COLING 2016 论文列表

We present a new Bayesian HMM word alignment model for statistical machine translation. The model is a mixture of an alignment model and a language model. The alignment component is a Bayesian extension of the standard HMM. The language model component is responsible for the generation of words needed for source fluency reasons from source language context. This allows for untranslatable source words to remain unaligned and at the same time avoids the introduction of artificial NULL words which introduces unusually long alignment jumps. Existing Bayesian word alignment models are unpractically slow because they consider each target position when resampling a given alignment link. The sampling complexity therefore grows linearly in the target sentence length. In order to make our model useful in practice, we devise an auxiliary variable Gibbs sampler that allows us to resample alignment links in constant time independently of the target sentence length. This leads to considerable speed improvements. Experimental results show that our model performs as well as existing word alignment toolkits in terms of resulting BLEU score.

Although more additional corpora are now available for Statistical Machine Translation (SMT), only the ones which belong to the same or similar domains of the original corpus can indeed enhance SMT performance directly. A series of SMT adaptation methods have been proposed to select these similar-domain data, and most of them focus on sentence selection. In comparison, phrase is a smaller and more fine grained unit for data selection, therefore we propose a straightforward and efficient connecting phrase based adaptation method, which is applied to both bilingual phrase pair and monolingual n-gram adaptation. The proposed method is evaluated on IWSLT/NIST data sets, and the results show that phrase based SMT performances are significantly improved (up to +1.6 in comparison with phrase based SMT baseline system and +0.9 in comparison with existing methods).

Human-targeted metrics provide a compromise between human evaluation of machine translation, where high inter-annotator agreement is difficult to achieve, and fully automatic metrics, such as BLEU or TER, that lack the validity of human assessment. Human-targeted translation edit rate (HTER) is by far the most widely employed human-targeted metric in machine translation, commonly employed, for example, as a gold standard in evaluation of quality estimation. Original experiments justifying the design of HTER, as opposed to other possible formulations, were limited to a small sample of translations and a single language pair, however, and this motivates our re-evaluation of a range of human-targeted metrics on a substantially larger scale. Results show significantly stronger correlation with human judgment for HBLEU over HTER for two of the nine language pairs we include and no significant difference between correlations achieved by HTER and HBLEU for the remaining language pairs. Finally, we evaluate a range of quality estimation systems employing HTER and direct assessment (DA) of translation adequacy as gold labels, resulting in a divergence in system rankings, and propose employment of DA for future quality estimation evaluations.

Selecting appropriate translations for source words with multiple meanings still remains a challenge for statistical machine translation (SMT). One reason for this is that most SMT systems are not good at detecting the proper sense for a polysemic word when it appears in different contexts. In this paper, we adopt a supersense tagging method to annotate source words with coarse-grained ontological concepts. In order to enable the system to choose an appropriate translation for a word or phrase according to the annotated supersense of the word or phrase, we propose two translation models with supersense knowledge: a maximum entropy based model and a supersense embedding model. The effectiveness of our proposed models is validated on a large-scale English-to-Spanish translation task. Results indicate that our method can significantly improve translation quality via correctly conveying the meaning of the source language to the target language.

Evaluating the quality of output from language processing systems such as machine translation or speech recognition is an essential step in ensuring that they are sufficient for practical use. However, depending on the practical requirements, evaluation approaches can differ strongly. Often, reference-based evaluation measures (such as BLEU or WER) are appealing because they are cheap and allow rapid quantitative comparison. On the other hand, practitioners often focus on manual evaluation because they must deal with frequently changing domains and quality standards requested by customers, for which reference-based evaluation is insufficient or not possible due to missing in-domain reference data (Harris et al., 2016). In this paper, we attempt to bridge this gap by proposing a framework for lightly supervised quality estimation. We collect manually annotated scores for a small number of segments in a test corpus or document, and combine them with automatically predicted quality scores for the remaining segments to predict an overall quality estimate. An evaluation shows that our framework estimates quality more reliably than using fully automatic quality estimation approaches, while keeping annotation effort low by not requiring full references to be available for the particular domain.

The attention mechanism is appealing for neural machine translation, since it is able to dynamically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse than conventional alignment models in alignment accuracy. In this paper, we analyze and explain this issue from the point view of reordering, and propose a supervised attention which is learned with guidance from conventional alignment models. Experiments on two Chinese-to-English translation tasks show that the supervised attention mechanism yields better alignments leading to substantial gains over the standard attention based NMT.

