Autumn ’16, M 10:45–12:30, Caldwell Lab 183
Instructor: Michael White
Recognizing and Generating Paraphrases
There’s more than one way to skin a cat — in other words, Dermis and feline can be divorced by manifold methods (internet), There are more ways to kill a dog than hanging (1678), or TIMTOWTDI, i.e. There is more than one way to do it (Perl motto).
The myriad ways in which the same idea can be expressed in natural language is a central problem in computational linguistics, posing difficult challenges for tasks such as information extraction, question answering and summarization that require some degree of paraphrase identification. At the same time, the periphrastic capabilities found in language offer opportunities for avoiding repetition and varying complexity or expressiveness in natural language generation.
In this seminar, we will read and discuss seminal and recent research on recognizing and generating paraphrases, with an eye towards applications including question answering, text simplification, and data augmentation. Topics will be drawn from those listed below, as well as any related ones suggested by student input.
- paraphrase identification
- paraphrase resources
- paraphrase alignment
- paraphrasing as monolingual machine translation
- paraphrasing applications: question answering, text
simplification, data augmentation
Students will be expected to actively participate in the discussion and research carried out in the seminar. As detailed below, students will be required to facilitate discussions and post questions on the readings in advance, as well as locate relevant background/tutorial materials. Additionally, students taking the course for 3 credits will be required to carry out a class project on a topic related to the seminar; alternatively, for students already working on a related topic, integrating their focus into the seminar will be an option.
Ling 5802 or equivalent, or permission of the instructor.
We’ll use Carmen to schedule discussion facilitators and post advance questions on the readings, as well as links to background/tutorial materials. We’ll also use it for submitting project documents.
Class participation (25%)
We are aiming for a dynamic discussion of papers, not death by powerpoint. Thus, we plan on taking a page from Eric Fosler-Lussier’s playbook, and requiring everyone (this includes you!) to post at least one question to the discussion list on Carmen by 8 p.m. the evening before each week’s readings will be discussed. Participants should also feel free to share their (initial) thoughts and views of the papers in their posts. In particular, questions of the type “What did they mean by X” or “Why did they do X instead of Y” are encouraged. Remember that most of the papers are targeted to people who are already expert in the area, so you shouldn’t expect to alway understand everything. Airing such questions can help everyone gain a better understanding of the paper — even those who thought they understood it!
Additionally, for this year’s seminar we are going to split each week’s meetings into one part devoted to the primary readings and one part devoted to background/tutorial materials, which students will be responsible for locating and going over in class. Thus, the expected schedule for each week is as follows:
- Tuesday: Main readings for the next week assigned
- Thursday: Skim readings, looking for issues or techniques where background/tutorial materials would be helpful; start scouring web for any such materials
- Friday: Post links to background/tutorial materials on Carmen by 8 p.m., including an explanation of what was found to be helfpul
- Sunday: Post questions on main readings on Carmen by 8 p.m.
- Monday: Go over background/tutorial materials and discuss readings
Facilitating discussions (25%)
Each week’s meeting will have a discussion facilitator. For the main readings, the facilitator should look over the posted questions and choose a subset for discussion. In class, the facilitator should start the session with a brief, five to ten minute summary of the papers, including the highlights and lowlights. Following the opening summary, the facilitator is responsible for managing the discussion, and ensuring that as many viewpoints are heard as possible.
For the part of the meeting on background/tutorial materials, the facilitator should come prepared to go over the materials that s/he found, as well as to determine when it would make sense ask other participants to go through the materials they found. Note that participants other than the facilitator should therefore also come prepared to go over the background/tutorial materials they found, at least briefly.
Students will be required to facilitate one or two sessions during the course. If the discussion does not take up the entire class period, the remaining time may be used to (informally) discuss class projects.
Term project (50%)
As noted above, students taking the course for 3 credits will be required to carry out a term project, either alone or in a team setting. A project sketch will be required to be presented informally in class for brainstorming during the eighth week, followed by a presentation during the last week of class, and a final report by the day the final exam would be held (if there were one).
For students taking the course for 1 credit, no project will be required, and class participation and facilitating discussions will each count for half of the class requirements.
The topics and readings we expect to cover are listed below; these will be refined as the course progresses.
Stephen Wan, Mark Dras, Robert Dale and Cecile Paris. 2006. Using Dependency-Based Features to Take the ‘Para-farce’ out of Paraphrase. In Proceedings of the Australasian Language Technology Workshop 2006.
Dipanjan Das and Noah Smith. 2009. Paraphrase Identification as Probabilistic Quasi-Synchronous Recognition. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP.
Arpita Das, Harish Yenala, Manoj Chinnakotla and Manish Shrivastava. 2016. Together we stand: Siamese Networks for Similar Question Retrieval. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016).
