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 true. Paraphrasing can be seen as bidirectional textual entailment and methods from the two areas are often similar. Both kinds of methods are useful, at least in principle, in a wide range of natural language processing applications, including question answering, summarization, text generation, and machine translation. We summarize key ideas from the two areas by considering in turn recognition, generation, and extraction methods, also pointing to prominent articles and resources.

We challenge the NLP community to participate in a large-scale, distributed effort to design and build resources for developing and evaluating solutions to new and existing NLP tasks in the context of Recognizing Textual Entailment. We argue that the single global label with which RTE examples are annotated is insufficient to effectively evaluate RTE system performance; to promote research on smaller, related NLP tasks, we believe more detailed annotation and evaluation are needed, and that this effort will benefit not just RTE researchers, but the NLP community as a whole. We use insights from successful RTE systems to propose a model for identifying and annotating textual inference phenomena in textual entailment examples. We present the results of a pilot annotation study that show this model is feasible and the results immediately useful. 1

In this article, an original view on how to improve phrase translation estimates is proposed. This proposal is grounded on two main ideas: first, that appropriate examples of a given phrase should participate more in building its translation distribution; second, that paraphrases can be used to better estimate this distribution. Initial experiments provide evidence of the potential of our approach and its implementation for effectively improving translation performance. 1

We present a general method for incorporating an “expert ” model into a Statistical Machine Translation (SMT) system, in order to improve its performance on a particular “area of expertise”, and apply this method to the specific task of finding adequate replacements for Out-of-Vocabulary (OOV) words. Candidate replacements are paraphrases and entailed phrases, obtained using monolingual resources. These candidate replacements are transformed into “dynamic biphrases”, generated at decoding time based on the context of each source sentence. Standard SMT features are enhanced with a number of new features aimed at scoring translations produced by using different replacements. Active learning is used to discriminatively train the model parameters from human assessments of the quality of translations. The learning framework yields an SMT system which is able to deal with sentences containing OOV words but also guarantees that the performance is not degraded for input sentences without OOV words. Results of experiments on English-French translation show that this method outperforms previous work addressing OOV words in terms of acceptability. 1

We report results on translation of SMS messages from Haitian Creole to English. We show improvements by applying spell checking techniques to unknown words and creating a lattice with the best known spelling equivalents. We also used a small cleaned corpus to train a cleaning model that we applied to the noisy corpora. 1

We present a method that paraphrases a given sentence by first generating candidate paraphrases and then ranking (or classifying) them. The candidates are generated by applying existing paraphrasing rules extracted from parallel corpora. The ranking component considers not only the overall quality of the rules that produced each candidate, but also the extent to which they preserve grammaticality and meaning in the particular context of the input sentence, as well as the degree to which the candidate differs from the input. We experimented with both a Maximum Entropy classifier and an SVR ranker. Experimental results show that incorporating features from an existing paraphrase recognizer in the ranking component improves performance, and that our overall method compares well against a state of the art paraphrase generator, when paraphrasing rules apply to the input sentences. We also propose a new methodology to evaluate the ranking components of generate-and-rank paraphrase generators, which evaluates them across different combinations of weights for grammaticality, meaning preservation, and diversity. The paper is accompanied by a paraphrasing dataset we constructed for evaluations of this kind. 1