worse in this respect.”
Word Ordering Without Syntax (2016, methodology): “Our work differs from the beam search approach for the WORDS+BNPS case of previous work in that we maintain multiple beams, as in stack decoding for phrase-based machine translation (Koehn, 2010), allowing us to incorporate the probabilities of internal, non-boundary words in the BNPs.”