Results 1 - 10
of
404
Discovering Word Senses from Text
- In Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining
, 2002
"... Inventories of manually compiled dictionaries usually serve as a source for word senses. However, they often include many rare senses while missing corpus/domain-specific senses. We present a clustering algorithm called CBC (Clustering By Committee) that automatically discovers word senses from text ..."
Abstract
-
Cited by 293 (18 self)
- Add to MetaCart
(Show Context)
Inventories of manually compiled dictionaries usually serve as a source for word senses. However, they often include many rare senses while missing corpus/domain-specific senses. We present a clustering algorithm called CBC (Clustering By Committee) that automatically discovers word senses from text. It initially discovers a set of tight clusters called committees that are well scattered in the similarity space. The centroid of the members of a committee is used as the feature vector of the cluster. We proceed by assigning words to their most similar clusters. After assigning an element to a cluster, we remove their overlapping features from the element. This allows CBC to discover the less frequent senses of a word and to avoid discovering duplicate senses. Each cluster that a word belongs to represents one of its senses. We also present an evaluation methodology for automatically measuring the precision and recall of discovered senses. Categories and Subject Descriptors H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval---Clustering.
Evaluating Natural Language Processing Systems
, 1993
"... This report presents a detailed analysis and review of NLP evaluation, in principle and in practice. Part 1 examines evaluation concepts and establishes a framework for NLP system evaluation. This makes use of experience in the related area of information retrieval and the analysis also refers to ev ..."
Abstract
-
Cited by 145 (0 self)
- Add to MetaCart
This report presents a detailed analysis and review of NLP evaluation, in principle and in practice. Part 1 examines evaluation concepts and establishes a framework for NLP system evaluation. This makes use of experience in the related area of information retrieval and the analysis also refers to evaluation in speech processing. Part 2 surveys significant evaluation work done so far, for instance in machine translation, and discusses the particular problems of generic system evaluation. The conclusion is that evaluation strategies and techniques for NLP need much more development, in particular to take proper account of the influence of system tasks and settings. Part 3 develops a general approach to NLP evaluation, aimed at methodologically-sound strategies for test and evaluation motivated by comprehensive performance factor identification. The analysis throughout the report is supported by extensive illustrative examples. This work was carried out under the UK Science and Engineeri...
Ontological Semantics
, 2004
"... This book introduces ontological semantics, a comprehensive approach to the treatment of text meaning by computer. Ontological semantics is an integrated complex of theories, methodologies, descriptions and implementations. In ontological semantics, a theory is viewed as a set of statements determin ..."
Abstract
-
Cited by 126 (37 self)
- Add to MetaCart
(Show Context)
This book introduces ontological semantics, a comprehensive approach to the treatment of text meaning by computer. Ontological semantics is an integrated complex of theories, methodologies, descriptions and implementations. In ontological semantics, a theory is viewed as a set of statements determining the format of descriptions of the phenomena with which the theory deals. A theory is associated with a methodology used to obtain the descriptions. Implementations are computer systems that use the descriptions to solve specific problems in text processing. Implementations of ontological semantics are combined with other processing systems to produce applications, such as information extraction or machine translation. The theory of ontological semantics is built as a society of microtheories covering such diverse ground as specific language phenomena, world knowledge organization, processing heuristics and issues relating to knowledge representation and implementation system architecture. The theory briefly sketched above is a top-level microtheory, the ontological semantics theory per se. Descriptions in ontological semantics include text meaning representations, lexical entries, ontological concepts and instances as well as procedures for manipulating texts and their meanings. Methodologies in ontological semantics are sets of techniques and instructions for acquiring and
Automatic Cross-Language Retrieval Using Latent Semantic Indexing
, 1997
"... We describe a method for fully automated cross-language document retrieval in which no query translation is required. Queries in one language can retrieve documents in other languages (as well as the original language). This is accomplished by a method that automatically constructs a multilingual se ..."
Abstract
-
Cited by 96 (2 self)
- Add to MetaCart
We describe a method for fully automated cross-language document retrieval in which no query translation is required. Queries in one language can retrieve documents in other languages (as well as the original language). This is accomplished by a method that automatically constructs a multilingual semantic space using Latent Semantic Indexing (LSI). Strong test results for the cross-language LSI (CLLSI) method are presented for a new French-English collection. We also provide evidence that this automatic method performs comparably to a retrieval method based on machine translation (MT-LSI), and explore several practical training methods. By all available measures, CL-LSI performs quite well and is widely applicable. Introduction Cross-language LSI (CL-LSI) is a fully automatic method for cross-language document retrieval in which no query translation is required. Queries in one language can retrieve documents in other languages (as well as the original language). This is accomplished b...
Data mining for hypertext: A tutorial survey
- ACM SIGKDD Explorations
, 2000
"... With over 800 million pages covering most areas of human endeavor, the World-wide Web is a fertile ground for data mining research to make a difference to the effectiveness of information search. Today, Web surfers access the Web through two dominant interfaces: clicking on hyperlinks and searching ..."
Abstract
-
Cited by 91 (0 self)
- Add to MetaCart
(Show Context)
With over 800 million pages covering most areas of human endeavor, the World-wide Web is a fertile ground for data mining research to make a difference to the effectiveness of information search. Today, Web surfers access the Web through two dominant interfaces: clicking on hyperlinks and searching via keyword queries. This process is often tentative and unsatisfactory. Better support is needed for expressing one's information need and dealing with a search result in more structured ways than available now. Data mining and machine learning have significant roles to play towards this end. In this paper we will survey recent advances in learning and mining problems related to hypertext in general and the Web in particular. We will review the continuum of supervised to semi-supervised to unsupervised learning problems, highlight the specific challenges which distinguish data mining in the hypertext domain from data mining in the context of data warehouses, and summarize the key areas of ...
