Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedness which is not available in discrete representations, distributed representations have proven useful in many NLP tasks. Recent work has shown how compositional semantic representations can successfully be applied to a number of monolingual applications such as sentiment analysis. At the same time, there has been some initial success in work on learning shared word-level representations across languages. We combine these two approaches by proposing a method for learning distributed representations in a multilingual setup. Our model learns to assign similar embeddings to aligned sentences and dissimilar ones to sentence which are not aligned while not requiring word alignments. We show that our representations are semantically informative and apply them to a cross-lingual document classification task where we outperform the previous state of the art. Further, by employing parallel corpora of multiple language pairs we find that our model learns representations that capture semantic relationships across languages for which no parallel data was used.
Word alignment is an important natural language processing task that indicates the correspondence between natural languages. Recently, unsupervised learning of log-linear models for word alignment has received considerable attention as it combines the merits of generative and discriminative approaches. However, a major challenge still remains: it is intractable to calculate the expectations of non-local features that are critical for capturing the divergence between natural languages. We propose a contrastive approach that aims to differentiate observed training examples from noises. It not only introduces prior knowledge to guide unsupervised learning but also cancels out partition functions. Based on the observation that the probability mass of log-linear models for word alignment is usually highly concentrated, we propose to use top-n alignments to approximate the expectations with respect to posterior distributions. This allows for efficient and accurate calculation of expectations of non-local features. Experiments show that our approach achieves significant improvements over state-of-the-art unsupervised word alignment methods.
We introduce a framework for unsupervised learning of structured predictors with overlapping, global features. Each input's latent representation is predicted conditional on the observable data using a feature-rich conditional random field. Then a reconstruction of the input is (re)generated, conditional on the latent structure, using models for which maximum likelihood estimation has a closed-form. Our autoencoder formulation enables efficient learning without making unrealistic independence assumptions or restricting the kinds of features that can be used. We illustrate insightful connections to traditional autoencoders, posterior regularization and multi-view learning. We show competitive results with instantiations of the model for two canonical NLP tasks: part-of-speech induction and bitext word alignment, and show that training our model can be substantially more efficient than comparable feature-rich baselines.
Neural Machine Translation (NMT) is a new approach to machine translation that has shown promising results that are comparable to traditional approaches. A significant weakness in conventional NMT systems is their inability to correctly translate very rare words: end-to-end NMTs tend to have relatively small vocabularies with a single unk symbol that represents every possible out-of-vocabulary (OOV) word. In this paper, we propose and implement an effective technique to address this problem. We train an NMT system on data that is augmented by the output of a word alignment algorithm, allowing the NMT system to emit, for each OOV word in the target sentence, the position of its corresponding word in the source sentence. This information is later utilized in a post-processing step that translates every OOV word using a dictionary. Our experiments on the WMT14 English to French translation task show that this method provides a substantial improvement of up to 2.8 BLEU points over an equivalent NMT system that does not use this technique. With 37.5 BLEU points, our NMT system is the first to surpass the best result achieved on a WMT14 contest task.
In this paper, we propose a novel word-alignment-based method to solve the FAQ-based question answering task. First, we employ a neural network model to calculate question similarity, where the word alignment between two questions is used for extracting features. Second, we design a bootstrap-based feature extraction method to extract a small set of effective lexical features. Third, we propose a learning-to-rank algorithm to train parameters more suitable for the ranking tasks. Experimental results, conducted on three languages (English, Spanish and Japanese), demonstrate that the question similarity model is more effective than baseline systems, the sparse features bring 5% improvements on top-1 accuracy, and the learning-to-rank algorithm works significantly better than the traditional method. We further evaluate our method on the answer sentence selection task. Our method outperforms all the previous systems on the standard TREC data set.
In this paper, we attempt to improve Statistical Machine Translation (SMT) systems on a very diverse set of language pairs (in both directions): Czech - English, Vietnamese - English, French - English and German - English. To accomplish this, we performed translation model training, created adaptations of training settings for each language pair, and obtained comparable corpora for our SMT systems. Innovative tools and data adaptation techniques were employed. The TED parallel text corpora for the IWSLT 2015 evaluation campaign were used to train language models, and to develop, tune, and test the system. In addition, we prepared Wikipedia-based comparable corpora for use with our SMT system. This data was specified as permissible for the IWSLT 2015 evaluation. We explored the use of domain adaptation techniques, symmetrized word alignment models, the unsupervised transliteration models and the KenLM language modeling tool. To evaluate the effects of different preparations on translation results, we conducted experiments and used the BLEU, NIST and TER metrics. Our results indicate that our approach produced a positive impact on SMT quality.
