Structural Parse Tree Features for Text Representation

Massung, Sean; Zhai, ChengXiang; Hockenmaier, Julia

doi:10.1109/icsc.2013.13

Cited by 35 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Including syntactic parse information to benefit NLP models have been actively investigated in decades. Syntactic feature engineering refers to efforts to statically extract domain specific features from syntax parse tree of the given text (Massung et al, 2013;Wang et al, 2015). Recent attempts also include leveraging syntactic parse tree structure to recursively generate sentence representations bottom-up (Socher et al, 2011;Zhu et al, 2015b;Tai et al, 2015;Zhu et al, 2015a).…”

Section: Syntax Encodingmentioning

confidence: 99%

“…Syntactic parse information plays an essential role in interpreting natural languages because natural language sentences are typically structured in a linguistic grammar. As such, in many NLP applications it is desirable to extract syntactic features from text or sentences, for which there exist a rich body of literature (Baayen et al, 1996;Hirst, 2007;Massung et al, 2013;Wang et al, 2015;Socher et al, 2011;Zhu et al, 2015b;Tai et al, 2015;Zhu et al, 2015a) To date, existing approaches to exploit syntactic information can be categorized into two categories. The first category may be regarded as "syntactic feature engineering".…”

Section: Introductionmentioning

confidence: 99%

“…In such approaches, certain properties or statistics are extracted from the syntax parse tree of a sentence as the syntactical feature. For example, the extracted feature may include the depths of the tree, frequency of certain structural patterns in the tree and so on (Massung et al, 2013;Wang et al, 2015). The advantage of such a method is that the extracted feature can be used for any kind of classifier, if the feature is deemed relevant to the classification task.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Syntax Encoding with Application in Authorship Attribution

Zhang

Guo

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation. The proposed syntax encoding scheme is provably informationlossless. In specific, an embedding vector is constructed for each word in the sentence, encoding the path in the syntax tree corresponding to the word. The one-to-one correspondence between these "syntax-embedding" vectors and the words (hence their embedding vectors) in the sentence makes it easy to integrate such a representation with all word-level NLP models. We empirically show the benefits of the syntax embeddings on the Authorship Attribution domain, where our approach improves upon the prior art and achieves new performance records on five benchmarking data sets.

show abstract

Section: Syntax Encodingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Syntax Encoding with Application in Authorship Attribution

Zhang

Guo

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Massung, Zhai and Hockenmaier (2013) also make use of grammatical parse tree features, but mainly focus on their structural aspects as opposed to the syntactic category labels. In one classification task, they found these features to work well in determining the nationality of student essay writers from the CEEAUS dataset.…”

Section: Native Language Identificationmentioning

confidence: 99%

Non-native text analysis: A survey

Massung¹,

Zhai²

2015

Nat. Lang. Eng.

Self Cite

View full text Add to dashboard Cite

Non-native speakers of English far outnumber native speakers; English is the main language of books, newspapers, airports, air-traffic control, international business, academic conferences, science, technology, diplomacy, sports, international competitions, pop music, and advertising (British Council 2014). Online education in the form of massive online open courses is also primarily in English—even teaching English. This creates enormous amounts of text written by non-native speakers, which in turn generates a need for grammar correction and analysis. Even aside from massive online open courses, the number of English learners in Asia alone is in the tens of millions. In this paper, we provide a survey of the two main areas of existing work on non-native text analysis, prefaced by an overview of common datasets used by researchers, comparing their attributes and potential uses. Then, an introduction to native language identification follows: determining the native language of an author based on text in the second language. This section is subdivided into various techniques and a shared task on this classification problem. Next, we discuss non-native grammatical error correction—finding and modifying text to fix errors or to make it sound more fluent. Again, we discuss different methods before investigating a relevant shared task. Lastly, we end with conclusions and potential future directions. While this survey primarily focuses on detecting and correcting non-nativeEnglishtext, many approaches are general and can be used across any language pairing.

show abstract

“…Grounded on deception theories such as the information manipulation theory (McCornack, 1992) and the reality monitoring theory (Johnson & Raye, 1981), works that distinguish between authentic and fictitious reviews have a technical orientation. They are mostly conducted by scholars from the computer science discipline using algorithmic techniques (Feng et al, 2012;Jindal & Liu, 2008;Massung et al, 2013). They tend to rely on either the bibliometric approach or the engineering approach of investigation.…”

Section: Authentic Versus Fictitious Reviewsmentioning

confidence: 99%

Study of authentic and fictitious online reviews

Snehasish¹

View full text Add to dashboard Cite

show abstract

Structural Parse Tree Features for Text Representation

Cited by 35 publications

References 18 publications

Syntax Encoding with Application in Authorship Attribution

Syntax Encoding with Application in Authorship Attribution

Non-native text analysis: A survey

Study of authentic and fictitious online reviews

Contact Info

Product

Resources

About