arXiv subjects

Gholamreza Haffari

Publications and source records attributed to Gholamreza Haffari.

173 records · Page 10Linked to original sources

arXiv2017

Incorporating Syntactic Uncertainty in Neural Machine Translation with Forest-to-Sequence Model

Incorporating syntactic information in Neural Machine Translation models is a method to compensate their requirement for a large amount of parallel training text, especially for low-resource language pairs. Previous works on using syntactic information provided by (inevitably error-prone) parsers has been promising. In this paper, we propose a forest-to-sequence Attentional Neural Machine Translation model to make use of exponentially many parse trees of the source sentence to compensate for the parser errors. Our method represents the collection of parse trees as a packed forest, and learns a neural attentional transduction model from the forest to the target sentence. Experiments on English to German, Chinese and Persian translation show the superiority of our method over the tree-to-sequence and vanilla sequence-to-sequence neural translation models.

cs.CL↗

arXiv2017

Towards Decoding as Continuous Optimization in Neural Machine Translation

We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We convert decoding - basically a discrete optimization problem - into a continuous optimization problem. The resulting constrained continuous optimisation problem is then tackled using gradient-based methods. Our powerful decoding framework enables decoding intractable models such as the intersection of left-to-right and right-to-left (bidirectional) as well as source-to-target and target-to-source (bilingual) NMT models. Our empirical results show that our decoding framework is effective, and leads to substantial improvements in translations generated from the intersected models where the typical greedy or beam search is not feasible. We also compare our framework against reranking, and analyse its advantages and disadvantages.

cs.CL↗

arXiv2016

Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees

Efficient methods for storing and querying are critical for scaling high-order n-gram language models to large corpora. We propose a language model based on compressed suffix trees, a representation that is highly compact and can be easily held in memory, while supporting queries needed in computing language model probabilities on-the-fly. We present several optimisations which improve query runtimes up to 2500x, despite only incurring a modest increase in construction time and memory usage. For large corpora and high Markov orders, our method is highly competitive with the state-of-the-art KenLM package. It imposes much lower memory requirements, often by orders of magnitude, and has runtimes that are either similar (for training) or comparable (for querying).

cs.CL↗

arXiv2016

Word Representation Models for Morphologically Rich Languages in Neural Machine Translation

Dealing with the complex word forms in morphologically rich languages is an open problem in language processing, and is particularly important in translation. In contrast to most modern neural systems of translation, which discard the identity for rare words, in this paper we propose several architectures for learning word representations from character and morpheme level word decompositions. We incorporate these representations in a novel machine translation model which jointly learns word alignments and translations via a hard attention mechanism. Evaluating on translating from several morphologically rich languages into English, we show consistent improvements over strong baseline methods, of between 1 and 1.5 BLEU points.

cs.NE↗

arXiv2016

A Latent Variable Recurrent Neural Network for Discourse Relation Language Models

This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences. A recurrent neural network generates individual words, thus reaping the benefits of discriminatively-trained vector representations. The discourse relations are represented with a latent variable, which can be predicted or marginalized, depending on the task. The resulting model can therefore employ a training objective that includes not only discourse relation classification, but also word prediction. As a result, it outperforms state-of-the-art alternatives for two tasks: implicit discourse relation classification in the Penn Discourse Treebank, and dialog act classification in the Switchboard corpus. Furthermore, by marginalizing over latent discourse relations at test time, we obtain a discourse informed language model, which improves over a strong LSTM baseline.

cs.CL↗

arXiv2016

Prepositional Attachment Disambiguation Using Bilingual Parsing and Alignments

In this paper, we attempt to solve the problem of Prepositional Phrase (PP) attachments in English. The motivation for the work comes from NLP applications like Machine Translation, for which, getting the correct attachment of prepositions is very crucial. The idea is to correct the PP-attachments for a sentence with the help of alignments from parallel data in another language. The novelty of our work lies in the formulation of the problem into a dual decomposition based algorithm that enforces agreement between the parse trees from two languages as a constraint. Experiments were performed on the English-Hindi language pair and the performance improved by 10% over the baseline, where the baseline is the attachment predicted by the MSTParser model trained for English.

cs.CL↗

arXiv2016

Incorporating Structural Alignment Biases into an Attentional Neural Translation Model

