arXiv subjects

Language models

Find arXiv papers on language models and computational linguistics, including cs.CL metadata. Use abstracts to explore model training, evaluation and natural-language processing.

Follow this topic with RSS

At least 73 records · Page 4Linked to original sources

arXiv2013

Intelligent Hybrid Man-Machine Translation Quality Estimation

Inferring evaluation scores based on human judgments is invaluable compared to using current evaluation metrics which are not suitable for real-time applications e.g. post-editing. However, these judgments are much more expensive to collect especially from expert translators, compared to evaluation based on indicators contrasting source and translation texts. This work introduces a novel approach for quality estimation by combining learnt confidence scores from a probabilistic inference model based on human judgments, with selective linguistic features-based scores, where the proposed inference model infers the credibility of given human ranks to solve the scarcity and inconsistency issues of human judgments. Experimental results, using challenging language-pairs, demonstrate improvement in correlation with human judgments over traditional evaluation metrics.

cs.CL↗

arXiv2013

Genetic approach for arabic part of speech tagging

With the growing number of textual resources available, the ability to understand them becomes critical. An essential first step in understanding these sources is the ability to identify the part of speech in each sentence. Arabic is a morphologically rich language, wich presents a challenge for part of speech tagging. In this paper, our goal is to propose, improve and implement a part of speech tagger based on a genetic alorithm. The accuracy obtained with this method is comparable to that of other probabilistic approaches.

cs.CL↗

arXiv2013

An alternative Gospel of structure: order, composition, processes

We survey some basic mathematical structures, which arguably are more primitive than the structures taught at school. These structures are orders, with or without composition, and (symmetric) monoidal categories. We list several `real life' incarnations of each of these. This paper also serves as an introduction to these structures and their current and potentially future uses in linguistics, physics and knowledge representation.

math.CT↗

arXiv2013

Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts

The use of robo-readers to analyze news texts is an emerging technology trend in computational finance. In recent research, a substantial effort has been invested to develop sophisticated financial polarity-lexicons that can be used to investigate how financial sentiments relate to future company performance. However, based on experience from other fields, where sentiment analysis is commonly applied, it is well-known that the overall semantic orientation of a sentence may differ from the prior polarity of individual words. The objective of this article is to investigate how semantic orientations can be better detected in financial and economic news by accommodating the overall phrase-structure information and domain-specific use of language. Our three main contributions are: (1) establishment of a human-annotated finance phrase-bank, which can be used as benchmark for training and evaluating alternative models; (2) presentation of a technique to enhance financial lexicons with attributes that help to identify expected direction of events that affect overall sentiment; (3) development of a linearized phrase-structure model for detecting contextual semantic orientations in financial and economic news texts. The relevance of the newly added lexicon features and the benefit of using the proposed learning-algorithm are demonstrated in a comparative study against previously used general sentiment models as well as the popular word frequency models used in recent financial studies. The proposed framework is parsimonious and avoids the explosion in feature-space caused by the use of conventional n-gram features.

cs.CL↗

arXiv2013

Clustering Algorithm for Gujarati Language

Natural language processing area is still under research. But now a day it is on platform for worldwide researchers. Natural language processing includes analyzing the language based on its structure and then tagging of each word appropriately with its grammar base. Here we have 50,000 tagged words set and we try to cluster those Gujarati words based on proposed algorithm, we have defined our own algorithm for processing. Many clustering techniques are available Ex. Single linkage, complete, linkage,average linkage, Hear no of clusters to be formed are not known, so it is all depends on the type of data set provided . Clustering is preprocess for stemming . Stemming is the process where root is extracted from its word. Ex. cats= cat+S, meaning. Cat: Noun and plural form.

cs.CL↗

arXiv2013

Speaker Independent Continuous Speech to Text Converter for Mobile Application

An efficient speech to text converter for mobile application is presented in this work. The prime motive is to formulate a system which would give optimum performance in terms of complexity, accuracy, delay and memory requirements for mobile environment. The speech to text converter consists of two stages namely front-end analysis and pattern recognition. The front end analysis involves preprocessing and feature extraction. The traditional voice activity detection algorithms which track only energy cannot successfully identify potential speech from input because the unwanted part of the speech also has some energy and appears to be speech. In the proposed system, VAD that calculates energy of high frequency part separately as zero crossing rate to differentiate noise from speech is used. Mel Frequency Cepstral Coefficient (MFCC) is used as feature extraction method and Generalized Regression Neural Network is used as recognizer. MFCC provides low word error rate and better feature extraction. Neural Network improves the accuracy. Thus a small database containing all possible syllable pronunciation of the user is sufficient to give recognition accuracy closer to 100%. Thus the proposed technique entertains realization of real time speaker independent applications like mobile phones, PDAs etc.