Learning Dependency Translation Models as Collections of Finite State Head Transducers
- Computational Linguistics
, 2000
"... The paper defines weighted head transducers,finite-state machines that perform middle-out string transduction. These transducers are strictly more expressive than the special case of standard leftto-right finite-state transducers. Dependency transduction models are then defined as collections of wei ..."
Abstract
-
Cited by 77 (3 self)
- Add to MetaCart
The paper defines weighted head transducers,finite-state machines that perform middle-out string transduction. These transducers are strictly more expressive than the special case of standard leftto-right finite-state transducers. Dependency transduction models are then defined as collections of weighted head transducers that are applied hierarchically. A dynamic programming search algorithm is described for finding the optimal transduction of an input string with respect to a dependency transduction model. A method for automatically training a dependency transduction model from a set of input-output example strings is presented. The method first searches for hierarchical alignments of the training examples guided by correlation statistics, and then constructs the transitions of head transducers that are consistent with these alignments. Experimental results are given for applying the training method to translation from English to Spanish and Japanese. 1.
Automatic Cross-Language Information Retrieval using Latent Semantic Indexing
- Cross-Language Information Retrieval, chapter 5
, 1998
"... We descride a method for fully automated cross-language document retrieval in which no query translation is required. Queries in one language can retrieve documents in other languages (as well as the original language). This is accomplished by a method that automatically constructs a multi-lingual s ..."
Abstract
-
Cited by 62 (5 self)
- Add to MetaCart
(Show Context)
We descride a method for fully automated cross-language document retrieval in which no query translation is required. Queries in one language can retrieve documents in other languages (as well as the original language). This is accomplished by a method that automatically constructs a multi-lingual semantic space using Latent Semantic Indexing (LSI). We present strong preliminary test results for our cross-language LSI (CL-LSI) method for a French-English collection. We also provide some evidence that this automatic method performs comparably to a retrieval method based on machine translation (MT-LSI).
Interactive Translation of Conversational Speech
- Computer
, 1996
"... We present JANUS-II, a large scale system effort aimed at interactive spoken language translation. JANUS-II now accepts spontaneous conversational speech in a limited domain in English, German or Spanish and produces output in German, English, Spanish, Japanese and Korean. The challenges of coarticu ..."
Abstract
-
Cited by 62 (8 self)
- Add to MetaCart
(Show Context)
We present JANUS-II, a large scale system effort aimed at interactive spoken language translation. JANUS-II now accepts spontaneous conversational speech in a limited domain in English, German or Spanish and produces output in German, English, Spanish, Japanese and Korean. The challenges of coarticulated, disfluent, ill-formed speech are manifold, and have required advances in acoustic modeling, dictionary learning, language modeling, semantic parsing and generation, to achieve acceptable performance. A semantic “interlingua ” that represents the intended meaning of an input sentence, facilitates the generation of culturally and contextually appropriate translation in the presence of irrelevant or erroneous information. Application of statistical, contextual, prosodic and discourse constraints permits a progressively narrowing search for the most plausible interpretation of an utterance. During translation, JANUS-II produces paraphrases that are used for interactive correction of translation errors. Beyond our continuing efforts to improve robustness and accuracy, we have also begun to study possible forms of deployment. Several system prototypes have been implemented to explore translation needs in different settings: speech translation in one-on-one video conferencing, as portable mobile
Cross-View Action Recognition via View Knowledge Transfer
"... In this paper, we present a novel approach to recognizing human actions from different views by view knowledge transfer. An action is originally modelled as a bag of visual-words (BoVW), which is sensitive to view changes. We argue that, as opposed to visual words, there exist some higher level feat ..."
Abstract
-
Cited by 47 (4 self)
- Add to MetaCart
(Show Context)
In this paper, we present a novel approach to recognizing human actions from different views by view knowledge transfer. An action is originally modelled as a bag of visual-words (BoVW), which is sensitive to view changes. We argue that, as opposed to visual words, there exist some higher level features which can be shared across views and enable the connection of action models for different views. To discover these features, we use a bipartite graph to model two view-dependent vocabularies, then apply bipartite graph partitioning to co-cluster two vocabularies into visual-word clusters called bilingual-words (i.e., high-level features), which can bridge the semantic gap across viewdependent vocabularies. Consequently, we can transfer a BoVW action model into a bag-of-bilingual-words (BoBW) model, which is more discriminative in the presence of view changes. We tested our approach on the IXMAS data set and obtained very promising results. Moreover, to further fuse view knowledge from multiple views, we apply a Locally Weighted Ensemble scheme to dynamically weight transferred models based on the local distribution structure around each test example. This process can further improve the average recognition rate by about 7%. 1.
Semantic-based Transfer
, 1996
"... This article presents a new semanticbased transfer approach developed and applied within the Verbmobil Machine Translation project. We give an overview of the declarative transfer fo,'malism to- gether with its procedural realization. Our approach is discussed and compared with several other ap ..."
Abstract
-
Cited by 43 (7 self)
- Add to MetaCart
This article presents a new semanticbased transfer approach developed and applied within the Verbmobil Machine Translation project. We give an overview of the declarative transfer fo,'malism to- gether with its procedural realization. Our approach is discussed and compared with several other approaches f,'om the MT literature. The results presented in this article have been implemented and integrated into the Verbmobil system.