Neural encoder-decoder models of machine translation have achieved impressive results, rivalling traditional translation models. However their modelling formulation is overly simplistic, and omits several key inductive biases built into traditional models. In this paper we extend the attentional neural translation model to include structural biases from word based alignment models, including positional bias, Markov conditioning, fertility and agreement over translation directions. We show improvements over a baseline attentional model and standard phrase-based model over several language pairs, evaluating on difficult languages in a low resource setting.

cs.CL↗

arXiv2015

Novel Bernstein-like Concentration Inequalities for the Missing Mass

We are concerned with obtaining novel concentration inequalities for the missing mass, i.e. the total probability mass of the outcomes not observed in the sample. We not only derive - for the first time - distribution-free Bernstein-like deviation bounds with sublinear exponents in deviation size for missing mass, but also improve the results of McAllester and Ortiz (2003) andBerend and Kontorovich (2013, 2012) for small deviations which is the most interesting case in learning theory. It is known that the majority of standard inequalities cannot be directly used to analyze heterogeneous sums i.e. sums whose terms have large difference in magnitude. Our generic and intuitive approach shows that the heterogeneity issue introduced in McAllester and Ortiz (2003) is resolvable at least in the case of missing mass via regulating the terms using our novel thresholding technique.

stat.ML↗

arXiv2015

Structured Prediction of Sequences and Trees using Infinite Contexts

Linguistic structures exhibit a rich array of global phenomena, however commonly used Markov models are unable to adequately describe these phenomena due to their strong locality assumptions. We propose a novel hierarchical model for structured prediction over sequences and trees which exploits global context by conditioning each generation decision on an unbounded context of prior decisions. This builds on the success of Markov models but without imposing a fixed bound in order to better represent global phenomena. To facilitate learning of this large and unbounded model, we use a hierarchical Pitman-Yor process prior which provides a recursive form of smoothing. We propose prediction algorithms based on A* and Markov Chain Monte Carlo sampling. Empirical results demonstrate the potential of our model compared to baseline finite-context Markov models on part-of-speech tagging and syntactic parsing.

cs.LG↗

arXiv2015

HetFHMM: A novel approach to infer tumor heterogeneity using factorial Hidden Markov model

Cancer arises from successive rounds of mutations which generate tumor cells with different genomic variation i.e. clones. For drug responsiveness and therapeutics, it is necessary to identify the clones in tumor sample accurately. Many methods are developed to infer tumor heterogeneity by either computing cellular prevalence and tumor phylogeny or predicting genotype of mutations. All methods suffer some problems e.g. inaccurate computation of clonal frequencies, discarding clone specific genotypes etc. In the paper, we propose a method, called- HetFHMM to infer tumor heterogeneity by predicting clone specific genotypes and cellular prevalence. To infer clone specific genotype, we consider the presence of multiple mutations at any genomic location. We also tested our model on different simulated data. The results shows that HetFHMM outperforms recent methods which infer tumor heterogeneity. Therefore, HetFHMM is a novel approach in tumor heterogeneity research area.

q-bio.GN↗

arXiv2013

An Efficient Algorithm for Upper Bound on the Partition Function of Nucleic Acids

It has been shown that minimum free energy structure for RNAs and RNA-RNA interaction is often incorrect due to inaccuracies in the energy parameters and inherent limitations of the energy model. In contrast, ensemble based quantities such as melting temperature and equilibrium concentrations can be more reliably predicted. Even structure prediction by sampling from the ensemble and clustering those structures by Sfold [7] has proven to be more reliable than minimum free energy structure prediction. The main obstacle for ensemble based approaches is the computational complexity of the partition function and base pairing probabilities. For instance, the space complexity of the partition function for RNA-RNA interaction is $O(n^4)$ and the time complexity is $O(n^6)$ which are prohibitively large [4,12]. Our goal in this paper is to give a fast algorithm, based on sparse folding, to calculate an upper bound on the partition function. Our work is based on the recent algorithm of Hazan and Jaakkola [10]. The space complexity of our algorithm is the same as that of sparse folding algorithms, and the time complexity of our algorithm is $O(MFE(n)\ell)$ for single RNA and $O(MFE(m, n)\ell)$ for RNA-RNA interaction in practice, in which $MFE$ is the running time of sparse folding and $\ell \leq n$ ($\ell \leq n + m$) is a sequence dependent parameter.

q-bio.BM↗