cs.CL↗

arXiv2013

Human and Automatic Evaluation of English-Hindi Machine Translation

For the past 60 years, Research in machine translation is going on. For the development in this field, a lot of new techniques are being developed each day. As a result, we have witnessed development of many automatic machine translators. A manager of machine translation development project needs to know the performance increase/decrease, after changes have been done in his system. Due to this reason, a need for evaluation of machine translation systems was felt. In this article, we shall present the evaluation of some machine translators. This evaluation will be done by a human evaluator and by some automatic evaluation metrics, which will be done at sentence, document and system level. In the end we shall also discuss the comparison between the evaluations.

cs.CL↗

arXiv2013

Information content versus word length in natural language: A reply to Ferrer-i-Cancho and Moscoso del Prado Martin [arXiv:1209.1751]

Recently, Ferrer i Cancho and Moscoso del Prado Martin [arXiv:1209.1751] argued that an observed linear relationship between word length and average surprisal (Piantadosi, Tily, & Gibson, 2011) is not evidence for communicative efficiency in human language. We discuss several shortcomings of their approach and critique: their model critically rests on inaccurate assumptions, is incapable of explaining key surprisal patterns in language, and is incompatible with recent behavioral results. More generally, we argue that statistical models must not critically rely on assumptions that are incompatible with the real system under study.

cs.CL↗

arXiv2013

A Novel Architecture For Question Classification Based Indexing Scheme For Efficient Question Answering

Question answering system can be seen as the next step in information retrieval, allowing users to pose question in natural language and receive compact answers. For the Question answering system to be successful, research has shown that the correct classification of question with respect to the expected answer type is requisite. We propose a novel architecture for question classification and searching in the index, maintained on the basis of expected answer types, for efficient question answering. The system uses the criteria for Answer Relevance Score for finding the relevance of each answer returned by the system. On analysis of the proposed system, it has been found that the system has shown promising results than the existing systems based on question classification.

cs.IR↗

arXiv2013

Learning Frames from Text with an Unsupervised Latent Variable Model

We develop a probabilistic latent-variable model to discover semantic frames---types of events and their participants---from corpora. We present a Dirichlet-multinomial model in which frames are latent categories that explain the linking of verb-subject-object triples, given document-level sparsity. We analyze what the model learns, and compare it to FrameNet, noting it learns some novel and interesting frames. This document also contains a discussion of inference issues, including concentration parameter learning; and a small-scale error analysis of syntactic parsing accuracy.

cs.CL↗

arXiv2013

Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction

This paper proposes a novel approach for relation extraction from free text which is trained to jointly use information from the text and from existing knowledge. Our model is based on two scoring functions that operate by learning low-dimensional embeddings of words and of entities and relationships from a knowledge base. We empirically show on New York Times articles aligned with Freebase relations that our approach is able to efficiently use the extra information provided by a large subset of Freebase data (4M entities, 23k relationships) to improve over existing methods that rely on text features alone.

cs.CL↗

arXiv2013

Extracting Connected Concepts from Biomedical Texts using Fog Index

In this paper, we establish Fog Index (FI) as a text filter to locate the sentences in texts that contain connected biomedical concepts of interest. To do so, we have used 24 random papers each containing four pairs of connected concepts. For each pair, we categorize sentences based on whether they contain both, any or none of the concepts. We then use FI to measure difficulty of the sentences of each category and find that sentences containing both of the concepts have low readability. We rank sentences of a text according to their FI and select 30 percent of the most difficult sentences. We use an association matrix to track the most frequent pairs of concepts in them. This matrix reports that the first filter produces some pairs that hold almost no connections. To remove these unwanted pairs, we use the Equally Weighted Harmonic Mean of their Positive Predictive Value (PPV) and Sensitivity as a second filter. Experimental results demonstrate the effectiveness of our method.

cs.CL↗

arXiv2013

Extracting Information-rich Part of Texts using Text Denoising

The aim of this paper is to report on a novel text reduction technique, called Text Denoising, that highlights information-rich content when processing a large volume of text data, especially from the biomedical domain. The core feature of the technique, the text readability index, embodies the hypothesis that complex text is more information-rich than the rest. When applied on tasks like biomedical relation bearing text extraction, keyphrase indexing and extracting sentences describing protein interactions, it is evident that the reduced set of text produced by text denoising is more information-rich than the rest.

