Use of a lexical knowledge base for information access systems

Terminology ◽  
1998 ◽  
Vol 5 (2) ◽  
pp. 203-228 ◽  
Author(s):  
Bernardo Magnini
Keyword(s):  
Natural Language ◽  
Semantic Representation ◽  
Information Access ◽  
Dialogue Systems ◽  
Complex Sentence ◽  
Lexical Resources ◽  
Lexical Knowledge ◽  
Word Level ◽  
Sentence Level

The role of generic lexical resources as well as specialized terminology is crucial in the design of complex dialogue systems, where a human interacts with the computer using Natural Language. Lexicon and terminology are supposed to store information for several purposes, including the discrimination of semantic-ally inconsistent interpretations, the use of lexical variations, the compositional construction of a semantic representation for a complex sentence and the ability to access equivalencies across different languages. For these purposes it is necessary to rely on representational tools that are both theoretically motivated and operationally well defined. In this paper we propose a solution to lexical and terminology representation which is based on the combination of a linguistically motivated upper model and a multilingual WordNet. The upper model accounts for the linguistic analysis at the sentence level, while the multilingual WordNet accounts for lexical and conceptual relations at the word level.

scholarly journals Words and patterns: lexico-grammatical patterns and semantic relations in domain-specific discourses

2011 ◽  
pp. 213 ◽  
Author(s):  
Concepción Orna-Montesinos
Keyword(s):  
Linguistic Analysis ◽  
Dual Role ◽  
Semantic Relations ◽  
Disciplinary Knowledge ◽  
Lexical Resources ◽  
Lexical Knowledge ◽  
Underlying Assumption ◽  
Construction Engineering ◽  
Domain Specific

The underlying assumption of this study is the understanding of a specialized term as a summary of disciplinary knowledge, formalized at a textual level in the contextual relations which structure disciplinary lexical knowledge and are therefore essential for the successful interpretation of a text. With that aim this paper carries the analysis of the lexico-grammatical patterns which signal the hyponymy and meronymy relations of the term building, a key disciplinary concept in a corpus of construction engineering textbooks, using the WordNet database for reference. The linguistic analysis of the repertoire of lexico-grammatical patterns employed brings to the fore the dual role of hyponymy and meronymy as both semantic and metalinguistic discourse-organizing lexical resources, key in the rhetorical organization of the discourse of this discipline.

scholarly journals Introduction to the Special Issue on Cross-Language Algorithms and Applications

2016 ◽  
Vol 55 ◽  
pp. 1-15
Author(s):  
Marta R. Costa-jussà ◽  
Srinivas Bangalore ◽  
Patrik Lambert ◽  
Lluís Màrquez ◽  
Elena Montiel-Ponsoda
Keyword(s):  
Artificial Intelligence ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Information Access ◽  
Special Issue ◽  
Lexical Resources ◽  
Global Nature ◽  
Cross Lingual ◽  
Cross Language

With the increasingly global nature of our everyday interactions, the need for multilin- gual technologies to support efficient and effective information access and communication cannot be overemphasized. Computational modeling of language has been the focus of Natural Language Processing, a subdiscipline of Artificial Intelligence. One of the current challenges for this discipline is to design methodologies and algorithms that are cross- language in order to create multilingual technologies rapidly. The goal of this JAIR special issue on Cross-Language Algorithms and Applications (CLAA) is to present leading re- search in this area, with emphasis on developing unifying themes that could lead to the development of the science of multi- and cross-lingualism. In this introduction, we provide the reader with the motivation for this special issue and summarize the contributions of the papers that have been included. The selected papers cover a broad range of cross-lingual technologies including machine translation, domain and language adaptation for sentiment analysis, cross-language lexical resources, dependency parsing, information retrieval and knowledge representation. We anticipate that this special issue will serve as an invaluable resource for researchers interested in topics of cross-lingual natural language processing.

scholarly journals Learning semantic sentence representations from visually grounded language without lexical knowledge

2019 ◽  
Vol 25 (4) ◽  
pp. 451-466 ◽  
Author(s):  
Danny Merkx ◽  
Stefan L. Frank
Keyword(s):  
Visual Information ◽  
State Of The Art ◽  
Approaches To Learning ◽  
Semantic Content ◽  
Lexical Knowledge ◽  
Multimodal Data ◽  
Word Level ◽  
Current State ◽  
Sentence Level ◽  
Benchmark Datasets

