Katsuhito Sudoh

Incorporating Speech Recognition Confidence into Discriminative Named Entity Recognition of Speech Data

This paper proposes a named entity recognition (NER) method for speech recognition results that uses confidence on automatic speech recognition (ASR) as a feature. The ASR confidence feature indicates whether each word has been correctly recognized. The NER model is trained using ASR results with named entity (NE) labels as well as the corresponding transcriptions with NE labels. In experiments using support vector machines (SVMs) and speech data from Japanese newspaper articles, the proposed method outperformed a simple application of text-based NER to ASR results in NER F-measure by improving precision. These results show that the proposed method is effective in NER for noisy inputs.

HPSG-Based Preprocessing for English-to-Japanese Translation

Japanese sentences have completely different word orders from corresponding English sentences. Typical phrase-based statistical machine translation (SMT) systems such as Moses search for the best word permutation within a given distance limit (distortion limit). For English-to-Japanese translation, we need a large distance limit to obtain acceptable translations, and the number of translation candidates is extremely large. Therefore, SMT systems often fail to find acceptable translations within a limited time. To solve this problem, some researchers use rule-based preprocessing approaches, which reorder English words just like Japanese by using dozens of rules. Our idea is based on the following two observations: (1) Japanese is a typical head-final language, and (2) we can detect heads of English sentences by a head-driven phrase structure grammar (HPSG) parser. The main contributions of this article are twofold: First, we demonstrate how off-the-shelf, state-of-the-art HPSG parser enables us to write the reordering rules in an abstract level and can easily improve the quality of English-to-Japanese translation. Second, we also show that syntactic heads achieve better results than semantic heads. The proposed method outperforms the best system of NTCIR-7 PATMT EJ task.

Syntax-Based Post-Ordering for Efficient Japanese-to-English Translation

This article proposes a novel reordering method for efficient two-step Japanese-to-English statistical machine translation (SMT) that isolates reordering from SMT and solves it after lexical translation. This reordering problem, called post-ordering, is solved as an SMT problem from Head-Final English (HFE) to English. HFE is syntax-based reordered English that is very successfully used for reordering with English-to-Japanese SMT. The proposed method incorporates its advantage into the reverse direction, Japanese-to-English, and solves the post-ordering problem by accurate syntax-based SMT with target language syntax. Two-step SMT with the proposed post-ordering empirically reduces the decoding time of the accurate but slow syntax-based SMT by its good approximation using intermediate HFE. The proposed method improves the decoding speed of syntax-based SMT decoding by about six times with comparable translation accuracy in Japanese-to-English patent translation experiments.

Discriminative Preordering Meets Kendall's

This paper explores a simple discriminative preordering model for statistical machine translation. Our model traverses binary constituent trees, and classifies whether children of each node should be reordered. The model itself is not extremely novel, but herein we introduce a new procedure to determine oracle labels so as to maximize Kendall’s τ . Experiments in Japanese-to-English translation revealed that our simple method is comparable with, or superior to, state-of-the-art methods in translation accuracy.

tau

Previous research demonstrates that discourse relations can help generate high-quality summaries. Existing studies usually adopt existing discourse parsers directly with no modifications, hence cannot take full advantage of discourse parsing. This paper describes a new single document summarization system. In contrast to previous work, we train a discourse parser specially for summarization by using summaries. The training data are dynamically changed during the training phase to enable the parser to grab the text units that are important for summaries. A special tree-based summary extraction algorithm is designed to work with the new parser. The proposed system enables us to combine discourse parsing and summarization in a unified scheme. Experiments on both the RST-DT and DUC2001 datasets show the effectiveness of the proposed method.

Maximization

This paper presents a novel technique for empty category (EC) detection using distributed word representations. A joint model is learned from the labeled data to map both the distributed representations of the contexts of ECs and EC types to a low dimensional space. In the testing phase, the context of possible EC positions will be projected into the same space for empty category detection. Experiments on Chinese Treebank prove the effectiveness of the proposed method. We improve the precision by about 6 points on a subset of Chinese Treebank, which is a new state-ofthe-art performance on CTB.

Summarization based on task-oriented discourse parsing

This paper proposes a discriminative named entity recognition (NER) method from automatic speech recognition (ASR) results. The proposed method uses the confidence of the ASR result as a feature that represents whether each word has been correctly recognized. Consequently, it provides robust NER for the noisy input caused by ASR errors. The NER model is trained using ASR results and reference transcriptions with named entity (NE) annotation. Experimental results using support vector machines (SVMs) and speech data from Japanese newspaper articles show that the proposed method outperformed a simple application of text-based NER to the ASR results, especially in terms of improving precision.

Empty Category Detection With Joint Context-Label Embeddings

Coordinations refer to phrases such as “A and/but/or/... B”. The detection of coordinations remains a major problem due to the complexity of their components. Existing work normally classified the training data into two categories: correct and incorrect. This often caused the problem of data imbalance which inevitably damaged performances of the models they used. We propose to fully exploit the differences between training data by formulating the detection of coordinations as a ranking problem to remedy this problem. We develop a novel model based on the long short-term memory network. Experiments on Penn Treebank and Genia verified the effectiveness of the proposed model.

Named Entity Recognition from Speech Using Discriminative Models and Speech Recognition Confidence

Training of neural machine translation (NMT) models usually uses mini-batches for efficiency purposes. During the mini-batched training process, it is necessary to pad shorter sentences in a mini-batch to be equal in length to the longest sentence therein for efficient computation. Previous work has noted that sorting the corpus based on the sentence length before making mini-batches reduces the amount of padding and increases the processing speed. However, despite the fact that mini-batch creation is an essential step in NMT training, widely used NMT toolkits implement disparate strategies for doing so, which have not been empirically validated or compared. This work investigates mini-batch creation strategies with experiments over two different datasets. Our results suggest that the choice of a mini-batch creation strategy has a large effect on NMT training and some length-based sorting strategies do not always work well compared with simple shuffling.

Learning to Rank for Coordination Detection

Opinion rating has been studied for a long time and recent work started to pay attention to topical aspects opinion rating, for example, the food quality, service, location and price of a restaurant. In this paper, we focus on predicting the overall and aspect rating of entities based on widely available on-line reviews. A novel hierarchical Bayesian generative method is developed for this task. It enables us to mine the overall and aspect ratings of both entity and its reviews at the same time. We conduct experiments on TripAdvisor and results show that we can predict entity-level and review-level overall ratings and aspect ratings well.