• Publications
  • Influence
Bleu: a Method for Automatic Evaluation of Machine Translation
TLDR
This work proposes a method of automatic machine translation evaluation that is quick, inexpensive, and language-independent, that correlates highly with human evaluation, and that has little marginal cost per run. Expand
Language Model Based Arabic Word Segmentation
We approximate Arabic's rich morphology by a model that a word consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). Our methodExpand
Why Inverse Document Frequency?
TLDR
It is shown that the IDF is the optimal weight associated with a word-feature in an information retrieval setting where the authors treat each document as the query that retrieves itself, which means IDF is optimal for document self-retrieval. Expand
Bidding for Representative Allocations for Display Advertising
TLDR
This work characterize what allocations can be implemented with randomized bidding, namely those where the desired share obtained at each price is a non-increasing function of price. Expand
Distortion Models for Statistical Machine Translation
TLDR
A new distortion model is proposed that can be used with existing phrase-based SMT decoders to address n-gram language model limitations and a novel metric to measure word order similarity (or difference) between any pair of languages based on word alignments is proposed. Expand
DARPA communicator dialog travel planning systems: the june 2000 data collection
TLDR
This paper describes results of an experiment with 9 different DARPA Communicator Systems who participated in the June 2000 data collection and describes the experimental design, the approach to data collection, the metrics collected, and results comparing the systems. Expand
Maximum likelihood and discriminative training of direct translation models
TLDR
This work considers translating natural language sentences into a formal language using direct translation models built automatically from training data, and reports results in the air travel information system domain and compares the two methods of training. Expand
Corpus-based comprehensive and diagnostic MT evaluation: initial Arabic, Chinese, French, and Spanish results
TLDR
Two metrics for automatic evaluation of machine translation quality, BLEU and NEE, are compared to human judgment of quality of translation of Arabic, Chinese, French, and Spanish documents into English. Expand
The IBM conversational telephony system for financial applications
TLDR
This system uses several components including robust large vocabulary continuous speech recognition, natural language understanding, dialog management, and text-to-speech synthesis technologies to create a telephonebased conversational system in the domain of mutual fund transactions. Expand
...
1
2
3
...