cs.IR↗

arXiv2013

A Novel Architecture for Relevant Blog Page Identifcation

Blogs are undoubtedly the richest source of information available in cyberspace. Blogs can be of various natures i.e. personal blogs which contain posts on mixed issues or blogs can be domain specific which contains posts on particular topics, this is the reason, they offer wide variety of relevant information which is often focused. A general search engine gives back a huge collection of web pages which may or may not give correct answers, as web is the repository of information of all kinds and a user has to go through various documents before he gets what he was originally looking for, which is a very time consuming process. So, the search can be made more focused and accurate if it is limited to blogosphere instead of web pages. The reason being that the blogs are more focused in terms of information. So, User will only get related blogs in response to his query. These results will be then ranked according to our proposed method and are finally presented in front of user in descending order

cs.IR↗

arXiv2013

Exploring The Contribution of Unlabeled Data in Financial Sentiment Analysis

With the proliferation of its applications in various industries, sentiment analysis by using publicly available web data has become an active research area in text classification during these years. It is argued by researchers that semi-supervised learning is an effective approach to this problem since it is capable to mitigate the manual labeling effort which is usually expensive and time-consuming. However, there was a long-term debate on the effectiveness of unlabeled data in text classification. This was partially caused by the fact that many assumptions in theoretic analysis often do not hold in practice. We argue that this problem may be further understood by adding an additional dimension in the experiment. This allows us to address this problem in the perspective of bias and variance in a broader view. We show that the well-known performance degradation issue caused by unlabeled data can be reproduced as a subset of the whole scenario. We argue that if the bias-variance trade-off is to be better balanced by a more effective feature selection method unlabeled data is very likely to boost the classification performance. We then propose a feature selection framework in which labeled and unlabeled training samples are both considered. We discuss its potential in achieving such a balance. Besides, the application in financial sentiment analysis is chosen because it not only exemplifies an important application, the data possesses better illustrative power as well. The implications of this study in text classification and financial sentiment analysis are both discussed.

cs.CL↗

arXiv2013

Ontology Enrichment by Extracting Hidden Assertional Knowledge from Text

In this position paper we present a new approach for discovering some special classes of assertional knowledge in the text by using large RDF repositories, resulting in the extraction of new non-taxonomic ontological relations. Also we use inductive reasoning beside our approach to make it outperform. Then, we prepare a case study by applying our approach on sample data and illustrate the soundness of our proposed approach. Moreover in our point of view current LOD cloud is not a suitable base for our proposal in all informational domains. Therefore we figure out some directions based on prior works to enrich datasets of Linked Data by using web mining. The result of such enrichment can be reused for further relation extraction and ontology enrichment from unstructured free text documents.

cs.IR↗

arXiv2013

Context Specific Event Model For News Articles

We present a new context based event indexing and event ranking model for News Articles. The context event clusters formed from the UNL Graphs uses the modified scoring scheme for segmenting events which is followed by clustering of events. From the context clusters obtained three models are developed- Identification of Main and Sub events; Event Indexing and Event Ranking. Based on the properties considered from the UNL Graphs for the modified scoring main events and sub events associated with main-events are identified. The temporal details obtained from the context cluster are stored using hashmap data structure. The temporal details are place-where the event took; person-who involved in that event; time-when the event took place. Based on the information collected from the context clusters three indices are generated- Time index, Person index, and Place index. This index gives complete details about every event obtained from context clusters. A new scoring scheme is introduced for ranking the events. The scoring scheme for event ranking gives weight-age based on the priority level of the events. The priority level includes the occurrence of the event in the title of the document, event frequency, and inverse document frequency of the events.

cs.CL↗

arXiv2013

Logical analysis of natural language semantics to solve the problem of computer understanding

An object--oriented approach to create a natural language understanding system is considered. The understanding program is a formal system built on the base of predicative calculus. Horn's clauses are used as well--formed formulas. An inference is based on the principle of resolution. Sentences of natural language are represented in the view of typical predicate set. These predicates describe physical objects and processes, abstract objects, categories and semantic relations between objects. Predicates for concrete assertions are saved in a database. To describe the semantics of classes for physical objects, abstract concepts and processes, a knowledge base is applied. The proposed representation of natural language sentences is a semantic net. Nodes of such net are typical predicates. This approach is perspective as, firstly, such typification of nodes facilitates essentially forming of processing algorithms and object descriptions, secondly, the effectiveness of algorithms is increased (particularly for the great number of nodes), thirdly, to describe the semantics of words, encyclopedic knowledge is used, and this permits essentially to extend the class of solved problems.

cs.CL↗