Articles

Sequence labeling models like conditional random fields have been successfully applied in a variety of NLP tasks. However, as the size of label set and dataset grows, the learning speed of batch algorithms like L-BFGS quickly becomes computationally unacceptable. Several online learning methods have been proposed in large scale setting, …...

Snippet generation plays an important role in a search engine. Good snippets provide users a good indication on the main content of a search result related to the query and on whether one can find relevant information in it. Previous studies on snippet generation focused on selecting sentences that are …...

Scientific publications contain many references to method terminologies used during scientific experiments. New terms are constantly created within the research community, especially in the biomedical domain where thousands of papers are published each week. In this study we report our attempt to automatically extract such method terminologies from scientific research …...

Testing a theory against real world data can sometimes be helpful in figuring out the shortcom- ings of your current theory. In this paper, we test a theory about the syntax-semantics interface of German nach-particle verbs against data from a web corpus in order to see if we can use …...

Sentence compression is important in a wide range of applications in natural language process- ing. Previous approaches of Japanese sentence compression can be divided into two groups. Word-based methods extract a subset of words from a sentence to shorten it, while bunsetsu- based methods extract a subset of bunsetsu (where …...

We propose a new measure of semantic similarity between words in context, which exploits the syntactic/semantic structure of the context surrounding each target word. For a given pair of target words and their sentential contexts, labeled directed graphs are made from the output of a semantic parser on these sentences. …...

Ranking tweets is a fundamental task to make it easier to distill the vast amounts of information shared by users. In this paper, we explore the novel idea of ranking tweets on a topic using heterogeneous networks. We construct heterogeneous networks by harnessing cross-genre linkages between tweets and semantically-related web …...

Geolocation prediction is vital to geospatial applications like localised search and local event detection. Predominately, social media geolocation models are based on full text data, including common words with no geospatial dimension (e.g. today) and noisy strings (tmrw), potentially hampering prediction and leading to slower/more memory-intensive models. In this paper, …...

Topic modeling for information retrieval (IR) has attracted significant attention and demonstrated good performance in a wide variety of tasks over the years. In this paper, we first present a comprehensive comparison of various topic modeling approaches, including the so-called document topic models (DTM) and word topic models (WTM), for …...

This paper brings up an important issue, polysemy problems, in a Chinese to Taiwanese TTS (text-to-speech) system. Polysemy means there are words with more than one meaning or pronunciation, such as “我們” (we), “不” (no), “你” (you), “我” (I), and “要” (want). We first will show the importance of the …...

The usual challenges of transcribing spoken language are compounded for Southern Min (Taiwanese) because it lacks a generally accepted orthography. This study reports the development and testing of software tools for assisting such transcription. Three tools are compared, each representing a different type of interface with our corpus-based Southern Min …...

Sanskrit, the classical language of India, presents specific challenges for computational linguistics: exact phonetic transcription in writing that obscures word boundaries, rich morphology and an enormous corpus, among others. Recent international cooperation has developed innovative solutions to these problems and significant resources for linguistic research. Solutions include efficient segmenting and …...

Many of the state-of-the-art methods for constructing a polarity lexicon rely on the propagation of polarity on the lexical network. In one of those methods, where the Ising spin model is em- ployed as a probabilistic model, it is reported that the system exhibits the phase transition in the vicinity …...

In this work we present a novel approach to bootstrap domain specific terminology, namely Structured Term Recognition, and we apply it to the medical domain. In contrast to previous approaches, based on observing distributional properties of terminology with respect to their contexts, our method analyzes the “internal structure” of multi-word …...

We present a new method to generate extractive multi-document summaries. The method uses Integer Linear Programming to jointly maximize the importance of the sentences it includes in the summary and their diversity, without exceeding a maximum allowed summary length. To obtain an importance score for each sentence, it uses a …...

Manual corpus annotation is getting widely used in Natural Language Processing (NLP). While being recognized as a difficult task, no in-depth analysis of its complexity has been performed yet. We provide in this article a grid of analysis of the different complexity dimensions of an annotation task, which helps estimating …...

There is a demand for taxonomies to organise large collections of documents into categories for browsing and exploration. This paper examines four existing taxonomies that have been manually created, along with two methods for deriving taxonomies automatically from data items. We use these taxonomies to organise items from a large …...

Online user comments contain valuable user opinions. Comments vary greatly in quality and detecting high quality comments is a subtask of opinion mining and summarization research. Finding attentive comments that provide some reasoning is highly valuable in understanding the user’s opinion particularly in sociopolitical opinion mining and aids policy makers, …...

In this paper, we propose a novel semantic cohesion model. Our model utilizes the predicate- argument structures as soft constraints and plays the role as a reordering model in the phrase- based statistical machine translation system. We build a translation system with GALE data. Experimental results on the NIST02, NIST03, …...

We investigate the stacking of dependency and phrase structure parsers, i.e. we define features from the output of a phrase structure parser for a dependency parser and vice versa. Our features are based on the original form of the external parses and we also compare this approach to converting phrase …...