Formal Semantics in the Real World
GoTAL '08 Proceedings of the 6th international conference on Advances in Natural Language Processing
Assessing the impact of frame semantics on textual entailment
Natural Language Engineering
A survey of paraphrasing and textual entailment methods
Journal of Artificial Intelligence Research
Exploiting paraphrases and deferred sense commitment to interpret questions more reliably
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Generating phrasal and sentential paraphrases: A survey of data-driven methods
Computational Linguistics
Statistical metaphor processing
Computational Linguistics
Hi-index | 0.00 |
Recognizing and generating textual entailment and paraphrases are regarded as important technologies in a broad range of NLP applications, including, information extraction, summarization, question answering, information retrieval, machine translation and text generation. Both textual entailment and paraphrasing address relevant aspects of natural language semantics. Entailment is a directional relation between two expressions in which one of them implies the other, whereas paraphrase is a relation in which two expressions convey essentially the same meaning. Indeed, paraphrase can be defined as bi-directional entailment. While it may be debatable how such semantic definitions can be made well-founded, in practice we have already seen evidence that such knowledge is essential for many applications. There have been two lines of workshops in this field. One is a series of three workshops on paraphrasing -- in Tokyo 2001, in Sapporo at ACL-2003 and in Jeju at IJCNLP-2005. The other is the Workshop on Empirical Modeling of Semantic Equivalence and Entailment (at ACL-2005), and two workshops of the previous PASCAL Recognizing Textual Entailment (RTE) Challenges (2005 and 2006). We combine those two lines of similar effort together at this workshop in order to see the convergence of the field and exchange ideas among a wider audience. The workshop has two parts. The first is the general session where submission was open, which covers a wide variety of topics including knowledge formalisms and resources and techniques for acquiring and utilizing knowledge. The second part is the concluding workshop of the 3rd PASCAL RTE Challenge, the primary benchmark for textual entailment recognition systems (see the RTE-3 organizers paper). The workshop program includes the general session papers and selected presentations and a poster session of participating RTE-3 systems.