- Jonas Mueller and Aditya Thyagarajan. 2016. Siamese Recurrent Architectures for Learning Sentence Similarity. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16).
- Wenpeng Yin, Hinrich Schütze, Bing Xiang and Bowen Zhou. 2016. ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs. Transactions of the Association of Computational Linguistics, 4(1):259–272.
Hadi Amiri, Philip Resnik, Jordan Boyd-Graber and Hal Daumé III. 2016. Learning Text Pair Similarity with Context-sensitive Autoencoders. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016).
Juri Ganitkevitch, Benjamin Van Durme and Chris Callison-Burch. 2013. PPDB: The Paraphrase Database. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
- John Wieting, Mohit Bansal, Kevin Gimpel, Karen Livescu and Dan Roth. 2015. From Paraphrase Database to Compositional Paraphrase Model and Back. Transactions of the Association of Computational Linguistics, 3(1):345–358.
Ellie Pavlick, Pushpendre Rastogi, Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2015. PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.
Anne Cocos and Chris Callison-Burch. 2016. Clustering Paraphrases by Word Sense. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
- Ivan A. Sag, Timothy Baldwin, Francis Bond, Ann Copestake and Dan Flickinger. 2002. Multiword Expressions: A Pain in the Neck for NLP. In Lecture Notes in Computer Science, 2276:1–15.
- Wenpeng Yin and Hinrich Schütze. 2015. Discriminative Phrase Embedding for Paraphrase Identification. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
- Kapil Thadani, Scott Martin and Michael White. 2012. A Joint Phrasal and Dependency Model for Paraphrase Alignment. In Proc. of COLING 2012. (poster)
Md Arafat Sultan, Steven Bethard, and Tamara Sumner. 2015. Feature-Rich Two-Stage Logistic Regression for Monolingual Alignment. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.
- Wei Xu, Alan Ritter, Chris Callison-Burch, William B. Dolan and Yangfeng Ji. 2014. Extracting Lexically Divergent Paraphrases from Twitter. Transactions of the Association for Computational Linguistics, 2(1):435–448.
- Ajda Gokcen, Evan Jaffe, Johnsey Erdmann, Michael White and Douglas Danforth. 2016. A Corpus of Word-Aligned Asked and Anticipated Questions in a Virtual Patient Dialogue System. In Proc. of the 10th edition of the Language Resources and Evaluation Conference (LREC 2016).
- Wenpeng Yin and Hinrich Schütze. 2016. Why and How to Pay Different Attention to Phrase Alignments of Different Intensities. arXiv preprint.
Paraphrasing as Monolingual Machine Translation
Minh-Thang Luong, Hieu Pham and Christopher D. Manning. 2015. Effective Approaches to Attention-based Neural Machine Translation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.
- Dzmitry Bahdanau, KyungHyun Cho and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In Proceedings of ICLR 2015.
- Zhaopeng Tu, Zhengdong Lu, Yang Liu, Xiaohua Liu and Hang Li. 2016. Modeling Coverage for Neural Machine Translation. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.
Paraphrasing Applications: Question Answering, Text
Simplification, Data Augmentation
- Iulian Serban, Alberto García-Durán, Çaglar Gülçehre, Sungjin Ahn, A. P. Sarath Chandar, Aaron C. Courville and Yoshua Bengio. 2016. Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.
- Manjuan Duan, Ethan Hill and Michael White. 2016. Generating Disambiguating Paraphrases for Structurally Ambiguous Sentences. In Proc. of the Tenth Linguistic Annotation Workshop at ACL 2016 (LAW-X).
- Mandya Angrosh and Advaith Siddharthan. 2014. Text simplification using synchronous dependency grammars: Generalising automatically harvested rules. In Proceedings of the 8th International Natural Language Generation Conference (INLG-14).
- Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen and Chris Callison-Burch. 2016. Optimizing Statistical Machine Translation for Text Simplification. Transactions of the Association for Computational Linguistics, 4(1):401–415.
Policy on Academic Misconduct
As with any class at this university, students are required to follow the Ohio State Code of Student Conduct. In particular, note that students are not allowed to, among other things, submit plagiarized (copied but unacknowledged) work for credit. If any violation occurs, the instructor is required to report the violation to the Council on Academic Misconduct.
Students with Disabilities
Students who need an accommodation based on the impact of a disability should contact me to arrange an appointment as soon as possible to discuss the course format, to anticipate needs, and to explore potential accommodations. I rely on the Office of Disability Services for assistance in verifying the need for accommodations and developing accommodation strategies. Students who have not previously contacted the Office for Disability Services are encouraged to do so (292-3307; http://www.ods.ohio-state.edu).
This syllabus is subject to change. All important changes will be made in
writing (email), with ample time for adjustment.