Related papers: Reranking Machine Translation Hypotheses with Stru…
In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source…
Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between…
In language modeling, it is difficult to incorporate entity relationships from a knowledge-base. One solution is to use a reranker trained with global features, in which global features are derived from n-best lists. However, training such…
This year, the Nara Institute of Science and Technology (NAIST)'s submission to the 2015 Workshop on Asian Translation was based on syntax-based statistical machine translation, with the addition of a reranking component using neural…
A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…
The thesis presents an attempt at using the syntactic structure in natural language for improved language models for speech recognition. The structured language model merges techniques in automatic parsing and language modeling using an…
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…
More recently, Bidirectional Encoder Representations from Transformers (BERT) was proposed and has achieved impressive success on many natural language processing (NLP) tasks such as question answering and language understanding, due mainly…
Reranking methods in machine translation aim to close the gap between common evaluation metrics (e.g. BLEU) and maximum likelihood learning and decoding algorithms. Prior works address this challenge by training models to rerank beam search…
Beam search optimization resolves many issues in neural machine translation. However, this method lacks principled stopping criteria and does not learn how to stop during training, and the model naturally prefers the longer hypotheses…
Language model is one of the most important modules in statistical machine translation and currently the word-based language model dominants this community. However, many translation models (e.g. phrase-based models) generate the target…
I train models for the task of neural machine translation for English-Hungarian and Hungarian-English, using the Hunglish2 corpus. The main contribution of this work is evaluating different data augmentation methods during the training of…
Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid…
The discrepancy between maximum likelihood estimation (MLE) and task measures such as BLEU score has been studied before for autoregressive neural machine translation (NMT) and resulted in alternative training algorithms (Ranzato et al.,…
In this paper, we propose two new features for estimating phrase-based machine translation parameters from mainly monolingual data. Our method is based on two recently introduced neural network vector representation models for words and…
The interest in statistical machine translation systems increases currently due to political and social events in the world. A proposed Statistical Machine Translation (SMT) based model that can be used to translate a sentence from the…
In this paper, we introduce a hybrid search for attention-based neural machine translation (NMT). A target phrase learned with statistical MT models extends a hypothesis in the NMT beam search when the attention of the NMT model focuses on…
In this paper, we discuss different methods which use meta information and richer context that may accompany source language input to improve machine translation quality. We focus on category information of input text as meta information,…
Recent Large Language Models (LLMs) have significantly advanced natural language processing and automated decision-making. However, these models still encounter difficulties when performing complex reasoning tasks involving logical…
Incorporating stronger syntactic biases into neural language models (LMs) is a long-standing goal, but research in this area often focuses on modeling English text, where constituent treebanks are readily available. Extending constituent…