The attentional mechanism has proven to be effective in improving end-to-end neural machine translation. However, due to the intricate structural divergence between natural languages, unidirectional attention-based models might only capture partial aspects of attentional regularities. We propose agreement-based joint training for bidirectional attention-based end-to-end neural machine translation. Instead of training source-to-target and target-to-source translation models independently,our approach encourages the two complementary models to agree on word alignment matrices on the same training data. Experiments on Chinese-English and English-French translation tasks show that agreement-based joint training significantly improves both alignment and translation quality over independent training.
IBM models are very important word alignment models in Machine Translation. Following the Maximum Likelihood Estimation principle to estimate their parameters, the models will easily overfit the training data when the data are sparse. While smoothing is a very popular solution in Language Model, there still lacks studies on smoothing for word alignment. In this paper, we propose a framework which generalizes the notable work Moore [2004] of applying additive smoothing to word alignment models. The framework allows developers to customize the smoothing amount for each pair of word. The added amount will be scaled appropriately by a common factor which reflects how much the framework trusts the adding strategy according to the performance on data. We also carefully examine various performance criteria and propose a smoothened version of the error count, which generally gives the best result.
Obtaining syntactic parses is a crucial part of many NLP pipelines. However, most of the world's languages do not have large amounts of syntactically annotated corpora available for building parsers. Syntactic projection techniques attempt to address this issue by using parallel corpora consisting of resource-poor and resource-rich language pairs, taking advantage of a parser for the resource-rich language and word alignment between the languages to project the parses onto the data for the resource-poor language. These projection methods can suffer, however, when the two languages are divergent. In this paper, we investigate the possibility of using small, parallel, annotated corpora to automatically detect divergent structural patterns between two languages. These patterns can then be used to improve structural projection algorithms, allowing for better performing NLP tools for resource-poor languages, in particular those that may not have large amounts of annotated data necessary for traditional, fully-supervised methods. While this detection process is not exhaustive, we demonstrate that common patterns of divergence can be identified automatically without prior knowledge of a given language pair, and the patterns can be used to improve performance of projection algorithms.
We present a simple neural network for word alignment that builds source and target word window representations to compute alignment scores for sentence pairs. To enable unsupervised training, we use an aggregation operation that summarizes the alignment scores for a given target word. A soft-margin objective increases scores for true target words while decreasing scores for target words that are not present. Compared to the popular Fast Align model, our approach improves alignment accuracy by 7 AER on English-Czech, by 6 AER on Romanian-English and by 1.7 AER on English-French alignment.
In order to control computational complexity, neural machine translation (NMT) systems convert all rare words outside the vocabulary into a single unk symbol. Previous solution (Luong et al., 2015) resorts to use multiple numbered unks to learn the correspondence between source and target rare words. However, testing words unseen in the training corpus cannot be handled by this method. And it also suffers from the noisy word alignment. In this paper, we focus on a major type of rare words -- named entity (NE), and propose to translate them with character level sequence to sequence model. The NE translation model is further used to derive high quality NE alignment in the bilingual training corpus. With the integration of NE translation and alignment modules, our NMT system is able to surpass the baseline system by 2.9 BLEU points on the Chinese to English task.
In this paper, we propose an effective way for biasing the attention mechanism of a sequence-to-sequence neural machine translation (NMT) model towards the well-studied statistical word alignment models. We show that our novel guided alignment training approach improves translation quality on real-life e-commerce texts consisting of product titles and descriptions, overcoming the problems posed by many unknown words and a large type/token ratio. We also show that meta-data associated with input texts such as topic or category information can significantly improve translation quality when used as an additional signal to the decoder part of the network. With both novel features, the BLEU score of the NMT system on a product title set improves from 18.6 to 21.3%. Even larger MT quality gains are obtained through domain adaptation of a general domain NMT system to e-commerce data. The developed NMT system also performs well on the IWSLT speech translation task, where an ensemble of four variant systems outperforms the phrase-based baseline by 2.1% BLEU absolute.
