Paraphrase Relations Research Articles

Analisis Kohesi Leksikal dan Gramatikal Serta Koherensi dalam Teks Diskusi

<p>Writing discussion text is a skill that must be mastered by junior high school students. However, in writing discussion texts the connectedness and linkage of sentences has not received serious attention, especially the use of lexical and grammatical cohesion and coherence. In this regard, the purpose of this study was to find out the inappropriate use of lexical and grammatical cohesion and coherence in the discussion texts of SMP Negeri Jakarta Timur students. This research deals with the object of study of the discussion texts of class IX students of State Middle School in East Jakarta as many as 602 texts. By random sampling, 64 discussion texts were selected and 585 sentences were collected. This is done by analyzing each sentence in the discussion text regarding the inappropriate use of lexical and grammatical cohesion and its coherence. Data were analyzed using a qualitative description method. The instrument used in this study is the human instrument. The results of this study indicate that the use of markers of lexical and grammatical cohesion and coherence is incorrect in 112 sentences or 19.15%. The use of lexical cohesion markers includes the use of repetition of 9 sentences or 1.53%, synonyms of 2 or 0.34%, antonyms of 1 sentence or 0.17%, and collocation of 2 sentences or 0.34%. The use of grammatical cohesion markers includes the use of references in 21 sentences or 3.59%, ellipsis 10 sentences or 1.71%, and conjunctions 33 sentences or 5.64%. The use of coherence markers includes the use of causal relations 6 sentences or 1.03%, affirmative relations 2 sentences or 0.34%, summation relations 5 sentences or 0.85%, conditional relations 2 sentences or 0.34%, relations purpose-conditions 2 sentences or 0.34%, contradictory relations 2 sentences or 0.34%, overgeneralization 2 sentences or 0.34%, and paraphrase relations 10 sentences .or 1.71%.</p><p> </p><p>Keywords: Lexical Cohesion, Grammatical Cohesion, Coherence, Discussion Text</p>si

Automatic Construction of Fine-Grained Paraphrase Corpora System Using Language Inference Model

Paraphrase detection and generation are important natural language processing (NLP) tasks. Yet the term paraphrase is broad enough to include many fine-grained relations. This leads to different tolerance levels of semantic divergence in the positive paraphrase class among publicly available paraphrase datasets. Such variation can affect the generalisability of paraphrase classification models. It may also impact the predictability of paraphrase generation models. This paper presents a new model which can use few corpora of fine-grained paraphrase relations to construct automatically using language inference models. The fine-grained sentence level paraphrase relations are defined based on word and phrase level counterparts. We demonstrate that the fine-grained labels from our proposed system can make it possible to generate paraphrases at desirable semantic level. The new labels could also contribute to general sentence embedding techniques.

Extracting Lexically Divergent Paraphrases from Twitter

We present MultiP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter. We jointly model paraphrase relations between word and sentence pairs and assume only sentence-level annotations during learning. Using this principled latent variable model alone, we achieve the performance competitive with a state-of-the-art method which combines a latent space model with a feature-based supervised classifier. Our model also captures lexically divergent paraphrases that differ from yet complement previous methods; combining our model with previous work significantly outperforms the state-of-the-art. In addition, we present a novel annotation methodology that has allowed us to crowdsource a paraphrase corpus from Twitter. We make this new dataset available to the research community.

Like subject verbs and causal clauses in English

Perlmutter claimed (Perlmutter, 1968) that the like subject constraint in English is a deep structure constraint. Apart from being a contribution to a theory of filtering devices in natural languages, this claim is of interest because it is based on the assignment of abstract deep structures containing causal clauses which do not appear in surface structure. For example, Perlmutter proposed deriving the sentence:(1) ( = (7)) I tried to be arrested.from the deep structures:rather than from the more conservative:(3) ( = (9)) I tried [Pro arrest I]Like other proposed abstract deep structures, (2) brings out the meaning of the sentence; it predicts paraphrase relations between (1) and the sentences:Perlmutter presented independent evidence for this analysis, but he also used it to explain away what would otherwise have been counterexample to the claim that the like subject constraint holds over deep structures (the ‘deep subject hypothesis’).