Discriminative Reranking for Machine Translation

By Libin Shen, Anoop Sarkar, Franz Joseph Och. 2004

256 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Residual Energy-Based Models for Text Generation (2020, methodology): “Our approach appears similar to discriminative reranking approaches used in the parsing and machine translation community (Shen et al., 2004).”
Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering (2017, methodology): “Re-ranking has been commonly used in NLP problems, such as in parsing and translation, in order to make use of high-order or global features that are too expensive for decoding algorithms (Collins & Koo, 2005; Shen et al., 2004; Huang, 2008; Dyer et al., 2016).”
Dynamic Entity Representations in Neural Language Models (2017, methodology): “This task is analogous to the reranking approach used in machine translation (Shen et al., 2004).”
Real or Fake? Learning to Discriminate Machine from Human Generated Text (2019, background): “ting” (Freund & Schapire, 1997). Using a separately trained scoring function to evaluate and rank candidate outputs has a long history which dates back to work on parsing and machine translation (Shen et al., 2004). In that work however, the goal was to improve a weak generator by employing a li”
Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models (2020, background): “Discriminative re-ranking was ﬁrst introduced by Shen et al. (2004) for improving the performance of machine translation (MT).”
Batch Tuning Strategies for Statistical Machine Translation (2012, background): “Pairwise ranking (Shen et al., 2004; Hopkins and May, 2011) recasts tuning as classiﬁcation, and can be very easy to implement, as it ﬁts nicely into the established MERT infrastructure.”
Trading Off Diversity and Quality in Natural Language Generation (2020, background): “The concept of oversampling generations and then ranking them has been popular since the days of statistical machine translation (Shen et al., 2004) but has also been used more recently in other domains (Li et al., 2016; Ippolito et al., 2019b; Kriz et al., 2019).”
LEVER: Learning to Verify Language-to-Code Generation with Execution (2023, methodology): “The idea of discriminative reranking (Shen et al., 2004; Collins & Koo, 2005) is to learn a scoring function R ( x, ˆ y ) that measures how likely ˆ y is the best output for input x .”
Multiple Choice Learning: Learning to Produce Multiple Structured Outputs (2012, background): “In Natural Language Processing, this is the case for sentence parsing [8] and machine translation [26], where an initial system produces a list of M -Best hypotheses [12, 24] (also called k-best lists in the NLP literature), which are then re-ranked.”
Forest Reranking: Discriminative Parsing with Non-Local Features (2008, methodology): “Discriminative reranking has become a popular technique for many NLP problems, in particular, parsing (Collins, 2000) and machine translation (Shen et al., 2005).”
An End-to-End Discriminative Approach to Machine Translation (2006, methodology): “The second approach is to use reranking, in which a baseline classiﬁer generates an n -best list of candidate translations, and a separate discriminative classiﬁer chooses amongst them (Shen et al., 2004; Och et al., 2004).”
A Systematic Exploration of Diversity in Machine Translation (2013, methodology): “gree of success (Och et al., 2004; Shen et al., 2004; Hildebrand and Vogel, 2008); some have attributed its mixed results to a lack of diversity in the M -best lists traditionally used.”
RefSum: Refactoring Neural Summarization (2021, methodology): “…used across different NLP tasks, such as constituency parsing (Collins and Koo, 2005; Huang, 2008), dependency parsing (Zhou et al., 2016; Do and Rehbein, 2020), semantic parsing (Ge and Mooney, 2006; Yin and Neubig, 2019), machine translation (Shen et al., 2004; Mizumoto and Matsumoto, 2016).”
Residual Energy-Based Models for Text (2021, methodology): “Our approach appears similar to discriminative reranking approaches used in the parsing and machine translation community (Shen et al., 2004; Naskar et al., 2020).”
Better k-best Parsing (2005, background): “A typical example is discriminative reranking on k -best lists from a generative module, such as (Collins, 2000) for parsing and (Shen et al. , 2004) for translation, where the reranking model has nonlocal features that cannot be computed during parsing proper.”
Clause Restructuring for Statistical Machine Translation (2005, methodology): “(Och et al., 2004; Shen et al., 2004) describe the use of syntactic features in reranking the output of a full translation system, but the syntactic features give very small gains: for example the majority of the gain in performance in the experiments in (Och et al., 2004) was due to the addition…”
Dependency Treelet Translation: Syntactically Informed Phrasal SMT (2005, methodology): “Our first attempt at selecting lambdas was to use Perceptron-based discriminative reranking [33], due to its simple algorithmic structure and fast training speed.”
Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity (2020, background): “, 2019), and in other domains including machine translation (Shen et al., 2004), dialogue generation (Wen et al.”