In neural machine translation, the attention mechanism facilitates the translation process by producing a soft alignment between the source sentence and the target sentence. However, without dedicated distortion and fertility models seen in traditional SMT systems, the learned alignment may not be accurate, which can lead to low translation quality. In this paper, we propose two novel models to improve attention-based neural machine translation. We propose a recurrent attention mechanism as an implicit distortion model, and a fertility conditioned decoder as an implicit fertility model. We conduct experiments on large-scale Chinese–English translation tasks. The results show that our models significantly improve both the alignment and translation quality compared to the original attention mechanism and several other variations.

Estimating similarities at different levels of linguistic units, such as words, sub-phrases and phrases, is helpful for measuring semantic similarity of an entire bilingual phrase. In this paper, we propose a convolution-enhanced bilingual recursive neural network (ConvBRNN), which not only exploits word alignments to guide the generation of phrase structures but also integrates multiple-level information of the generated phrase structures into bilingual semantic modeling. In order to accurately learn the semantic hierarchy of a bilingual phrase, we develop a recursive neural network to constrain the learned bilingual phrase structures to be consistent with word alignments. Upon the generated source and target phrase structures, we stack a convolutional neural network to integrate vector representations of linguistic units on the structures into bilingual phrase embeddings. After that, we fully incorporate information of different linguistic units into a bilinear semantic similarity model. We introduce two max-margin losses to train the ConvBRNN model: one for the phrase structure inference and the other for the semantic similarity model. Experiments on NIST Chinese-English translation tasks demonstrate the high quality of the generated bilingual phrase structures with respect to word alignments and the effectiveness of learned semantic similarities on machine translation.

This article proposes a novel character-aware neural machine translation (NMT) model that views the input sequences as sequences of characters rather than words. On the use of row convolution (Amodei et al., 2015), the encoder of the proposed model composes word-level information from the input sequences of characters automatically. Since our model doesn’t rely on the boundaries between each word (as the whitespace boundaries in English), it is also applied to languages without explicit word segmentations (like Chinese). Experimental results on Chinese-English translation tasks show that the proposed character-aware NMT model can achieve comparable translation performance with the traditional word based NMT models. Despite the target side is still word based, the proposed model is able to generate much less unknown words.

In this paper, we provide a solution to multilingual sentiment classification using deep learning. Given input text in a language, we use word translation into English and then the embeddings of these English words to train a classifier. This projection into the English space plus word embeddings gives a simple and uniform framework for multilingual sentiment analysis. A novel idea is augmentation of the training data with polar words, appearing in these sentences, along with their polarities. This approach leads to a performance gain of 7-10% over traditional classifiers on many languages, irrespective of text genre, despite the scarcity of resources in most languages.

This article presents the results we obtained on a complex annotation task (that of dependency syntax) using a specifically designed Game with a Purpose, ZombiLingo. We show that with suitable mechanisms (decomposition of the task, training of the players and regular control of the annotation quality during the game), it is possible to obtain annotations whose quality is significantly higher than that obtainable with a parser, provided that enough players participate. The source code of the game and the resulting annotated corpora (for French) are freely available.

We present a novel way for designing complex joint inference and learning models using Saul (Kordjamshidi et al., 2015), a recently-introduced declarative learning-based programming language (DeLBP). We enrich Saul with components that are necessary for a broad range of learning based Natural Language Processing tasks at various levels of granularity. We illustrate these advances using three different, well-known NLP problems, and show how these generic learning and inference modules can directly exploit Saul’s graph-based data representation. These properties allow the programmer to easily switch between different model formulations and configurations, and consider various kinds of dependencies and correlations among variables of interest with minimal programming effort. We argue that Saul provides an extremely useful paradigm both for the design of advanced NLP systems and for supporting advanced research in NLP.

Microblogging services allow users to create hashtags to categorize their posts. In recent years, the task of recommending hashtags for microblogs has been given increasing attention. However, most of existing methods depend on hand-crafted features. Motivated by the successful use of long short-term memory (LSTM) for many natural language processing tasks, in this paper, we adopt LSTM to learn the representation of a microblog post. Observing that hashtags indicate the primary topics of microblog posts, we propose a novel attention-based LSTM model which incorporates topic modeling into the LSTM architecture through an attention mechanism. We evaluate our model using a large real-world dataset. Experimental results show that our model significantly outperforms various competitive baseline methods. Furthermore, the incorporation of topical attention mechanism gives more than 7.4% improvement in F1 score compared with standard LSTM method.

