Articles

Approximate sentence matching (ASM) is an important technique for tasks in machine translation (MT) such as example-based MT (EBMT) which influences the translation time and the quality of translation output. We investigate different approaches to find similar sentences in an example base and evaluate their efficiency (runtime), effectiveness, and the …...

We propose a first ever code-switch language model for mixed language speech recognition that incorporates syntactic constraints by a code-switch boundary prediction model, a code-switch translation model, and a reconstruction model. A WFST-based decoder then recognizes speech by combining an acoustic model, a pronunciation model and the code-switch language model …...

We present a novel topic modelling-based methodology to track emerging events in microblogs such as Twitter. Our topic model has an in-built update mechanism based on time slices and implements a dynamic vocabulary. We first show that the method is robust in detecting events using a range of datasets with …...

Compounds occur very frequently in Indian Languages. There are no strict orthographic conventions for compounds in modern Indian Languages. In this paper, Sanskrit compounding system is examined thoroughly and the insight gained from the Sanskrit grammar is applied for the analysis of compounds in Hindi and Marathi. It is interesting …...

Event anaphora resolution plays a critical role in discourse analysis. This paper focuses on improving event pronoun resolution using both local and global semantic information. In particular, a predicate-argument structure is proposed to represent the local semantic information about an event while the global semantic information is represented by the …...

Distributed representations of words have proven extremely useful in numerous natural lan- guage processing tasks. Their appeal is that they can help alleviate data sparsity problems common to supervised learning. Methods for inducing these representations require only unlabeled language data, which are plentiful for many natural languages. In this work, …...

This paper presents a novel method of improving Combinatory Categorial Grammar (CCG) parsing using features generated from Dependency Grammar (DG) parses and combined using reranking. Different grammar formalisms have different strengths and different parsing models have consequently divergent views of the data. More specifically, dependency parsers are sensitive to linguistic …...

This paper investigates a solution to yes/no question answering, which can be mapped to the task of determining the correctness of a given proposition. Generally it is hard to obtain explicit evidence to conclude a proposition is false from an information source, so we convert this task to a set …...

Online shoppers depend on customer reviews when evaluating products or services. However, in the international online marketplace, reviews in a user’s language may not be available. Translation of online customer reviews is therefore an important service. A crucial aspect of this task is translating opinion words, key words that capture …...

Extracting biomedical named entities is one of the major challenges in automatic processing of biomedical literature. This paper proposes a machine learning approach for finding phenotype names in text. Features are included in a machine learning infrastructure to implement the rules found in our previously developed rule-based system. The system …...

The phonetic alphabet enables people to dictate letters of the alphabet accurately by using representative words, i.e., A for Alpha. Japanese kanji (idiographic Chinese characters) vastly outnumber the letters of the Roman alphabet, and thus Japanese requires an explanatory reading like a phonetic alphabet. We call the explanatory reading of …...

Citations are a valuable resource for characterizing scientific publications that has already been used in applications such as summarization and information retrieval. These applications could be even better served by expanding citation information. We aim to achieve this by extracting and classifying citation information from the text, so that subsequent …...

Coreference resolution is the problem of clustering mentions into entities and is very critical for natural language understanding. This paper studies the problem of coreference resolution in the context of the newly emerging domain of Electronic Health Records (EHRs). The commonly used “best-link” model for coreference resolution considers only the …...

This paper presents the first systematic study of the coreference resolution problem in a general inference-based discourse processing framework. Employing the mode of inference called weighted abduction, we propose a novel solution to the overmerging problem inherent to inference-based frameworks. The overmerging problem consists in erroneously assuming distinct entities to …...

Traditional general readability methods tend to underperform in domain-specific document retrieval because they fail to effectively differentiate the reading difficulty of the individual domain-specific terms and the semantic associations between the textual units in a document. On the other hand, recently proposed domain-specific readability methods have relied upon an external …...

Recently, methods for mining graph sequences have attracted considerable interest in data- mining research. A graph sequence is a data structure used to represent changing networks. The aim of graph sequence mining is to enumerate common changing patterns appearing more frequently than a given threshold in graph sequences. Dependency analysis …...

Combinatory Categorial Grammar (CCG) is an expressive grammar formalism which is able to capture long-range dependencies. However, building large and wide-coverage treebanks for CCG is expensive and time-consuming. In this paper, we focus on the problem of unsupervised CCG induction from plain texts. Based on the baseline model in (Bisk …...

This work investigates an interesting and challenging task in summarization, i.e., personalized social summarization, which aims to adapt summarization result of a specified document to an intended user based on his interests inferred from social context implicitly. Most existing summarization systems generate a uniform version of summary for different users …...

This paper develops a new statistical method of building language models (LMs) of Japanese dialects for automatic speech recognition (ASR). One possible application is to recognize a variety of utterances in our daily lives. The most crucial problem in training language models for dialects is the shortage of linguistic corpora …...

Automatic methods to create entity dictionaries or gazetteers have used only a small number of entity types (18 at maximum), which could pose a limitation for fine-grained information extraction. This paper aims to create a dictionary of 200 extended named entity (ENE) types. Using Wikipedia as a basic resource, we …...