Взаимная информация

We describe a statistical technique for assign- ing senses to words. An instance of a word is as- signed a sense by asking a question about the con- text in …...

Bootstrap methods (unsupervised classification) that generate word classes without requiring pretagging have had notable success in the last few years. The methods described here strengthen these approaches and produce excellent …...

Statistical language models are useful because they can provide probabilis- tic information upon uncertain decision making. The most common statistic is n-grams measuring word cooccurrences in texts. The method suffers …...

Many information retrieval(IR) systems retrieve relevant documents based on exact matching of keywords between a query and documents. This method degrades precision rate. In order to solve the problem, we …...

For languages whose character set is very large and whose orthography does not require spac- ing between words, such as Japanese, tokenizing and part-of-speech tagging are often the diffi- cult …...

Non-compositional expressions present a special challenge to NLP applications. We present a method for automatic identification of non-compositional ex- pressions using their statistical properties in a text corpus. Our method …...

AbstractFor cross-language information retrieval (CLIR), often queries or documents are translated into the other language to create a mono-lingual information retrieval situation. Having surveyed recent research results on translation-based CLIR, …...

An easy way of translating queries in one language to the other for cross-language information retrieval (IR) is to use a simple bilingual dictionary. Because of the general- purpose nature …...

We have participated in the SENSEVAL-2 En- glish tasks (all words and lexical sample) with an unsupervised system based on mutual infor- mation measured over a large corpus (277 mil- …...

This paper proposes a practical approach employing n-gram models and error-correction rules for Thai key prediction and Thai-English language identification. The paper also proposes rule-reduction algorithm applying mutual information to …...

Automatic Multi-word Units Extraction is an important issue in Natural Language Processing. This paper has proposed a new statistical method based on a large-scale balanced corpus to extract multi-word units. …...

The task of identifying proper names, unknown words and new terms, is an important step in text processing systems. This paper describes a method of using mutual information to collect …...

Language model based IR system proposed in recent 5 years has introduced the language model approach in the speech recognition area into the IR community and improves the performance of …...

Ngram models are simple in language modeling and have been successfully used in speech recognition and other tasks. However, they can only capture the short distance context dependency within an …...

This paper describes a hybrid system for WSD, pre- sented to the English all-words and lexical-sample tasks, that relies on two different unsupervised ap- proaches. The first one selects the …...

. Mining terminology translation from a large amount of Web data can be applied in many fields such as reading/writing assistant, machine translation and cross-language information retrieval. How to find …...

. Category-based statistic language model is an important method to solve the problem of sparse data. But there are two bottlenecks about this model: (1) the problem of word clustering, …...

. It remains to be a difficult issue to convert Chinese language into Chinese sign language, which makes it hard to implement an obstacle free Chinese sign language information service …...

This paper focuses on the evaluation of meth- ods for the automatic acquisition of Multiword Expressions (MWEs) for robust grammar engi- neering. First we investigate the hypothesis that MWEs can …...

We describe an approach for acquiring the domain-specific dialog knowledge required to configure a task-oriented dialog system that uses human-human interaction data. The key aspects of this problem are the …...

. This work is part of a large research project entitled "Oreillodule" aimed at developing tools for automatic speech recognition, translation, and synthesis for Arabic language. Our attention has mainly …...

This paper presents a novel, ranking-style word segmentation approach, called RSVM- Seg, which is well tailored to Chinese informa- tion retrieval(CIR). This strategy makes seg- mentation decision based on the …...

A machine translated sentence is seldom completely correct. Confidence measures are designed to detect incorrect words, phrases or sentences, or to provide an esti- mation of the probability of correctness. …...

AbstractThe knowledge about the relation between events is quite useful for coreference resolution, anaphora resolution, and several NLP applications such as dialogue system. This paper presents a large scale database …...

This paper takes an in-depth look at the relationship between mechanically extracted keywords and ‘Top Ten News of the Year’ compiled by the news editors. A previous study that briefly …...

AbstractZero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, …...

AbstractA longstanding debate in semiotics centers on the relationship between linguistic signs and their corresponding semantics: is there an arbitrary relationship between a word form and its meaning, or does …...

AbstractIn Community-based Question Answering system(CQA), Answer Selection(AS) is a critical task, which focuses on finding a suitable answer within a list of candidate answers. For neural network models, the key …...

AbstractWord embedding-based similarity measures are currently among the top-performing methods on unsupervised semantic textual similarity (STS) tasks. Recent work has increasingly adopted a statistical view on these embeddings, with some …...

AbstractThe success of neural networks on a diverse set of NLP tasks has led researchers to question how much these networks actually “know” about natural language. Probes are a natural …...

AbstractPimentel et al. (2020) recently analysed probing from an information-theoretic perspective. They argue that probing should be seen as approximating a mutual information. This led to the rather unintuitive conclusion …...

AbstractWeakly supervised question answering usually has only the final answers as supervision signals while the correct solutions to derive the answers are not provided. This setting gives rise to the …...

AbstractCharge prediction aims to predict the final charge for a case according to its fact descriptionand plays an important role in legal assistance systems. With deep learning based methods prediction …...

AbstractPre-trained language models derive substantial linguistic and factual knowledge from the massive corpora on which they are trained, and prompt engineering seeks to align these models to specific tasks. Unfortunately, …...

AbstractNatural language understanding (NLU) models tend to rely on spurious correlations (i.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the …...

AbstractAutomatic language processing is used frequently in the Human Resources (HR) sector for automated candidate sourcing and evaluation of resumes. These models often use pre-trained language models where it is …...

AbstractWhen working with textual data, a natural application of disentangled representations is the fair classification where the goal is to make predictions without being biased (or influenced) by sensible attributes …...

AbstractIn the presented study, we discover that the so-called “transition freedom” metric appears superior for unsupervised tokenization purposes in comparison to statistical metrics such as mutual information and conditional probability, …...