In statistical word alignment for machine translation, function words usually cause poor aligning performance because they do not have clear correspondence between different languages. This paper proposes a novel approach to improve word alignment by pruning alignments of function words from an existing alignment model with high precision and recall. Based on monolingual and bilingual frequency characteristics, a language-independent function word recognition algorithm is first proposed. Then a group of carefully defined syntactic structures combined with content word alignments are used for further function word alignment pruning. The experimental results show that the proposed approach improves both the quality of word alignment and the performance of statistical machine translation on Chinese-to-English, German-to-English and French-to-English language pairs.

With the progress in machine translation, it becomes more subtle to develop the evaluation metric capturing the systems’ differences in comparison to the human translations. In contrast to the current efforts in leveraging more linguistic information to depict translation quality, this paper takes the thread of combining language independent features for a robust solution to MT evaluation metric. To compete with finer granularity of modeling brought by linguistic features, the proposed method augments the word level metrics by a letter based calculation. An empirical study is then conducted over WMT data to train the metrics by ranking SVM. The results reveal that the integration of current language independent metrics can generate well enough performance for a variety of languages. Time-split data validation is promising as a better training setting, though the greedy strategy also works well.

Part of the long lasting cultural heritage of China is the classical ancient Chinese poems which follow strict formats and complicated linguistic rules. Automatic Chinese poetry composition by programs is considered as a challenging problem in computational linguistics and requires high Artificial Intelligence assistance, and has not been well addressed. In this paper, we formulate the poetry composition task as an optimization problem based on a generative summarization framework under several constraints. Given the user specified writing intents, the system retrieves candidate terms out of a large poem corpus, and then orders these terms to fit into poetry formats, satisfying tonal and rhythm requirements. The optimization process under constraints is conducted via iterative term substitutions till convergence, and outputs the subset with the highest utility as the generated poem. For experiments, we perform generation on large datasets of 61,960 classic poems from Tang and Song Dynasty of China. A comprehensive evaluation, using both human judgments and ROUGE scores, has demonstrated the effectiveness of our proposed approach.

Previous text processing techniques focus on text itself while neglecting human reading process. Therefore they are limited in special applications. This paper proposes a text scanning mechanism for generating the dynamic impressions of words in text by simulating recall, association and forget processes during reading. Experiments show that the mechanism is suitable for multiple text processing applications.

Lexical cohesion arises from a chain of lexical items that establish links between sentences in a text. In this paper we propose three different models to capture lexical cohesion for document-level machine translation: (a) a direct reward model where translation hypotheses are rewarded whenever lexical cohesion devices occur in them, (b) a conditional probability model where the appropriateness of using lexical cohesion devices is measured, and (c) a mutual information trigger model where a lexical cohesion relation is considered as a trigger pair and the strength of the association between the trigger and the triggered item is estimated by mutual information. We integrate the three models into hierarchical phrase-based machine translation and evaluate their effectiveness on the NIST Chinese-English translation tasks with large-scale training data. Experiment results show that all three models can achieve substantial improvements over the baseline and that the mutual information trigger model performs better than the others.

Due to the explosive growth of the Internet online reviews, we can easily collect a large amount of labeled reviews from different domains. But only some of them are beneficial for training a desired target-domain sentiment classifier. Therefore, it is important for us to identify those samples that are the most relevant to the target domain and use them as training data. To address this problem, a novel approach, based on instance selection and instance weighting via PU learning, is proposed. PU learning is used at first to learn an in-target-domain selector, which assigns an in-target-domain probability to each sample in the training set. For instance selection, the samples with higher in-target-domain probability are used as training data; For instance weighting, the calibrated in-target-domain probabilities are used as sampling weights for training an instance-weighted naive Bayes model, based on the principle of maximum weighted likelihood estimation. The experimental results prove the necessity and effectiveness of the approach, especially when the size of training data is large. It is also proved that the larger the Kullback-Leibler divergence between the training and test data is, the more effective the proposed approach will be.

In question answering, answer extraction aims topin-point the exact answer from passages. However,most previous methods perform such extractionon each passage separately, without consideringclues provided in other passages. This paperpresents a novel approach to extract answers byfully leveraging connections among different passages.Specially, extraction is performed on a PassageGraph which is built by adding links uponmultiple passages. Different passages are connectedby linking words with the same stem. Weuse the factor graph as our model for answer extraction.Experimental results on multiple QA datasets demonstrate that our method significantly improvesthe performance of answer extraction.

Convolution tree kernels have been successfully applied to many language processing tasks for achieving state-of-the-art accuracy. Unfortunately, higher computational complexity of learning with kernels w.r.t. using explicit feature vectors makes them less attractive for large-scale data.In this paper, we study the latest approaches to solve such problems ranging from feature hashing to reverse kernel engineering and approximate cutting plane training with model compression. We derive a novel method that relies on reverse-kernel engineering together with an efficient kernel learning method. The approach gives the advantage of using tree kernels to automatically generate rich structured feature spaces and working in the linear space where learning and testing is fast. We experimented with training sets up to 4 million examples from Semantic Role Labeling. The results show that (i) the choice of correct structural features is essential and (ii) we can speed-up training from weeks to less than 20 minutes.

This paper presents a reranking approach to combining constituent and dependency parsing, aimed at improving parsing performance on both sides. Most previous combination methods rely on complicated joint decoding to integrate graph- and transition-based dependency models. Instead, our approach makes use of a high-performance probabilistic context free grammar (PCFG) model to output k-best candidate constituent trees, and then a dependency parsing model to rerank the trees by their scores from both models, so as to get the most probable parse. Experimental results show that this reranking approach achieves the highest accuracy of constituent and dependency parsing on Chinese treebank (CTB5.1) and a comparable performance to the state of the art on English treebank (WSJ).

In this paper we present an approach aimed at enriching the Open Information Extraction paradigm with semantic relation ontologization by integrating syntactic and semantic features into its workflow. To achieve this goal, we combine deep syntactic analysis and distributional semantics using a shortest path kernel method and soft clustering. The output of our system is a set of automatically discovered and ontologized semantic relations.