A Smorgasbord of Features for Statistical Machine Translation

By Franz Joseph Och, Daniel Gildea, Sanjeev Khudanpur, Anoop Sarkar, Kenji Yamada, Alexander M. Fraser, Shankar Kumar, Libin Shen, David A. Smith, Katherine Eng and 3 more. 2004

325 citations recorded by the source corpus.

Subfields: Natural Language Processing

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

Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2021, background): “[92], Zhang and Nivre [150]), where NLP researchers or engineers used their domain knowledge to deine and extract salient features from raw data and provide models with the appropriate inductive bias to”
11,001 New Features for Statistical Machine Translation (2009, background): “The work of Och et al (2004) is perhaps the best-known study of new features and their impact on translation quality.”
Dependency Treelet Translation: Syntactically Informed Phrasal SMT (2005, background): “A recent workshop investigated employing a variety of syntactically motivated features in this approach, but found very little positive impact ([25]).”
Clause Restructuring for Statistical Machine Translation (2005, methodology): “Reranking methods have also been proposed as a method for using syntactic information (Koehn and Knight, 2003; Och et al., 2004; Shen et al., 2004).”
Re-evaluating the Role of Bleu in Machine Translation Research (2006, unknown): “…in translation quality with the integration of word sense disambiguation (Carpuat and Wu, 2005), or work which attempted to integrate syntactic information but which failed to improve Bleu (Char-niak et al., 2003; Och et al., 2004) may deserve a second look with a more targeted manual evaluation.”
BRIO: Bringing Order to Abstractive Summarization (2022, background): “Discriminative Reranking Discriminative reranking has been widely studied for conditional generation tasks (Shen et al., 2004; Och et al., 2004; Wan et al., 2015; Mizumoto and Matsumoto, 2016).”
ILLC-UvA Adaptation System (Scorpio) at WMT’16 IT-DOMAIN Task (2016, methodology): “Following (Cuong and Sima’an, 2015), we ﬁnd it useful to exploit the word-level feature derived from IBM model 1 score (Och et al., 2004).”
A Review on Language Models as Knowledge Bases (2022, methodology): “It has moved the ﬁeld from feature engineering (Och et al., 2004; Zhang and Nivre, 2011) and architecture engineering (Chung et al., 2014; Kim, 2014; Bahdanau et al., 2015; Vaswani et al., 2017) to the pre-train and ﬁne-tune paradigm (Radford and Narasimhan, 2018; Dong et al., 2019; Lewis et al.,…”
Factored Translation Models (2007, background): “Och et al. (2004) report minor improvements with linguistic features on a Chinese-English task, Koehn and Knight (2003) show some success in re-ranking noun phrases for German-English.”
Continuous Space Language Models for Statistical Machine Translation (2006, background): “Many different feature functions were explored in (Och et al., 2004).”
Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation (2015, background): “…modelling, such as lexicalized PCFGs (Charniak, 2001; Collins, 2003; Charniak et al., 2003), or structured language models (Chelba and Jelinek, 2000); previous efforts to include them in the translation process failed to improve translation performance (Och et al., 2004; Post and Gildea, 2008).”
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.”
An End-to-End Discriminative Approach to Machine Translation (2006, methodology): “Unlike minimum error rate training (Och, 2003), our system is able to exploit large numbers of specific features in the same manner as static reranking systems (Shen et al., 2004; Och et al., 2004).”
NRC Russian-English Machine Translation System for WMT 2016 (2016, methodology): “We rescored 1000-best lists output from the de-coder using a rescoring model (Och et al., 2004; Foster et al., 2009) consisting of 82 features: 27 decoder features and 55 additional rescoring features.”
A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation (2007, methodology): “A typical reranking approach to SMT (Och et al., 2004) uses a 1000–best list.”
A Simple and Effective Hierarchical Phrase Reordering Model (2008, background): “Recent efforts (Tillman, 2004; Och et al., 2004; Koehn et al., 2007) have directly addressed this issue by introducing lexicalized reordering models into phrase-based systems, which condition reordering probabilities on the words of each phrase pair.”