This work focuses on the rapid development of linguistic annotation tools for resource-poor languages. We experiment several cross-lingual annotation projection methods using Recurrent Neural Networks (RNN) models. The distinctive feature of our approach is that our multilingual word representation requires only a parallel corpus between the source and target language. More precisely, our method has the following characteristics: (a) it does not use word alignment information, (b) it does not assume any knowledge about foreign languages, which makes it applicable to a wide range of resource-poor languages, (c) it provides truly multilingual taggers. We investigate both uni- and bi-directional RNN models and propose a method to include external information (for instance low level information from POS) in the RNN to train higher level taggers (for instance, super sense taggers). We demonstrate the validity and genericity of our model by using parallel corpora (obtained by manual or automatic translation). Our experiments are conducted to induce cross-lingual POS and super sense taggers.
We report on an exploratory analysis of Emoji Dick, a project that leverages crowdsourcing to translate Melville's Moby Dick into emoji. This distinctive use of emoji removes textual context, and leads to a varying translation quality. In this paper, we use statistical word alignment and part-of-speech tagging to explore how people use emoji. Despite these simple methods, we observed differences in token and part-of-speech distributions. Experiments also suggest that semantics are preserved in the translation, and repetition is more common in emoji.
Identifying the different varieties of the same language is more challenging than unrelated languages identification. In this paper, we propose an approach to discriminate language varieties or dialects of Mandarin Chinese for the Mainland China, Hong Kong, Taiwan, Macao, Malaysia and Singapore, a.k.a., the Greater China Region (GCR). When applied to the dialects identification of the GCR, we find that the commonly used character-level or word-level uni-gram feature is not very efficient since there exist several specific problems such as the ambiguity and context-dependent characteristic of words in the dialects of the GCR. To overcome these challenges, we use not only the general features like character-level n-gram, but also many new word-level features, including PMI-based and word alignment-based features. A series of evaluation results on both the news and open-domain dataset from Wikipedia show the effectiveness of the proposed approach.
Neural Machine Translation (NMT) is a new approach for Machine Translation (MT), and due to its success, it has absorbed the attention of many researchers in the field. In this paper, we study NMT model on Persian-English language pairs, to analyze the model and investigate the appropriateness of the model for scarce-resourced scenarios, the situation that exists for Persian-centered translation systems. We adjust the model for the Persian language and find the best parameters and hyper parameters for two tasks: translation and transliteration. We also apply some preprocessing task on the Persian dataset which yields to increase for about one point in terms of BLEU score. Also, we have modified the loss function to enhance the word alignment of the model. This new loss function yields a total of 1.87 point improvements in terms of BLEU score in the translation quality.
We outline a bidirectional translation system that converts sentences from American Sign Language (ASL) to English, and vice versa. To perform machine translation between ASL and English, we utilize a generative approach. Specifically, we employ an adjustment to the IBM word-alignment model 1 (IBM WAM1), where we define language models for English and ASL, as well as a translation model, and attempt to generate a translation that maximizes the posterior distribution defined by these models. Then, using these models, we are able to quantify the concepts of fluency and faithfulness of a translation between languages.
One of the most important problems in machine translation (MT) evaluation is to evaluate the similarity between translation hypotheses with different surface forms from the reference, especially at the segment level. We propose to use word embeddings to perform word alignment for segment-level MT evaluation. We performed experiments with three types of alignment methods using word embeddings. We evaluated our proposed methods with various translation datasets. Experimental results show that our proposed methods outperform previous word embeddings-based methods.
This paper describes the Arabic Multi-Genre Broadcast (MGB-2) Challenge for SLT-2016. Unlike last year's English MGB Challenge, which focused on recognition of diverse TV genres, this year, the challenge has an emphasis on handling the diversity in dialect in Arabic speech. Audio data comes from 19 distinct programmes from the Aljazeera Arabic TV channel between March 2005 and December 2015. Programmes are split into three groups: conversations, interviews, and reports. A total of 1,200 hours have been released with lightly supervised transcriptions for the acoustic modelling. For language modelling, we made available over 110M words crawled from Aljazeera Arabic website Aljazeera.net for a 10 year duration 2000-2011. Two lexicons have been provided, one phoneme based and one grapheme based. Finally, two tasks were proposed for this year's challenge: standard speech transcription, and word alignment. This paper describes the task data and evaluation process used in the MGB challenge, and summarises the results obtained.
We explore six challenges for neural machine translation: domain mismatch, amount of training data, rare words, long sentences, word alignment, and beam search. We show both deficiencies and improvements over the quality of phrase-based statistical machine translation.