A comparative study of neural machine translation models for Turkish language

Machine translation (MT) is an important challenge in the fields of Computational Linguistics. In this study, we conducted neural machine translation (NMT) experiments on two different architectures. First, Sequence to Sequence (Seq2Seq) architecture along with a variation that utilizes attention mechanism is performed on translation task. Second, an architecture that is fully based on the self-attention mechanism, namely Transformer, is employed to perform a comprehensive comparison. Besides, the contribution of employing Byte Pair Encoding (BPE) and Gumbel Softmax distributions are examined for both architectures. The experiments are conducted on two different datasets: TED Talks that is one of the popular benchmark datasets for NMT especially among morphologically rich languages like Turkish and WMT18 News dataset that is provided by The Third Conference on Machine Translation (WMT) for shared tasks on various aspects of machine translation. The evaluation of Turkish-to-English translations’ results demonstrate that the Transformer model with combination of BPE and Gumbel Softmax achieved 22.4 BLEU score on TED Talks and 38.7 BLUE score on WMT18 News dataset. The empirical results support that using Gumbel Softmax distribution improves the quality of translations for both architectures.

Analyzing Subword Techniques to Improve English to Sinhala Neural Machine Translation

Neural machine translation (NMT) is a remarkable approach which performs much better than the Statistical machine translation (SMT) models when there is an abundance of parallel corpus. However, vanilla NMT is primarily based upon word-level with a fixed vocabulary. Therefore, low resource morphologically rich languages such as Sinhala are mostly affected by the out of vocabulary (OOV) and Rare word problems. Recent advancements in subword techniques have opened up opportunities for low resource communities by enabling open vocabulary translation. In this paper, we extend our recently published state-of-the-art EN-SI translation system using the transformer and explore standard subword techniques on top of it to identify which subword approach has a greater effect on English Sinhala language pair. Our models demonstrate that subword segmentation strategies along with the state-of-the-art NMT can perform remarkably when translating English sentences into a rich morphology language regardless of a large parallel corpus.

ThamizhiMorph: A morphological parser for the Tamil language

This paper presents an open source and extendable Morphological Analyser cum Generator (MAG) for Tamil named ThamizhiMorph. Tamil is a low-resource language in terms of NLP processing tools and applications. In addition, most of the available tools are neither open nor extendable. A morphological analyser is a key resource for the storage and retrieval of morphophonological and morphosyntactic information, especially for morphologically rich languages, and is also useful for developing applications within Machine Translation. This paper describes how ThamizhiMorph is designed using a Finite-State Transducer (FST) and implemented using Foma. We discuss our design decisions based on the peculiarities of Tamil and its nominal and verbal paradigms. We specify a high-level meta-language to efficiently characterise the language’s inflectional morphology. We evaluate ThamizhiMorph using text from a Tamil textbook and the Tamil Universal Dependency treebank version 2.5. The evaluation and error analysis attest a very high performance level, with the identified errors being mostly due to out-of-vocabulary items, which are easily fixable. In order to foster further development, we have made our scripts, the FST models, lexicons, Meta-Morphological rules, lists of generated verbs and nouns, and test data sets freely available for others to use and extend upon.

Innovatively Fused Deep Learning with Limited Noisy Data for Evaluating Translations from Poor into Rich Morphology

Evaluation of machine translation (MT) into morphologically rich languages has not been well studied despite its importance. This paper proposes a classifier, that is, a deep learning (DL) schema for MT evaluation, based on different categories of information (linguistic features, natural language processing (NLP) metrics and embeddings), by using a model for machine learning based on noisy and small datasets. The linguistic features are string based for the language pairs English (EN)–Greek (EL) and EN–Italian (IT). The paper also explores the linguistic differences that affect evaluation accuracy between different kinds of corpora. A comparative study between using a simple embedding layer (mathematically calculated) and pre-trained embeddings is conducted. Moreover, an analysis of the impact of feature selection and dimensionality reduction on classification accuracy has been conducted. Results show that using a neural network (NN) model with different input representations produces results that clearly outperform the state-of-the-art for MT evaluation for EN–EL and EN–IT, by an increase of almost 0.40 points in correlation with human judgments on pairwise MT evaluation. It is observed that the proposed algorithm achieved better results on noisy and small datasets. In addition, for a more integrated analysis of the accuracy results, a qualitative linguistic analysis has been carried out in order to address complex linguistic phenomena.

Neural Modeling for Named Entities and Morphology (NEMO2)

Named Entity Recognition (NER) is a fundamental NLP task, commonly formulated as classification over a sequence of tokens. Morphologically rich languages (MRLs) pose a challenge to this basic formulation, as the boundaries of named entities do not necessarily coincide with token boundaries, rather, they respect morphological boundaries. To address NER in MRLs we then need to answer two fundamental questions, namely, what are the basic units to be labeled, and how can these units be detected and classified in realistic settings (i.e., where no gold morphology is available). We empirically investigate these questions on a novel NER benchmark, with parallel token- level and morpheme-level NER annotations, which we develop for Modern Hebrew, a morphologically rich-and-ambiguous language. Our results show that explicitly modeling morphological boundaries leads to improved NER performance, and that a novel hybrid architecture, in which NER precedes and prunes morphological decomposition, greatly outperforms the standard pipeline, where morphological decomposition strictly precedes NER, setting a new performance bar for both Hebrew NER and Hebrew morphological decomposition tasks.