In this paper we address a new problem of predicting affect and well-being scales in a real-world setting of heterogeneous, longitudinal and non-synchronous textual as well as non-linguistic data that can be harvested from on-line media and mobile phones. We describe the method for collecting the heterogeneous longitudinal data, how features are extracted to address missing information and differences in temporal alignment, and how the latter are combined to yield promising predictions of affect and well-being on the basis of widely used psychological scales. We achieve a coefficient of determination (R^2) of 0.71-0.76 and a correlation coefficient of 0.68-0.87 which is higher than the state-of-the art in equivalent multi-modal tasks for affect.

Probabilistic models are a useful means for analyzing large text corpora. Integrating such models with human interaction enables many new use cases. However, adding human interaction to probabilistic models requires inference algorithms which are both fast and accurate. We explore the use of Iterated Conditional Modes as a fast alternative to Gibbs sampling or variational EM. We demonstrate superior performance both in run time and model quality on three different models of text including a DP Mixture of Multinomials for web search result clustering, the Interactive Topic Model, and M OM R ESP , a multinomial crowdsourcing model.

This paper presents classification results for the analysis of sentiment in political news articles. The domain of political news is particularly challenging, as journalists are presumably objective, whilst at the same time opinions can be subtly expressed. To deal with this challenge, in this work we conduct a two-step classification model, distinguishing first subjective and second positive and negative sentiment texts. More specifically, we propose a shallow machine learning approach where only minimal features are needed to train the classifier, including sentiment-bearing Co-Occurring Terms (COTs) and negation words. This approach yields close to state-of-the-art results. Contrary to results in other domains, the use of negations as features does not have a positive impact in the evaluation results. This method is particularly suited for languages that suffer from a lack of resources, such as sentiment lexicons or parsers, and for those systems that need to function in real-time.

Sentiment classification becomes more and more important with the rapid growth of user generated content. However, sentiment classification task usually comes with two challenges: first, sentiment classification is highly domain-dependent and training sentiment classifier for every domain is inefficient and often impractical; second, since the quantity of labeled data is important for assessing the quality of classifier, it is hard to evaluate classifiers when labeled data is limited for certain domains. To address the challenges mentioned above, we focus on learning high-level features that are able to generalize across domains, so a global classifier can benefit with a simple combination of documents from multiple domains. In this paper, the proposed model incorporates both sentiment polarity and unlabeled data from multiple domains and learns new feature representations. Our model doesn’t require labels from every domain, which means the learned feature representation can be generalized for sentiment domain adaptation. In addition, the learned feature representation can be used as classifier since our model defines the meaning of feature value and arranges high-level features in a prefixed order, so it is not necessary to train another classifier on top of the new features. Empirical evaluations demonstrate our model outperforms baselines and yields competitive results to other state-of-the-art works on benchmark datasets.

During the 2016 United States presidential election, politicians have increasingly used Twitter to express their beliefs, stances on current political issues, and reactions concerning national and international events. Given the limited length of tweets and the scrutiny politicians face for what they choose or neglect to say, they must craft and time their tweets carefully. The content and delivery of these tweets is therefore highly indicative of a politician’s stances. We present a weakly supervised method for extracting how issues are framed and temporal activity patterns on Twitter for popular politicians and issues of the 2016 election. These behavioral components are combined into a global model which collectively infers the most likely stance and agreement patterns among politicians, with respective accuracies of 86.44% and 84.6% on average.

QA systems have been making steady advances in the challenging elementary science exam domain. In this work, we develop an explanation-based analysis of knowledge and inference requirements, which supports a fine-grained characterization of the challenges. In particular, we model the requirements based on appropriate sources of evidence to be used for the QA task. We create requirements by first identifying suitable sentences in a knowledge base that support the correct answer, then use these to build explanations, filling in any necessary missing information. These explanations are used to create a fine-grained categorization of the requirements. Using these requirements, we compare a retrieval and an inference solver on 212 questions. The analysis validates the gains of the inference solver, demonstrating that it answers more questions requiring complex inference, while also providing insights into the relative strengths of the solvers and knowledge sources. We release the annotated questions and explanations as a resource with broad utility for science exam QA, including determining knowledge base construction targets, as well as supporting information aggregation in automated inference.