Semantic interpretation of prepositions for NLP applications

Hartrumpf, Sven; Helbig, Hermann; Osswald, Rainer

doi:10.3115/1621431.1621436

Cited by 11 publications

(5 citation statements)

References 9 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence in text preprocessing, when the subject indicates that the corpus may have stopword-formed phrases, n-gramming should be done first to preserve the semantic information of these phrases. Moreover, if the NLP application involves dependency parsing or semantic reasoning, we have to be careful in removing stopwords, especially prepositions (Hartrumpf, Helbig, and Osswald 2006). For example, the sentence "The box is in the house, and the toy is in the box."…”

Section: Known Issues With Removing Stopwordsmentioning

confidence: 99%

Comparison of text preprocessing methods

Chai

2022

Nat. Lang. Eng.

View full text Add to dashboard Cite

Text preprocessing is not only an essential step to prepare the corpus for modeling but also a key area that directly affects the natural language processing (NLP) application results. For instance, precise tokenization increases the accuracy of part-of-speech (POS) tagging, and retaining multiword expressions improves reasoning and machine translation. The text corpus needs to be appropriately preprocessed before it is ready to serve as the input to computer models. The preprocessing requirements depend on both the nature of the corpus and the NLP application itself, that is, what researchers would like to achieve from analyzing the data. Conventional text preprocessing practices generally suffice, but there exist situations where the text preprocessing needs to be customized for better analysis results. Hence, we discuss the pros and cons of several common text preprocessing methods: removing formatting, tokenization, text normalization, handling punctuation, removing stopwords, stemming and lemmatization, n-gramming, and identifying multiword expressions. Then, we provide examples of text datasets which require special preprocessing and how previous researchers handled the challenge. We expect this article to be a starting guideline on how to select and fine-tune text preprocessing methods.

show abstract

Section: Known Issues With Removing Stopwordsmentioning

confidence: 99%

Comparison of text preprocessing methods

Chai

2022

Nat. Lang. Eng.

View full text Add to dashboard Cite

show abstract

“…Despite all these studies, Hartrumpf et al (2006) recalled that linguistic studies on preposition semantics have not obtained much impact on NLP applications. Litkowski and Hargraves (2005) presented The Preposition Project, which stores information of English preposition senses to be used in NLP with FrameNet 2 .…”

Section: Preposition Disambiguation In Nlpmentioning

confidence: 99%

Developing a knowledge base for preposition sense disambiguation: A view from Role and Reference Grammar and FunGramKB

Hernández-Pastor¹,

Periñán-Pascual²

2016

Onomázein

View full text Add to dashboard Cite

Prepositions represent a grammatical category of frequent use in many European languages. The combination of their semantics with other lexical categories usually makes them difficult to be computationally tractable. As far as natural language processing is concerned, some studies have contributed to make progress on the usage of prepositions. However, there still exists a need to develop a model that allows tackling the problems which result from the disambiguation of prepositional semantics. The goal of this paper is to describe a lexico-conceptual model which can store the knowledge required to disambiguate predicate prepositions, as well as how this model can be exploited by a parser to extract the semantic representation of a text. The theoretical foundation of this approach, which is grounded on the premises of Role and Reference Grammar and FunGramKB, is illustrated with temporal adjuncts expressed by prepositional phrases in English.

show abstract

“…Benamara ( 2005) used preposition semantics in a cooperative question answering system. In the context of cross-language question answering (CLQA), Hartrumpf, Helbig, and Osswald (2006) used MultiNet to interpret the semantics of German prepositions, and demonstrated that in instances where the answer passage contained a different preposition to that included in the original question, preposition semantics boosted the performance of their CLQA system. Boonthum, Toida, and Levinstein (2006) successfully applied their preposition WSD method in a paraphrase recognition task, namely, predicting that Kim covered the baby in blankets and Kim covered the baby with blankets have essentially the same semantics.…”

Section: Applicationsmentioning

confidence: 99%