We propose minimum risk training for end-to-end neural machine translation. Unlike
conventional maximum likelihood estimation, minimum risk training is capable of optimizing …

Despite the progress in machine translation quality estimation and evaluation in the last
years, decoding in neural machine translation (NMT) is mostly oblivious to this and centers …

While most neural machine translation (NMT) systems are still trained using maximum
likelihood estimation, recent work has demonstrated that optimizing systems to directly …

There has been much recent work on training neural attention models at the sequence-level
using either reinforcement learning-style methods or by optimizing the beam. In this paper …

Our goal is to learn a semantic parser that maps natural language utterances into
executable programs when only indirect supervision is available: examples are labeled with …

Abstract In Neural Machine Translation, it is typically assumed that the sentence with the
highest estimated probability should also be the translation with the highest quality as …

Recently, neural models have been proposed for headline generation by learning to map
documents to headlines with recurrent neural network. In this work, we give a detailed …

There has been a proliferation of recent work on SMT tuning algorithms capable of handling
larger feature sets than the traditional MERT approach. We analyze a number of these …

Training learnable metrics using modern language models has recently emerged as a
promising method for the automatic evaluation of machine translation. However, existing …

Dynamic programming (DP) solves a variety of structured combinatorial problems by
iteratively breaking them down into smaller subproblems. In spite of their versatility, many …