Experiments and Prospects of Example-Based Machine Translation
By Eiichiro Sumita, H. Iida. 1991
EBMT (Example-Based Machine Translation) is proposed. EBMT retrieves similar examples (pairs of source phrases, sentences, or texts and their translations) from a database of examples, adapting the examples to translate a new input. EBMT has the following features: (1) It is easily upgraded simply by inputting appropriate examples to the database; (2) It assigns a reliability factor to the translation result; (3) It is accelerated effectively by both indexing and parallel computing; (4) It is robust because of best-match reasoning; and (5) It well utilizes translator expertise. A prototype system has been implemented to deal with a difficult translation problem for conventional Rule-Based Machine Translation (RBMT), i.e., translating Japanese noun phrases of the form "N1 no N2" into English. The system has achieved about a 78% success rate on average. This paper explains the basic idea of EBMT, illustrates the experiment in detail, explains the broad applicability of EBMT to several difficult translation problems for RBMT and discusses the advantages of integrating EBMT with RBMT.
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
- Percy Liang
- Panupong Pasupat
- Kelvin Guu
- Jianfeng Gao
- Tatsunori B. Hashimoto
- Yizhe Zhang
- Lawrence Carin
- Weizhu Chen
Citations in the corpus
- A Retrieve-and-Edit Framework for Predicting Structured Outputs (2018, methodology): “The use of retrieval in text generation dates back to early example-based machine translation systems that retrieved and adapted phrases from a translation database [33].”
- What Makes Good In-Context Examples for GPT-3? (2021, background): “There is a long history of applying information retrieval in text generation (Sumita and Hitoshi, 1991).”
- Controllable Semantic Parsing via Retrieval Augmentation (2021, methodology): “Some utilize alignments between the retrieved examples and the input (Sumita and Iida, 1991; Gu et al., 2018b; Lu et al., 2019).”
- Survey of the State of the Art in Human Language Technology (2010, background): “At its simplest, this question involves selecting the most appropriate single word for a given unit of input. However, as soon as the semantic model approaches a realistic size, and as soon as the lexicon is large enough to permit alternative locutions, the problem becomes very complex. In some situ”