AbstractCurrent approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word embeddings. We use a multimodal sentence encoder trained on a corpus of images with matching text captions to produce visually grounded sentence embeddings. Deep Neural Networks are trained to map the two modalities to a common embedding space such that for an image the corresponding caption can be retrieved and vice versa. We show that our model achieves results comparable to the current state of the art on two popular image-caption retrieval benchmark datasets: Microsoft Common Objects in Context (MSCOCO) and Flickr8k. We evaluate the semantic content of the resulting sentence embeddings using the data from the Semantic Textual Similarity (STS) benchmark task and show that the multimodal embeddings correlate well with human semantic similarity judgements. The system achieves state-of-the-art results on several of these benchmarks, which shows that a system trained solely on multimodal data, without assuming any word representations, is able to capture sentence level semantics. Importantly, this result shows that we do not need prior knowledge of lexical level semantics in order to model sentence level semantics. These findings demonstrate the importance of visual information in semantics.

Geographically Aware Information Access with Geoparsing, Geocoding, and Georeferencing

2013 ◽  
Author(s):  
Lara Samulenok ◽  
Victoria L. Rubin
Keyword(s):  
Information Systems ◽  
Natural Language ◽  
Information Seeking ◽  
Information Access ◽  
Position Paper ◽  
Geospatial Information ◽  
Langage Naturel ◽  
Systèmes D’Information ◽  
Geospatial Information Systems

This position paper reviews and exemplifies advances in geospatial information systems and applications involving geospatial information and natural language. We discuss the role of geographically aware information access in human information behaviours such as information seeking, retrieval, and use, and highlight the role of automation in enriching current geospatial metadata.Cet exposé de position dresse et illustre les avancées dans le domaine des systèmes d’information géospatiale et des applications faisant appel à de l’information géospatiale et au langage naturel. On discute du rôle de l’accès à de l’information géographique relativement aux comportements informationnels tels que la recherche, le repérage et l’utilisation et on présente le rôle de l’automatisation dans l’enrichissement des métadonnées géospatiales actuelles.

scholarly journals Role of expectation and working memory constraints in Hindi comprehension: An eyetracking corpus analysis

2017 ◽  
Vol 10 (2) ◽  
Author(s):  
Arpit Agrawal ◽  
Sumeet Agarwal ◽  
Samar Husain
Keyword(s):  
Eye Tracking ◽  
Sentence Processing ◽  
Sentence Comprehension ◽  
Fixation Time ◽  
Storage Cost ◽  
Word Level ◽  
Total Fixation ◽  
Sentence Level ◽  
Cost Metrics

We used the Potsdam-Allahabad Hindi eye-tracking corpus to investigate the role of word-level and sentence-level factors during sentence comprehension in Hindi. Extending previous work that used this eye-tracking data, we investigate the role of surprisal and retrieval cost metrics during sentence processing. While controlling for word-level predictors (word complexity, syllable length, unigram and bigram frequencies) as well as sentence-level predictors such as integration and storage costs, we find a significant effect of surprisal on first-pass reading times (higher surprisal value leads to increase in FPRT). Effect of retrieval cost was only found for a higher degree of parser parallelism. Interestingly, while surprisal has a significant effect on FPRT, storage cost (another prediction-based metric) does not. A significant effect of storage cost shows up only in total fixation time (TFT), thus indicating that these two measures perhaps capture different aspects of prediction. The study replicates previous findings that both prediction-based and memory-based metrics are required to account for processing patterns during sentence comprehension. The results also show that parser model assumptions are critical in order to draw generalizations about the utility of a metric (e.g. surprisal) across various phenomena in a language.

scholarly journals MKPM: Multi keyword-pair matching for natural language sentences

2021 ◽  
Author(s):  
Xin Lu ◽  
Yao Deng ◽  
Ting Sun ◽  
Yi Gao ◽  
Jun Feng ◽  
...  
Keyword(s):  
Natural Language ◽  
Word Pair ◽  
Question Answering ◽  
Semantic Relationship ◽  
Sentence Pair ◽  
Word Level ◽  
Sentence Level ◽  
Pair Matching ◽  
Task Architecture ◽  
Sentence Matching

