Articles

We study the problem of natural language query generation for decision support sys- tems (DSS) in the problem resolution do- main. In this domain, a user has a task he is unable to accomplish (eg. bluetooth head- phone not playing music), which we cap- ture using language structures. We show …...

State-of-the-art statistical machine transla- tion systems rely heavily on training data and insufficient training data usually re- sults in poor translation quality. One so- lution to alleviate this problem is triangu- lation. Triangulation uses a third language as a pivot through which another source- target translation system can be built. …...

We offer a noisy channel approach for rec- ognizing and correcting erroneous words in referring expressions. Our mechanism handles three types of errors: it removes noisy input, inserts missing prepositions, and replaces mis-heard words (at present, they are replaced by generic words). Our mechanism was evaluated on a corpus of …...

We present a performance evaluation framework for Spoken Language Under- standing (SLU) modules, focusing on three elements: (1) characterization of spoken utterances, (2) experimental de- sign, and (3) quantitative evaluation met- rics. We then describe the application of our framework to Scusi?— our SLU sys- tem that focuses on referring …...

In this paper, we present our efforts to- wards incorporating external knowledge from Hindi WordNet to aid dependency parsing. We conduct parsing experiments on Hindi, an Indo-Aryan language, utiliz- ing the information from concept ontolo- gies available in Hindi WordNet to com- plement the morpho-syntactic information already available. The work …...

Dialog behavior is affected by power re- lations among the discourse participants. We show that four different types of power relations (hierarchical power, situational power, influence, and power over commu- nication) affect written dialog behavior in different ways. We also present a system that can identify power relations given a …...

Light verb constructions (LVCs) are verb and noun combinations in which the verb has lost its meaning to some degree and the noun is used in one of its original senses. They often share their syntactic pattern with other constructions (e.g. verb- object pairs) thus LVC detection can be viewed …...

We investigate the robustness of domain adaptation (DA) representations and meth- ods across target domains using part-of- speech (POS) tagging as a case study. We find that there is no single representation and method that works equally well for all target domains. In particular, there are large differences between target …...

This paper is concerned with capturing long-distance dependencies in sequence models. We propose a two-step strat- egy. First, the stacked learning technique is applied to integrate sequence models that are good at exploring local informa- tion and other high complexity models that are good at capturing long-distance de- pendencies. Second, …...

A major problem in the field of Chinese word segmentation is the identification of out-of- vocabulary words. We propose a simple yet effective approach for extracting maximized substrings, which provide good estimations of unknown word boundaries. We also develop a new semi-supervised segmentation technique that incorporates retrieved substrings using discriminative …...

Event recognition and event type classifi- cation are among the important areas in text mining. A state-of-the-art approach utilizing deep-level lexical semantics and syntactic dependencies suffers from a limitation of requiring too large feature space. In this paper, we propose a novel feature selection method using a semantic hierarchy of …...

In this research, we suggest an approach to retrieval-related tasks for Korean SMS text. Most of the previous approaches to such text used morphological analysis as the routine stage of the preprocessing workflow, functionally equivalent to POS tagging. However, such approaches suffer difficulties since Short Message Service language usually contains …...

This paper presents a simple but effec- tive approach to unknown word processing in Japanese morphological analysis, which handles 1) unknown words that are de- rived from words in a pre-defined lexicon and 2) unknown onomatopoeias. Our ap- proach leverages derivation rules and ono- matopoeia patterns, and correctly recog- nizes …...

This paper investigates the importance of a word lattice generation algorithm in joint word segmentation and POS tagging. We conducted experiments on three Japanese data sets to demonstrate that the previ- ously proposed pruning-based algorithm is in fact not efficient enough, and that the pipeline algorithm, which is introduced in …...

We study the linguistic phenomenon of informal words in the domain of Chi- nese microtext and present a novel method for normalizing Chinese informal words to their formal equivalents. We formal- ize the task as a classification problem and propose rule-based and statistical fea- tures to model three plausible channels …...

As the popularity of Community Ques- tion Answering(CQA) increases, spam- ming activities also picked up in number- s and variety. On CQA sites, spammers often pretend to ask questions, and selec- t answers which were published by their partners or themselves as the best answers. These fake best answers cannot …...

Social streams have proven to be the most up-to-date and inclusive information on cur- rent events. In this paper we propose a novel probabilistic modelling framework, called vi- olence detection model (VDM), which en- ables the identification of text containing vio- lent content and extraction of violence-related topics over social …...

Animacy is an inherent property of en- tities that nominals refer to in the phys- ical world. This semantic property of a nominal has received much attention in both linguistics and computational linguis- tics. In this paper, we present a robust unsupervised technique to infer the ani- macy of nominals …...

We present the Prague Discourse Treebank 1.0, a collection of Czech texts annotated for various discourse-related phenomena "beyond the sentence boundary". The treebank contains manual annotations of (1), discourse connect- ives, their arguments and senses, (2), textual coreference, and (3), bridging anaphora, all carried out on 50k sentences of the …...

This paper proposes a novel algorithm for multilingual mention detection: we ex- tract mentions from parse trees via kernel- based SVM learning. Our approach al- lows for straightforward mention detection for any language where (not necessary per- fect) parsing resources are available, with- out any complex language-specific rule engineering. We …...