In this paper, we investigate the impact of context for the paraphrase ranking task, comparing and quantifying results for multi-word expressions and single words. We focus on systematic integration of existing paraphrase resources to produce paraphrase candidates and later ask human annotators to judge paraphrasability in context. We first conduct a paraphrase-scoring annotation task with and ...

An important challenge for the automatic analysis of English written text is the abundance of noun compounds: sequences of nouns acting as a single noun. In our view, their semantics is best characterized by the set of all possible paraphrasing verbs, with associated weights, e.g., malaria mosquito is carry (23), spread (16), cause (12), transmit (9), etc. Using Amazon’s Mechanical Turk, we col...

String comparison methods such as BLEU (Papineni et al., 2002) are the de facto standard in MT evaluation (MTE) and in MT system parameter tuning (Och, 2003). It is difficult for these metrics to recognize legitimate lexical and grammatical paraphrases, which is important for MT system tuning (Madnani, 2010). We present two methods to address this: a shallow lexical substitution technique and a...

Using a forced-choice question-answering paradigm, K. Christianson, A. Hollingworth, J. F. Halliwell, and F. Ferreira (2001) showed that the original misinterpretation built during the analysis of a garden-path sentence lingers even after reanalysis has occurred. However, their methodology has been questioned (R. P. G. van Gompel, M. J. Pickering, J. Pearson, & G. Jacob, 2006). In this study, t...

Data-driven approaches to sentence compression define the task as dropping any subset of words from the input sentence while retaining important information and grammaticality. We show that only 16% of the observed compressed sentences in the domain of subtitling can be accounted for in this way. We argue that this is partly due to the lack of appropriate evaluation material and estimate that a...

We present an experiment in extracting collocations from the FrameNet corpus, specifically, support verbs such as direct in Environmentalists directed strong criticism at world leaders. Support verbs do not contribute meaning of their own and the meaning of the construction is provided by the noun; the recognition of support verbs is thus useful in text understanding. Having access to a list of...

Paraphrasing methods recognize, generate, or extract phrases, sentences, or longer natural language expressions that convey almost the same information. Textual entailment methods, on the other hand, recognize, generate, or extract pairs of natural language expressions, such that a human who reads (and trusts) the first element of a pair would most likely infer that the other element is also tr...

We propose a method of synonymous paraphrasing of a text based on WordNet synonymy data and Internet statistics of stable word combinations (collocations). Given a text, we look for words or expressions in it for which WordNet provides synonyms, and substitute them with such synonyms only if the latter form valid collocations with the surrounding words according to the statistics gathered from ...

This paper describes our approaches to paraphrase recognition in Twitter organized as task 1 in Semantic Evaluation 2015. Lots of approaches have been proposed to address the paraphrasing task on conventional texts ( surveyed in (Madnani and Dorr, 2010)). In this work we examined the effectiveness of various linguistic features proposed in traditional paraphrasing task on informal texts, (i.e.,...

This paper addresses the issue of post-transfer process in paraphrasing. Our previous investigation into transfer errors revealed that case assignment tends to be incorrect, irrespective of the types of transfer in lexical and structural paraphrasing of Japanese sentences [3]. Motivated by this observation, we propose an empirical method to detect incorrect case assignments. Our error detection...