AbstractSentence matching is widely used in various natural language tasks, such as natural language inference, paraphrase identification and question answering. For these tasks, we need to understand the logical and semantic relationship between two sentences. Most current methods use all information within a sentence to build a model and hence determine its relationship to another sentence. However, the information contained in some sentences may cause redundancy or introduce noise, impeding the performance of the model. Therefore, we propose a sentence matching method based on multi keyword-pair matching (MKPM), which uses keyword pairs in two sentences to represent the semantic relationship between them, avoiding the interference of redundancy and noise. Specifically, we first propose a sentence-pair-based attention mechanism sp-attention to select the most important word pair from the two sentences as a keyword pair, and then propose a Bi-task architecture to model the semantic information of these keyword pairs. The Bi-task architecture is as follows: 1. In order to understand the semantic relationship at the word level between two sentences, we design a word-pair task (WP-Task), which uses these keyword pairs to complete sentence matching independently. 2. We design a sentence-pair task (SP-Task) to understand the sentence level semantic relationship between the two sentences by sentence denoising. Through the integration of the two tasks, our model can understand sentences more accurately from the two granularities of word and sentence. Experimental results show that our model can achieve state-of-the-art performance in several tasks. Our source code is publicly available1.

Achieving Semantic Consistency for Multilingual Sentence Representation Using an Explainable Machine Natural Language Parser (MParser)

2021 ◽  
Vol 11 (24) ◽  
pp. 11699
Author(s):  
Peng Qin ◽  
Weiming Tan ◽  
Jingzhi Guo ◽  
Bingqing Shen ◽  
Qian Tang
Keyword(s):  
Natural Language ◽  
Semantic Representation ◽  
Word Sense ◽  
English Sentence ◽  
Heterogeneous Information ◽  
Input Method ◽  
Case Grammar ◽  
Sentence Level ◽  
Semantic Shift ◽  
Consistent Information

In multilingual semantic representation, the interaction between humans and computers faces the challenge of understanding meaning or semantics, which causes ambiguity and inconsistency in heterogeneous information. This paper proposes a Machine Natural Language Parser (MParser) to address the semantic interoperability problem between users and computers. By leveraging a semantic input method for sharing common atomic concepts, MParser represents any simple English sentence as a bag of unique and universal concepts via case grammar of an explainable machine natural language. In addition, it provides a human and computer-readable and -understandable interaction concept to resolve the semantic shift problems and guarantees consistent information understanding among heterogeneous sentence-level contexts. To evaluate the annotator agreement of MParser outputs that generates a list of English sentences under a common multilingual word sense, three expert participants manually and semantically annotated 75 sentences (505 words in total) in English. In addition, 154 non-expert participants evaluated the sentences’ semantic expressiveness. The evaluation results demonstrate that the proposed MParser shows higher compatibility with human intuitions.

scholarly journals The Role of Extension and Advisory Services in Strengthening Farmers’ Innovation Networks to Adapt to Climate Extremes

2021 ◽  
Vol 13 (4) ◽  
pp. 1941
Author(s):  
Md Kamruzzaman ◽  
Katherine Anne Daniell ◽  
Ataharul Chowdhury ◽  
Steven Crimp
Keyword(s):  
Information Access ◽  
Significant Risk ◽  
Climate Extremes ◽  
Rice Cultivation ◽  
Innovation Networks ◽  
Flash Flooding ◽  
Research Organizations ◽  
Local Input ◽  
Local Weather

There is anecdotal evidence of the effectiveness of Extension and Advisory Service (EAS) agencies for strengthening innovation networks to adapt to extreme events that impact agricultural production and productivity. In Bangladesh, the Department of Agricultural Extension (DAE) is responsible for ensuring sustainable rice farming, which is damaged by flash flooding every year. This study investigates how EAS can strengthen farmers’ innovation networks by examining DAE’s efforts to adapt rice cultivation to flash flooding. Using surveys and interviews from farmers affiliated with DAE (DAE-farmers) and farmers independent of DAE (non-DAE farmers), the effectiveness of innovation networks was examined. One of the key findings of this paper is that DAE’s efforts to strengthen the innovation networks of farmers to adapt rice cultivation to flash flooding focused on the facilitation of the agronomic network development. The organization missed the opportunity to enable the harvesting networks’ efficacy. As the harvesting activities are highly exposed to flash flooding, the absence of adequate support from the DAE and timely updates of local weather and flash flooding information indicates that farmers are still at significant risk. This study also shows the value of including both formal (e.g., EAS agencies, research organizations) and informal actors (e.g., relatives, local input dealers) in the innovation network as a way of ensuring diversity of information access.

Sign in / Sign up

Export Citation Format

Share Document